Token | sn |
Token ID | 3013 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
crying | +0.032 |
weeping | +0.032 |
Ros | +0.030 |
bleeding | +0.030 |
apped | +0.030 |
Neg logit contributions | |
stalls | -0.038 |
stall | -0.036 |
fare | -0.036 |
hike | -0.035 |
banks | -0.035 |
Token | ugg |
Token ID | 6837 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
stalls | +0.013 |
stall | +0.013 |
hike | +0.012 |
banks | +0.012 |
fare | +0.012 |
Neg logit contributions | |
weeping | -0.007 |
crying | -0.007 |
bleeding | -0.007 |
Ros | -0.007 |
blood | -0.007 |
Token | led |
Token ID | 992 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Ros | +0.023 |
weeping | +0.023 |
crying | +0.023 |
ir | +0.022 |
bleeding | +0.022 |
Neg logit contributions | |
stalls | -0.032 |
stall | -0.029 |
flavors | -0.029 |
banks | -0.029 |
hike | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
weeping | +0.028 |
crying | +0.027 |
Ros | +0.027 |
bleeding | +0.027 |
ir | +0.027 |
Neg logit contributions | |
stalls | -0.051 |
stall | -0.049 |
hike | -0.049 |
flavors | -0.048 |
banks | -0.048 |
Token | t |
Token ID | 256 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
weeping | +0.029 |
crying | +0.029 |
bleeding | +0.028 |
Ros | +0.028 |
ir | +0.027 |
Neg logit contributions | |
stalls | -0.060 |
stall | -0.057 |
hike | -0.057 |
flavors | -0.056 |
banks | -0.056 |
Token | eddy |
Token ID | 21874 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
weeping | +0.044 |
Emily | +0.042 |
crying | +0.041 |
sorry | +0.039 |
blood | +0.038 |
Neg logit contributions | |
fare | -0.103 |
belts | -0.100 |
cases | -0.099 |
stalls | -0.098 |
flavors | -0.097 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
Ros | +0.129 |
ir | +0.128 |
weeping | +0.128 |
apped | +0.126 |
crying | +0.125 |
Neg logit contributions | |
stalls | -0.159 |
hike | -0.155 |
stall | -0.153 |
banks | -0.153 |
fare | -0.147 |
Token | all |
Token ID | 477 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
weeping | +0.048 |
crying | +0.047 |
bleeding | +0.046 |
Ros | +0.045 |
ir | +0.044 |
Neg logit contributions | |
stalls | -0.094 |
flavors | -0.090 |
stall | -0.088 |
hike | -0.088 |
fare | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
weeping | +0.057 |
Ros | +0.056 |
crying | +0.056 |
bleeding | +0.056 |
ir | +0.055 |
Neg logit contributions | |
stalls | -0.072 |
hike | -0.068 |
stall | -0.068 |
banks | -0.067 |
flavors | -0.067 |
Token | time |
Token ID | 640 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
weeping | +0.045 |
crying | +0.044 |
bleeding | +0.044 |
Ros | +0.044 |
ir | +0.043 |
Neg logit contributions | |
stalls | -0.028 |
stall | -0.026 |
flavors | -0.026 |
hike | -0.026 |
banks | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
crying | +0.002 |
weeping | +0.002 |
bleeding | +0.002 |
streaming | +0.002 |
ir | +0.002 |
Neg logit contributions | |
stalls | -0.002 |
banks | -0.002 |
fare | -0.002 |
hike | -0.002 |
stall | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
weeping | +0.031 |
crying | +0.030 |
bleeding | +0.029 |
Ros | +0.028 |
ir | +0.028 |
Neg logit contributions | |
stalls | -0.056 |
hike | -0.054 |
banks | -0.053 |
stall | -0.053 |
fare | -0.053 |
Token | happiest |
Token ID | 49414 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
weeping | +0.030 |
Ros | +0.029 |
crying | +0.029 |
bleeding | +0.029 |
microphone | +0.027 |
Neg logit contributions | |
stalls | -0.053 |
stall | -0.050 |
cases | -0.050 |
banks | -0.049 |
hike | -0.049 |
Token | frog |
Token ID | 21264 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
weeping | +0.095 |
crying | +0.093 |
Ros | +0.092 |
bleeding | +0.091 |
ir | +0.090 |
Neg logit contributions | |
stalls | -0.127 |
stall | -0.119 |
hike | -0.119 |
banks | -0.118 |
flavors | -0.117 |
Token | in |
Token ID | 287 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
weeping | +0.055 |
crying | +0.054 |
bleeding | +0.051 |
ir | +0.048 |
apped | +0.048 |
Neg logit contributions | |
stalls | -0.145 |
fare | -0.140 |
flavors | -0.139 |
banks | -0.139 |
hike | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
Ros | +0.067 |
bleeding | +0.065 |
weeping | +0.063 |
apped | +0.062 |
crying | +0.062 |
Neg logit contributions | |
stalls | -0.070 |
stall | -0.067 |
hike | -0.067 |
banks | -0.064 |
flavors | -0.063 |
Token | whole |
Token ID | 2187 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
bleeding | +0.098 |
apped | +0.098 |
weeping | +0.097 |
Ros | +0.097 |
crying | +0.096 |
Neg logit contributions | |
stalls | -0.092 |
hike | -0.089 |
banks | -0.087 |
stall | -0.086 |
flavors | -0.082 |
Token | wide |
Token ID | 3094 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
bleeding | +0.154 |
weeping | +0.150 |
crying | +0.148 |
blood | +0.147 |
Ros | +0.147 |
Neg logit contributions | |
stalls | -0.148 |
hike | -0.139 |
stall | -0.139 |
banks | -0.134 |
flavors | -0.130 |
Token | world |
Token ID | 995 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
weeping | +0.077 |
crying | +0.075 |
ir | +0.075 |
Ros | +0.075 |
bleeding | +0.074 |
Neg logit contributions | |
stalls | -0.084 |
hike | -0.078 |
stall | -0.078 |
flavors | -0.078 |
fare | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
weeping | +0.026 |
crying | +0.026 |
ir | +0.024 |
apped | +0.023 |
streaming | +0.023 |
Neg logit contributions | |
stalls | -0.041 |
banks | -0.040 |
flavors | -0.040 |
stall | -0.039 |
list | -0.039 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
bleeding | +0.051 |
weeping | +0.050 |
crying | +0.049 |
Ros | +0.048 |
streaming | +0.048 |
Neg logit contributions | |
stalls | -0.052 |
stall | -0.050 |
hike | -0.049 |
banks | -0.048 |
flavors | -0.047 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.58e-03 |
Pos logit contributions | |
weeping | +0.039 |
bleeding | +0.038 |
Ros | +0.038 |
crying | +0.037 |
streaming | +0.036 |
Neg logit contributions | |
stalls | -0.046 |
stall | -0.044 |
hike | -0.043 |
banks | -0.042 |
flavors | -0.042 |
Token | her |
Token ID | 607 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
w | +0.083 |
bleeding | +0.081 |
itt | +0.080 |
apped | +0.080 |
shattered | +0.078 |
Neg logit contributions | |
list | -0.058 |
shelves | -0.056 |
stalls | -0.056 |
hike | -0.055 |
experiments | -0.054 |
Token | daddy |
Token ID | 35822 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
ir | +0.027 |
Ros | +0.026 |
weeping | +0.025 |
bleeding | +0.025 |
apped | +0.025 |
Neg logit contributions | |
stalls | -0.047 |
stall | -0.046 |
hike | -0.045 |
flavors | -0.045 |
list | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
weeping | +0.086 |
crying | +0.084 |
bleeding | +0.083 |
Ros | +0.082 |
ir | +0.080 |
Neg logit contributions | |
stalls | -0.130 |
hike | -0.124 |
banks | -0.122 |
flavors | -0.122 |
stall | -0.122 |
Token | the |
Token ID | 262 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
ir | +0.027 |
Ros | +0.026 |
weeping | +0.025 |
bleeding | +0.025 |
el | +0.024 |
Neg logit contributions | |
stalls | -0.023 |
flavors | -0.021 |
hike | -0.021 |
stall | -0.021 |
list | -0.021 |
Token | t |
Token ID | 256 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
ir | +0.061 |
apped | +0.059 |
Ros | +0.056 |
apping | +0.055 |
weeping | +0.055 |
Neg logit contributions | |
stalls | -0.050 |
flavors | -0.048 |
stall | -0.048 |
hike | -0.048 |
fare | -0.046 |
Token | eddy |
Token ID | 21874 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
Emily | +0.052 |
rys | +0.048 |
microphone | +0.047 |
weeping | +0.046 |
boom | +0.045 |
Neg logit contributions | |
fare | -0.092 |
flavors | -0.091 |
belts | -0.090 |
stall | -0.090 |
stalls | -0.090 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
ir | +0.158 |
apping | +0.151 |
Ros | +0.149 |
apped | +0.148 |
itt | +0.147 |
Neg logit contributions | |
stalls | -0.124 |
banks | -0.121 |
stall | -0.120 |
bank | -0.119 |
flavors | -0.119 |
Token | tight |
Token ID | 5381 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
weeping | +0.080 |
crying | +0.079 |
bleeding | +0.078 |
Ros | +0.077 |
ir | +0.075 |
Neg logit contributions | |
stalls | -0.080 |
hike | -0.075 |
stall | -0.074 |
banks | -0.073 |
flavors | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
crying | +0.007 |
weeping | +0.007 |
bleeding | +0.007 |
streaming | +0.007 |
apped | +0.006 |
Neg logit contributions | |
stalls | -0.008 |
stall | -0.008 |
hike | -0.008 |
fare | -0.007 |
flavors | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ir | +0.036 |
bleeding | +0.034 |
weeping | +0.033 |
Ros | +0.033 |
microphone | +0.033 |
Neg logit contributions | |
stalls | -0.037 |
stall | -0.035 |
hike | -0.034 |
list | -0.034 |
banks | -0.034 |
Token | knew |
Token ID | 2993 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
weeping | +0.025 |
ir | +0.025 |
Ros | +0.025 |
bleeding | +0.024 |
crying | +0.024 |
Neg logit contributions | |
stalls | -0.023 |
hike | -0.022 |
flavors | -0.022 |
stall | -0.022 |
banks | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
Ros | +0.051 |
ir | +0.050 |
weeping | +0.049 |
bleeding | +0.048 |
crying | +0.048 |
Neg logit contributions | |
stalls | -0.052 |
stall | -0.049 |
hike | -0.048 |
flavors | -0.047 |
banks | -0.046 |
Token | c |
Token ID | 269 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
ir | +0.004 |
weeping | +0.004 |
Ros | +0.004 |
crying | +0.004 |
bleeding | +0.004 |
Neg logit contributions | |
stalls | -0.005 |
stall | -0.004 |
hike | -0.004 |
flavors | -0.004 |
banks | -0.004 |
Token | uddled |
Token ID | 32745 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
weeping | +0.017 |
Ros | +0.016 |
crying | +0.016 |
Emily | +0.016 |
Ros | +0.016 |
Neg logit contributions | |
stalls | -0.015 |
belts | -0.014 |
flavors | -0.014 |
cases | -0.014 |
stall | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
weeping | +0.021 |
crying | +0.020 |
bleeding | +0.020 |
Ros | +0.020 |
ir | +0.019 |
Neg logit contributions | |
stalls | -0.040 |
hike | -0.038 |
stall | -0.038 |
banks | -0.037 |
flavors | -0.037 |
Token | t |
Token ID | 256 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
ir | +0.050 |
Ros | +0.050 |
apped | +0.048 |
weeping | +0.047 |
streaming | +0.046 |
Neg logit contributions | |
stalls | -0.054 |
stall | -0.052 |
flavors | -0.051 |
hike | -0.051 |
fare | -0.051 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
Emily | +0.045 |
weeping | +0.041 |
Ros | +0.041 |
streaming | +0.040 |
Po | +0.038 |
Neg logit contributions | |
belts | -0.075 |
fare | -0.073 |
cases | -0.072 |
belt | -0.069 |
flavors | -0.069 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
Ros | +0.143 |
ir | +0.143 |
apped | +0.139 |
apping | +0.135 |
weeping | +0.134 |
Neg logit contributions | |
stalls | -0.141 |
stall | -0.137 |
banks | -0.135 |
bank | -0.132 |
hike | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
weeping | +0.057 |
crying | +0.057 |
bleeding | +0.056 |
Ros | +0.053 |
ir | +0.052 |
Neg logit contributions | |
stalls | -0.092 |
flavors | -0.088 |
hike | -0.087 |
stall | -0.086 |
banks | -0.085 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ir | +0.002 |
weeping | +0.002 |
bleeding | +0.002 |
Ros | +0.002 |
crying | +0.002 |
Neg logit contributions | |
stalls | -0.004 |
stall | -0.004 |
hike | -0.003 |
banks | -0.003 |
flavors | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
ir | +0.017 |
Ros | +0.016 |
apped | +0.016 |
streaming | +0.015 |
weeping | +0.015 |
Neg logit contributions | |
flavors | -0.018 |
stalls | -0.017 |
stall | -0.017 |
belts | -0.017 |
hike | -0.017 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
weeping | +0.047 |
crying | +0.047 |
bleeding | +0.046 |
Ros | +0.046 |
ir | +0.044 |
Neg logit contributions | |
stalls | -0.067 |
hike | -0.063 |
banks | -0.063 |
stall | -0.063 |
fare | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
weeping | +0.032 |
crying | +0.032 |
bleeding | +0.030 |
Ros | +0.029 |
apped | +0.029 |
Neg logit contributions | |
stalls | -0.044 |
fare | -0.043 |
stall | -0.042 |
flavors | -0.042 |
hike | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
Ros | +0.026 |
weeping | +0.026 |
ir | +0.026 |
bleeding | +0.026 |
crying | +0.026 |
Neg logit contributions | |
stalls | -0.032 |
hike | -0.030 |
stall | -0.030 |
flavors | -0.029 |
fare | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ir | +0.012 |
Ros | +0.012 |
bleeding | +0.011 |
blood | +0.011 |
apped | +0.011 |
Neg logit contributions | |
stalls | -0.016 |
hike | -0.016 |
stall | -0.015 |
banks | -0.015 |
flavors | -0.015 |
Token | blue |
Token ID | 4171 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
weeping | +0.019 |
crying | +0.019 |
bleeding | +0.019 |
Ros | +0.019 |
ir | +0.018 |
Neg logit contributions | |
stalls | -0.027 |
hike | -0.025 |
stall | -0.025 |
banks | -0.025 |
flavors | -0.025 |
Token | t |
Token ID | 256 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
Ros | +0.053 |
weeping | +0.052 |
ir | +0.051 |
crying | +0.051 |
bleeding | +0.050 |
Neg logit contributions | |
stalls | -0.068 |
stall | -0.066 |
hike | -0.065 |
banks | -0.065 |
flavors | -0.065 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
Emily | +0.045 |
weeping | +0.040 |
crying | +0.040 |
rys | +0.039 |
Po | +0.038 |
Neg logit contributions | |
fare | -0.075 |
belts | -0.074 |
cases | -0.073 |
flavors | -0.073 |
stalls | -0.072 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
Ros | +0.135 |
ir | +0.135 |
weeping | +0.131 |
apped | +0.131 |
apping | +0.128 |
Neg logit contributions | |
stalls | -0.145 |
flavors | -0.138 |
banks | -0.138 |
hike | -0.137 |
stall | -0.136 |
Token | closed |
Token ID | 4838 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
weeping | +0.063 |
crying | +0.063 |
bleeding | +0.061 |
Ros | +0.060 |
ir | +0.060 |
Neg logit contributions | |
stalls | -0.074 |
stall | -0.070 |
flavors | -0.069 |
hike | -0.069 |
banks | -0.068 |
Token | their |
Token ID | 511 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
stalls | +0.011 |
stall | +0.011 |
banks | +0.010 |
hike | +0.010 |
flavors | +0.010 |
Neg logit contributions | |
Ros | -0.008 |
weeping | -0.008 |
bleeding | -0.008 |
ir | -0.008 |
crying | -0.008 |
Token | eyes |
Token ID | 2951 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
stalls | +0.041 |
stall | +0.039 |
hike | +0.039 |
banks | +0.039 |
flavors | +0.039 |
Neg logit contributions | |
weeping | -0.011 |
Ros | -0.011 |
crying | -0.011 |
bleeding | -0.011 |
ir | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e-03 |
Pos logit contributions | |
weeping | +0.015 |
crying | +0.015 |
bleeding | +0.015 |
Ros | +0.015 |
ir | +0.015 |
Neg logit contributions | |
stalls | -0.018 |
hike | -0.017 |
stall | -0.017 |
flavors | -0.017 |
banks | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
weeping | +0.047 |
crying | +0.046 |
Ros | +0.046 |
bleeding | +0.045 |
ir | +0.044 |
Neg logit contributions | |
stalls | -0.053 |
stall | -0.050 |
hike | -0.050 |
fare | -0.049 |
banks | -0.049 |
Token | happy |
Token ID | 3772 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
ir | +0.047 |
Ros | +0.046 |
weeping | +0.046 |
bleeding | +0.045 |
el | +0.045 |
Neg logit contributions | |
stalls | -0.058 |
stall | -0.055 |
hike | -0.054 |
banks | -0.054 |
flavors | -0.054 |
Token | that |
Token ID | 326 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
ir | +0.111 |
itt | +0.102 |
el | +0.102 |
Ros | +0.100 |
ternally | +0.100 |
Neg logit contributions | |
hike | -0.065 |
stalls | -0.062 |
stall | -0.060 |
flavors | -0.059 |
list | -0.055 |
Token | her |
Token ID | 607 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
weeping | +0.089 |
ir | +0.089 |
Ros | +0.088 |
bleeding | +0.087 |
crying | +0.087 |
Neg logit contributions | |
stalls | -0.116 |
hike | -0.111 |
stall | -0.109 |
flavors | -0.108 |
banks | -0.107 |
Token | t |
Token ID | 256 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
Ros | +0.039 |
ir | +0.039 |
weeping | +0.039 |
crying | +0.038 |
apped | +0.038 |
Neg logit contributions | |
stalls | -0.049 |
hike | -0.047 |
stall | -0.047 |
flavors | -0.047 |
banks | -0.046 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
Emily | +0.057 |
sorry | +0.053 |
rys | +0.053 |
boom | +0.052 |
weeping | +0.051 |
Neg logit contributions | |
belts | -0.086 |
flavors | -0.085 |
fare | -0.084 |
cases | -0.083 |
stall | -0.081 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
ir | +0.145 |
apped | +0.138 |
apping | +0.135 |
aps | +0.134 |
Ros | +0.128 |
Neg logit contributions | |
flavors | -0.139 |
stalls | -0.138 |
hike | -0.133 |
stall | -0.132 |
banks | -0.131 |
Token | was |
Token ID | 373 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
weeping | +0.070 |
crying | +0.070 |
bleeding | +0.069 |
Ros | +0.065 |
streaming | +0.064 |
Neg logit contributions | |
stalls | -0.089 |
stall | -0.083 |
hike | -0.082 |
fare | -0.081 |
banks | -0.081 |
Token | fixed |
Token ID | 5969 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
ir | +0.062 |
weeping | +0.060 |
Ros | +0.060 |
apped | +0.059 |
el | +0.059 |
Neg logit contributions | |
stalls | -0.066 |
hike | -0.063 |
stall | -0.063 |
flavors | -0.061 |
fare | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
weeping | +0.065 |
Ros | +0.064 |
crying | +0.064 |
bleeding | +0.063 |
ir | +0.063 |
Neg logit contributions | |
stalls | -0.077 |
stall | -0.072 |
hike | -0.072 |
flavors | -0.071 |
banks | -0.071 |
Token | that |
Token ID | 326 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
ir | +0.040 |
el | +0.036 |
weeping | +0.036 |
Ros | +0.036 |
apped | +0.036 |
Neg logit contributions | |
stalls | -0.036 |
hike | -0.034 |
flavors | -0.034 |
stall | -0.032 |
belts | -0.032 |
Token | man |
Token ID | 582 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
weeping | +0.052 |
crying | +0.052 |
bleeding | +0.050 |
blood | +0.049 |
Ros | +0.049 |
Neg logit contributions | |
stalls | -0.045 |
banks | -0.043 |
hike | -0.042 |
stall | -0.040 |
fare | -0.039 |
Token | who |
Token ID | 508 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
weeping | +0.043 |
crying | +0.043 |
bleeding | +0.041 |
Ros | +0.038 |
streaming | +0.038 |
Neg logit contributions | |
stalls | -0.081 |
banks | -0.077 |
flavors | -0.077 |
hike | -0.077 |
stall | -0.076 |
Token | shielded |
Token ID | 45153 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
weeping | +0.020 |
crying | +0.019 |
Ros | +0.019 |
bleeding | +0.019 |
ir | +0.019 |
Neg logit contributions | |
stalls | -0.018 |
hike | -0.017 |
stall | -0.017 |
banks | -0.016 |
flavors | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
apped | +0.023 |
apping | +0.023 |
weeping | +0.022 |
aps | +0.021 |
itt | +0.021 |
Neg logit contributions | |
stalls | -0.020 |
flavors | -0.018 |
banks | -0.018 |
bank | -0.018 |
shelves | -0.018 |
Token | t |
Token ID | 256 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
Ros | +0.034 |
ir | +0.034 |
apped | +0.033 |
weeping | +0.033 |
crying | +0.032 |
Neg logit contributions | |
stalls | -0.041 |
flavors | -0.039 |
banks | -0.038 |
stall | -0.038 |
fare | -0.038 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
Emily | +0.040 |
weeping | +0.039 |
crying | +0.036 |
sorry | +0.035 |
Ros | +0.035 |
Neg logit contributions | |
cases | -0.090 |
fare | -0.090 |
stalls | -0.088 |
flavors | -0.087 |
stall | -0.087 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
apped | +0.137 |
ir | +0.134 |
Ros | +0.134 |
apping | +0.130 |
weeping | +0.129 |
Neg logit contributions | |
stalls | -0.147 |
banks | -0.145 |
stall | -0.142 |
hike | -0.142 |
bank | -0.141 |
Token | from |
Token ID | 422 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
weeping | +0.062 |
crying | +0.061 |
Ros | +0.060 |
bleeding | +0.060 |
ir | +0.059 |
Neg logit contributions | |
stalls | -0.082 |
stall | -0.077 |
hike | -0.077 |
flavors | -0.076 |
banks | -0.075 |
Token | harm |
Token ID | 4419 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
apped | +0.041 |
Ros | +0.040 |
ir | +0.038 |
apping | +0.037 |
aps | +0.037 |
Neg logit contributions | |
stalls | -0.049 |
stall | -0.046 |
banks | -0.046 |
hike | -0.046 |
bank | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
weeping | +0.062 |
Ros | +0.061 |
crying | +0.061 |
bleeding | +0.061 |
ir | +0.060 |
Neg logit contributions | |
stalls | -0.078 |
stall | -0.073 |
hike | -0.073 |
banks | -0.072 |
flavors | -0.072 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
bleeding | +0.051 |
ir | +0.051 |
weeping | +0.050 |
streaming | +0.049 |
microphone | +0.049 |
Neg logit contributions | |
stalls | -0.050 |
stall | -0.049 |
hike | -0.047 |
flavors | -0.046 |
fare | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
stalls | +0.033 |
hike | +0.032 |
flavors | +0.032 |
stall | +0.031 |
fare | +0.031 |
Neg logit contributions | |
crying | -0.021 |
weeping | -0.021 |
bleeding | -0.019 |
streaming | -0.018 |
ir | -0.017 |
Token | disappeared |
Token ID | 12120 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
weeping | +0.003 |
crying | +0.003 |
bleeding | +0.003 |
Ros | +0.003 |
ir | +0.003 |
Neg logit contributions | |
stalls | -0.003 |
stall | -0.003 |
hike | -0.003 |
flavors | -0.003 |
banks | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
weeping | +0.026 |
crying | +0.025 |
bleeding | +0.025 |
Ros | +0.025 |
ir | +0.025 |
Neg logit contributions | |
stalls | -0.028 |
hike | -0.027 |
stall | -0.027 |
flavors | -0.026 |
banks | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Ros | +0.021 |
eddy | +0.020 |
apping | +0.020 |
apped | +0.019 |
ooming | +0.019 |
Neg logit contributions | |
stalls | -0.017 |
stall | -0.016 |
flavors | -0.016 |
shelves | -0.015 |
hike | -0.015 |
Token | t |
Token ID | 256 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
apped | +0.037 |
ir | +0.037 |
Ros | +0.035 |
apping | +0.034 |
aps | +0.033 |
Neg logit contributions | |
stalls | -0.033 |
flavors | -0.033 |
stall | -0.033 |
fare | -0.032 |
hike | -0.031 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
weeping | +0.041 |
streaming | +0.039 |
crying | +0.038 |
Emily | +0.038 |
sorry | +0.038 |
Neg logit contributions | |
cases | -0.077 |
stall | -0.076 |
flavors | -0.075 |
fare | -0.075 |
stalls | -0.074 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
apping | +0.154 |
apped | +0.154 |
ir | +0.151 |
Ros | +0.148 |
aps | +0.145 |
Neg logit contributions | |
stalls | -0.122 |
stall | -0.121 |
flavors | -0.120 |
bank | -0.118 |
banks | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
weeping | +0.073 |
crying | +0.073 |
bleeding | +0.071 |
ir | +0.068 |
streaming | +0.067 |
Neg logit contributions | |
stalls | -0.078 |
flavors | -0.073 |
hike | -0.073 |
stall | -0.072 |
banks | -0.071 |
Token | Amy |
Token ID | 14235 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ir | +0.024 |
microphone | +0.024 |
el | +0.023 |
weeping | +0.023 |
streaming | +0.023 |
Neg logit contributions | |
stalls | -0.023 |
stall | -0.022 |
hike | -0.021 |
banks | -0.021 |
flavors | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
Ros | +0.019 |
ir | +0.019 |
weeping | +0.019 |
bleeding | +0.019 |
crying | +0.018 |
Neg logit contributions | |
stalls | -0.017 |
banks | -0.016 |
stall | -0.016 |
hike | -0.016 |
flavors | -0.016 |
Token | left |
Token ID | 1364 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
ir | +0.028 |
Ros | +0.027 |
el | +0.026 |
w | +0.026 |
itt | +0.025 |
Neg logit contributions | |
stalls | -0.024 |
stall | -0.024 |
bank | -0.023 |
banks | -0.023 |
ranc | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +9.57e-03 |
Pos logit contributions | |
stalls | +0.002 |
stall | +0.001 |
banks | +0.001 |
hike | +0.001 |
nic | +0.001 |
Neg logit contributions | |
crying | -0.001 |
weeping | -0.001 |
bleeding | -0.001 |
streaming | -0.001 |
el | -0.001 |
Token | hold |
Token ID | 1745 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
crying | +0.014 |
weeping | +0.013 |
ir | +0.013 |
bleeding | +0.013 |
streaming | +0.012 |
Neg logit contributions | |
stalls | -0.019 |
stall | -0.017 |
cases | -0.017 |
belts | -0.016 |
flavors | -0.016 |
Token | up |
Token ID | 510 |
Feature activation | -8.92e-04 |
Pos logit contributions | |
weeping | +0.005 |
Ros | +0.005 |
bleeding | +0.005 |
crying | +0.005 |
ir | +0.005 |
Neg logit contributions | |
stalls | -0.008 |
stall | -0.007 |
flavors | -0.007 |
hike | -0.007 |
fare | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
stalls | +0.002 |
hike | +0.002 |
stall | +0.002 |
banks | +0.002 |
flavors | +0.002 |
Neg logit contributions | |
weeping | -0.001 |
crying | -0.001 |
Ros | -0.001 |
bleeding | -0.001 |
ir | -0.001 |
Token | t |
Token ID | 256 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
Ros | +0.048 |
weeping | +0.048 |
ir | +0.047 |
crying | +0.047 |
bleeding | +0.046 |
Neg logit contributions | |
stalls | -0.059 |
stall | -0.056 |
hike | -0.056 |
flavors | -0.055 |
banks | -0.055 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
weeping | +0.035 |
crying | +0.033 |
bleeding | +0.031 |
blood | +0.030 |
Emily | +0.030 |
Neg logit contributions | |
flavors | -0.088 |
fare | -0.088 |
stalls | -0.088 |
stall | -0.088 |
belts | -0.087 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
ir | +0.125 |
Ros | +0.124 |
weeping | +0.124 |
apped | +0.122 |
crying | +0.120 |
Neg logit contributions | |
stalls | -0.158 |
stall | -0.153 |
hike | -0.152 |
banks | -0.151 |
flavors | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
crying | +0.057 |
weeping | +0.056 |
bleeding | +0.055 |
ir | +0.053 |
el | +0.053 |
Neg logit contributions | |
stalls | -0.081 |
flavors | -0.077 |
hike | -0.074 |
fare | -0.073 |
stall | -0.072 |
Token | In |
Token ID | 554 |
Feature activation | -5.25e-03 |
Pos logit contributions | |
ir | +0.024 |
bleeding | +0.024 |
weeping | +0.023 |
blood | +0.023 |
el | +0.023 |
Neg logit contributions | |
stalls | -0.020 |
banks | -0.018 |
hike | -0.018 |
stall | -0.018 |
list | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
stalls | +0.008 |
stall | +0.008 |
hike | +0.008 |
list | +0.008 |
flavors | +0.007 |
Neg logit contributions | |
Ros | -0.008 |
weeping | -0.008 |
bleeding | -0.008 |
apped | -0.008 |
ir | -0.008 |
Token | end |
Token ID | 886 |
Feature activation | +9.47e-03 |
Pos logit contributions | |
stalls | +0.018 |
stall | +0.017 |
flavors | +0.017 |
hike | +0.017 |
fare | +0.017 |
Neg logit contributions | |
weeping | -0.019 |
crying | -0.019 |
bleeding | -0.019 |
Ros | -0.019 |
ir | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
Ros | +0.027 |
ir | +0.027 |
weeping | +0.026 |
bleeding | +0.026 |
apped | +0.025 |
Neg logit contributions | |
stalls | -0.024 |
hike | -0.023 |
stall | -0.022 |
banks | -0.022 |
flavors | -0.022 |
Token | leave |
Token ID | 2666 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
Ros | +0.045 |
apped | +0.044 |
weeping | +0.044 |
ir | +0.044 |
bleeding | +0.044 |
Neg logit contributions | |
stalls | -0.036 |
hike | -0.035 |
banks | -0.034 |
stall | -0.033 |
fare | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
weeping | +0.048 |
crying | +0.048 |
bleeding | +0.047 |
Ros | +0.046 |
ir | +0.045 |
Neg logit contributions | |
stalls | -0.065 |
hike | -0.061 |
stall | -0.061 |
banks | -0.060 |
flavors | -0.060 |
Token | soft |
Token ID | 2705 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
Ros | +0.049 |
ir | +0.049 |
weeping | +0.049 |
bleeding | +0.047 |
crying | +0.047 |
Neg logit contributions | |
stalls | -0.055 |
stall | -0.052 |
hike | -0.052 |
flavors | -0.051 |
banks | -0.051 |
Token | t |
Token ID | 256 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
weeping | +0.063 |
crying | +0.062 |
Ros | +0.062 |
bleeding | +0.061 |
ir | +0.061 |
Neg logit contributions | |
stalls | -0.075 |
hike | -0.070 |
stall | -0.070 |
banks | -0.069 |
flavors | -0.069 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
Emily | +0.037 |
weeping | +0.036 |
streaming | +0.034 |
crying | +0.033 |
Ros | +0.033 |
Neg logit contributions | |
stall | -0.090 |
stalls | -0.090 |
fare | -0.090 |
flavors | -0.089 |
cases | -0.089 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
ir | +0.130 |
Ros | +0.130 |
apped | +0.128 |
weeping | +0.125 |
crying | +0.121 |
Neg logit contributions | |
stalls | -0.153 |
hike | -0.148 |
stall | -0.147 |
banks | -0.146 |
flavors | -0.143 |
Token | behind |
Token ID | 2157 |
Feature activation | +3.37e-03 |
Pos logit contributions | |
weeping | +0.050 |
crying | +0.049 |
bleeding | +0.048 |
Ros | +0.046 |
ir | +0.045 |
Neg logit contributions | |
stalls | -0.099 |
flavors | -0.094 |
stall | -0.093 |
hike | -0.093 |
banks | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
weeping | +0.006 |
crying | +0.006 |
bleeding | +0.005 |
Ros | +0.005 |
ir | +0.005 |
Neg logit contributions | |
stalls | -0.005 |
stall | -0.005 |
hike | -0.005 |
flavors | -0.005 |
banks | -0.005 |
Token | But |
Token ID | 887 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
weeping | +0.031 |
crying | +0.031 |
Ros | +0.029 |
bleeding | +0.029 |
Ros | +0.028 |
Neg logit contributions | |
stalls | -0.043 |
stall | -0.040 |
flavors | -0.039 |
hike | -0.039 |
fare | -0.038 |
Token | his |
Token ID | 465 |
Feature activation | +7.04e-04 |
Pos logit contributions | |
weeping | +0.006 |
crying | +0.006 |
bleeding | +0.006 |
Ros | +0.005 |
apped | +0.005 |
Neg logit contributions | |
stalls | -0.005 |
stall | -0.005 |
banks | -0.005 |
hike | -0.005 |
flavors | -0.005 |
Token | rot |
Token ID | 10599 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
weeping | +0.058 |
crying | +0.057 |
bleeding | +0.055 |
streaming | +0.055 |
Emily | +0.053 |
Neg logit contributions | |
stall | -0.085 |
stalls | -0.085 |
fare | -0.084 |
nic | -0.082 |
land | -0.082 |
Token | was |
Token ID | 373 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
weeping | +0.096 |
crying | +0.094 |
Ros | +0.092 |
bleeding | +0.092 |
ir | +0.091 |
Neg logit contributions | |
stalls | -0.108 |
hike | -0.101 |
stall | -0.101 |
banks | -0.099 |
fare | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
weeping | +0.056 |
crying | +0.055 |
Ros | +0.055 |
bleeding | +0.054 |
ir | +0.054 |
Neg logit contributions | |
stalls | -0.080 |
hike | -0.076 |
stall | -0.076 |
banks | -0.075 |
flavors | -0.075 |
Token | happiest |
Token ID | 49414 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
weeping | +0.045 |
crying | +0.044 |
Ros | +0.044 |
bleeding | +0.043 |
ir | +0.043 |
Neg logit contributions | |
stalls | -0.060 |
hike | -0.056 |
stall | -0.056 |
banks | -0.055 |
flavors | -0.055 |
Token | he |
Token ID | 339 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
bleeding | +0.085 |
weeping | +0.085 |
Ros | +0.085 |
ir | +0.083 |
crying | +0.082 |
Neg logit contributions | |
stalls | -0.121 |
stall | -0.117 |
hike | -0.113 |
flavors | -0.113 |
fare | -0.109 |
Token | had |
Token ID | 550 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
weeping | +0.080 |
crying | +0.079 |
bleeding | +0.076 |
Ros | +0.074 |
ir | +0.073 |
Neg logit contributions | |
stalls | -0.134 |
banks | -0.131 |
fare | -0.127 |
flavors | -0.127 |
hike | -0.125 |
Token | ever |
Token ID | 1683 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
weeping | +0.090 |
crying | +0.088 |
ir | +0.086 |
Ros | +0.086 |
bleeding | +0.085 |
Neg logit contributions | |
stalls | -0.199 |
hike | -0.190 |
stall | -0.189 |
banks | -0.189 |
flavors | -0.187 |
Token | been |
Token ID | 587 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
crying | +0.085 |
weeping | +0.085 |
bleeding | +0.081 |
ir | +0.081 |
streaming | +0.077 |
Neg logit contributions | |
stalls | -0.106 |
fare | -0.103 |
stall | -0.102 |
hike | -0.101 |
list | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
weeping | +0.111 |
crying | +0.109 |
Ros | +0.108 |
bleeding | +0.108 |
ir | +0.107 |
Neg logit contributions | |
stalls | -0.136 |
hike | -0.128 |
stall | -0.128 |
flavors | -0.126 |
banks | -0.126 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
bleeding | +0.044 |
weeping | +0.044 |
crying | +0.042 |
Ros | +0.042 |
ir | +0.042 |
Neg logit contributions | |
stalls | -0.049 |
stall | -0.047 |
hike | -0.045 |
banks | -0.045 |
flavors | -0.045 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
weeping | +0.021 |
bleeding | +0.020 |
Ros | +0.020 |
crying | +0.020 |
ir | +0.020 |
Neg logit contributions | |
stalls | -0.027 |
stall | -0.025 |
hike | -0.025 |
banks | -0.025 |
flavors | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
stalls | +0.005 |
hike | +0.005 |
banks | +0.005 |
stall | +0.005 |
fare | +0.005 |
Neg logit contributions | |
crying | -0.003 |
weeping | -0.003 |
bleeding | -0.003 |
streaming | -0.003 |
ir | -0.003 |
Token | made |
Token ID | 925 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ir | +0.017 |
weeping | +0.017 |
Ros | +0.017 |
bleeding | +0.017 |
crying | +0.016 |
Neg logit contributions | |
stalls | -0.019 |
hike | -0.018 |
flavors | -0.018 |
stall | -0.018 |
banks | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +7.36e-03 |
Pos logit contributions | |
weeping | +0.018 |
bleeding | +0.017 |
Ros | +0.017 |
ir | +0.017 |
crying | +0.017 |
Neg logit contributions | |
stalls | -0.022 |
flavors | -0.021 |
hike | -0.021 |
stall | -0.020 |
banks | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
weeping | +0.012 |
Ros | +0.012 |
bleeding | +0.012 |
crying | +0.011 |
ir | +0.011 |
Neg logit contributions | |
stalls | -0.012 |
hike | -0.012 |
stall | -0.012 |
banks | -0.011 |
flavors | -0.011 |
Token | happiest |
Token ID | 49414 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
streaming | +0.031 |
Ros | +0.031 |
bleeding | +0.031 |
weeping | +0.031 |
ir | +0.031 |
Neg logit contributions | |
stalls | -0.031 |
hike | -0.030 |
stall | -0.030 |
banks | -0.030 |
fare | -0.029 |
Token | bird |
Token ID | 6512 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
Ros | +0.089 |
bleeding | +0.086 |
ir | +0.084 |
weeping | +0.084 |
apped | +0.082 |
Neg logit contributions | |
stalls | -0.125 |
stall | -0.120 |
hike | -0.119 |
flavors | -0.116 |
fare | -0.113 |
Token | in |
Token ID | 287 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
weeping | +0.107 |
crying | +0.104 |
Ros | +0.103 |
bleeding | +0.103 |
ir | +0.101 |
Neg logit contributions | |
stalls | -0.180 |
hike | -0.170 |
stall | -0.170 |
banks | -0.168 |
flavors | -0.168 |
Token | the |
Token ID | 262 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
Ros | +0.047 |
bleeding | +0.046 |
apped | +0.045 |
weeping | +0.044 |
crying | +0.043 |
Neg logit contributions | |
stalls | -0.049 |
stall | -0.047 |
hike | -0.046 |
flavors | -0.044 |
banks | -0.043 |
Token | world |
Token ID | 995 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
apped | +0.073 |
bleeding | +0.073 |
streaming | +0.073 |
Ros | +0.072 |
ir | +0.072 |
Neg logit contributions | |
stalls | -0.072 |
hike | -0.069 |
stall | -0.068 |
banks | -0.067 |
bank | -0.064 |
Token | ! |
Token ID | 0 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
crying | +0.030 |
weeping | +0.030 |
ir | +0.028 |
streaming | +0.028 |
bleeding | +0.028 |
Neg logit contributions | |
stalls | -0.044 |
banks | -0.042 |
stall | -0.041 |
flavors | -0.041 |
hike | -0.041 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
ir | +0.047 |
bleeding | +0.047 |
weeping | +0.047 |
crying | +0.045 |
blood | +0.044 |
Neg logit contributions | |
stalls | -0.037 |
stall | -0.036 |
fare | -0.035 |
hike | -0.034 |
list | -0.034 |
Token | each |
Token ID | 1123 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
crying | +0.033 |
weeping | +0.033 |
bleeding | +0.032 |
blood | +0.030 |
Ros | +0.030 |
Neg logit contributions | |
stalls | -0.065 |
stall | -0.064 |
fare | -0.063 |
hike | -0.062 |
banks | -0.061 |
Token | other |
Token ID | 584 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
weeping | +0.028 |
Ros | +0.028 |
ir | +0.028 |
crying | +0.028 |
bleeding | +0.027 |
Neg logit contributions | |
stalls | -0.031 |
stall | -0.029 |
hike | -0.029 |
flavors | -0.029 |
banks | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -7.87e-04 |
Pos logit contributions | |
crying | +0.002 |
weeping | +0.002 |
bleeding | +0.002 |
microphone | +0.002 |
streaming | +0.002 |
Neg logit contributions | |
stalls | -0.003 |
hike | -0.003 |
stall | -0.003 |
banks | -0.003 |
fare | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
stalls | +0.001 |
hike | +0.001 |
stall | +0.001 |
flavors | +0.001 |
banks | +0.001 |
Neg logit contributions | |
weeping | -0.001 |
Ros | -0.001 |
ir | -0.001 |
crying | -0.001 |
bleeding | -0.001 |
Token | t |
Token ID | 256 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
ir | +0.039 |
apped | +0.038 |
Ros | +0.037 |
apping | +0.036 |
weeping | +0.035 |
Neg logit contributions | |
stalls | -0.039 |
stall | -0.037 |
flavors | -0.037 |
hike | -0.037 |
fare | -0.036 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
Emily | +0.051 |
rys | +0.047 |
weeping | +0.046 |
Ros | +0.045 |
Po | +0.045 |
Neg logit contributions | |
cases | -0.081 |
fare | -0.079 |
belts | -0.078 |
stalls | -0.076 |
flavors | -0.075 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
ir | +0.148 |
Ros | +0.143 |
apping | +0.142 |
apped | +0.139 |
aps | +0.134 |
Neg logit contributions | |
stalls | -0.132 |
flavors | -0.127 |
stall | -0.125 |
banks | -0.125 |
bank | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
crying | +0.063 |
weeping | +0.062 |
bleeding | +0.061 |
microphone | +0.056 |
blood | +0.055 |
Neg logit contributions | |
stalls | -0.076 |
hike | -0.071 |
stall | -0.070 |
banks | -0.070 |
flavors | -0.070 |
Token | They |
Token ID | 1119 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
weeping | +0.006 |
bleeding | +0.006 |
ir | +0.006 |
crying | +0.006 |
Ros | +0.006 |
Neg logit contributions | |
stalls | -0.005 |
stall | -0.005 |
hike | -0.005 |
flavors | -0.005 |
banks | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
stalls | +0.004 |
stall | +0.004 |
hike | +0.004 |
flavors | +0.004 |
banks | +0.004 |
Neg logit contributions | |
weeping | -0.004 |
crying | -0.004 |
bleeding | -0.004 |
Ros | -0.004 |
ir | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
Ros | +0.021 |
ir | +0.021 |
weeping | +0.019 |
el | +0.019 |
apped | +0.019 |
Neg logit contributions | |
stalls | -0.023 |
stall | -0.021 |
hike | -0.021 |
flavors | -0.021 |
banks | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
weeping | +0.032 |
crying | +0.032 |
ir | +0.031 |
Ros | +0.031 |
bleeding | +0.031 |
Neg logit contributions | |
stalls | -0.039 |
flavors | -0.037 |
hike | -0.037 |
fare | -0.036 |
stall | -0.036 |
Token | soon |
Token ID | 2582 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
ir | +0.013 |
Ros | +0.013 |
bleeding | +0.013 |
weeping | +0.012 |
apped | +0.012 |
Neg logit contributions | |
stalls | -0.012 |
hike | -0.012 |
flavors | -0.011 |
banks | -0.011 |
stall | -0.011 |
Token | became |
Token ID | 2627 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
weeping | +0.043 |
crying | +0.042 |
Ros | +0.041 |
ir | +0.040 |
bleeding | +0.040 |
Neg logit contributions | |
stalls | -0.068 |
stall | -0.065 |
fare | -0.064 |
flavors | -0.063 |
banks | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
weeping | +0.060 |
crying | +0.059 |
Ros | +0.058 |
ir | +0.058 |
bleeding | +0.058 |
Neg logit contributions | |
stalls | -0.082 |
stall | -0.077 |
hike | -0.077 |
flavors | -0.077 |
banks | -0.076 |
Token | strongest |
Token ID | 12841 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
weeping | +0.033 |
Ros | +0.033 |
ir | +0.033 |
crying | +0.033 |
bleeding | +0.032 |
Neg logit contributions | |
stalls | -0.036 |
hike | -0.034 |
stall | -0.034 |
flavors | -0.033 |
fare | -0.033 |
Token | bird |
Token ID | 6512 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
Ros | +0.057 |
apped | +0.052 |
weeping | +0.051 |
bleeding | +0.051 |
ir | +0.049 |
Neg logit contributions | |
stalls | -0.073 |
stall | -0.070 |
flavors | -0.068 |
hike | -0.068 |
banks | -0.066 |
Token | in |
Token ID | 287 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
Ros | +0.111 |
weeping | +0.110 |
bleeding | +0.107 |
crying | +0.107 |
ir | +0.106 |
Neg logit contributions | |
stalls | -0.169 |
hike | -0.160 |
stall | -0.160 |
banks | -0.157 |
flavors | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
Ros | +0.076 |
apped | +0.072 |
bleeding | +0.071 |
ternally | +0.068 |
streaming | +0.067 |
Neg logit contributions | |
stalls | -0.060 |
stall | -0.060 |
hike | -0.057 |
banks | -0.052 |
flavors | -0.051 |
Token | sky |
Token ID | 6766 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
apped | +0.070 |
Ros | +0.069 |
streaming | +0.068 |
bleeding | +0.068 |
weeping | +0.068 |
Neg logit contributions | |
stalls | -0.065 |
hike | -0.062 |
stall | -0.061 |
banks | -0.061 |
bank | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
weeping | +0.085 |
crying | +0.083 |
bleeding | +0.082 |
Ros | +0.082 |
ir | +0.082 |
Neg logit contributions | |
stalls | -0.077 |
hike | -0.072 |
stall | -0.072 |
banks | -0.070 |
flavors | -0.070 |
Token | The |
Token ID | 383 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
bleeding | +0.031 |
weeping | +0.030 |
crying | +0.030 |
ir | +0.030 |
Ros | +0.030 |
Neg logit contributions | |
stalls | -0.038 |
stall | -0.036 |
hike | -0.036 |
banks | -0.036 |
fare | -0.035 |
Token | listen |
Token ID | 6004 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
stalls | +0.018 |
stall | +0.017 |
hike | +0.017 |
banks | +0.017 |
flavors | +0.017 |
Neg logit contributions | |
weeping | -0.022 |
crying | -0.021 |
Ros | -0.021 |
bleeding | -0.021 |
ir | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -6.11e-03 |
Pos logit contributions | |
stalls | +0.029 |
hike | +0.028 |
stall | +0.028 |
banks | +0.028 |
flavors | +0.028 |
Neg logit contributions | |
crying | -0.019 |
weeping | -0.019 |
bleeding | -0.018 |
Ros | -0.017 |
ir | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
stalls | +0.010 |
stall | +0.010 |
banks | +0.009 |
hike | +0.009 |
list | +0.009 |
Neg logit contributions | |
ir | -0.009 |
bleeding | -0.009 |
Ros | -0.009 |
microphone | -0.009 |
weeping | -0.009 |
Token | threw |
Token ID | 9617 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
stalls | +0.023 |
fare | +0.022 |
stall | +0.022 |
hike | +0.022 |
banks | +0.021 |
Neg logit contributions | |
crying | -0.018 |
bleeding | -0.017 |
weeping | -0.017 |
blood | -0.017 |
Ros | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
stalls | +0.006 |
stall | +0.005 |
flavors | +0.005 |
banks | +0.005 |
bank | +0.005 |
Neg logit contributions | |
Ros | -0.005 |
weeping | -0.005 |
apped | -0.005 |
ir | -0.005 |
apping | -0.004 |
Token | tant |
Token ID | 24246 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
weeping | +0.031 |
Ros | +0.031 |
streaming | +0.031 |
el | +0.030 |
apped | +0.030 |
Neg logit contributions | |
stall | -0.039 |
stalls | -0.038 |
list | -0.037 |
bank | -0.036 |
ticket | -0.036 |
Token | rum |
Token ID | 6582 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
weeping | +0.153 |
Ros | +0.150 |
bleeding | +0.149 |
crying | +0.148 |
microphone | +0.147 |
Neg logit contributions | |
flavors | -0.112 |
stalls | -0.104 |
stall | -0.103 |
nic | -0.102 |
fare | -0.100 |
Token | in |
Token ID | 287 |
Feature activation | -7.62e-03 |
Pos logit contributions | |
Ros | +0.006 |
ir | +0.006 |
weeping | +0.005 |
microphone | +0.005 |
streaming | +0.005 |
Neg logit contributions | |
stalls | -0.005 |
stall | -0.004 |
belts | -0.004 |
banks | -0.004 |
flavors | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
stalls | +0.012 |
stall | +0.012 |
flavors | +0.011 |
shelves | +0.011 |
list | +0.011 |
Neg logit contributions | |
apped | -0.012 |
Ros | -0.012 |
weeping | -0.012 |
apping | -0.011 |
eddy | -0.011 |
Token | store |
Token ID | 3650 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
Ros | +0.022 |
ir | +0.021 |
weeping | +0.021 |
crying | +0.021 |
bleeding | +0.020 |
Neg logit contributions | |
stalls | -0.026 |
stall | -0.025 |
banks | -0.025 |
hike | -0.024 |
flavors | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
hike | +0.083 |
flavors | +0.081 |
stalls | +0.080 |
nic | +0.080 |
banks | +0.078 |
Neg logit contributions | |
crying | -0.052 |
weeping | -0.048 |
bleeding | -0.046 |
apped | -0.044 |
blood | -0.043 |
Token | love |
Token ID | 1842 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
weeping | +0.028 |
crying | +0.027 |
Ros | +0.027 |
bleeding | +0.027 |
ir | +0.026 |
Neg logit contributions | |
stalls | -0.041 |
stall | -0.039 |
hike | -0.038 |
banks | -0.038 |
fare | -0.037 |
Token | my |
Token ID | 616 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
apped | +0.049 |
ir | +0.049 |
Ros | +0.048 |
weeping | +0.046 |
bleeding | +0.045 |
Neg logit contributions | |
stalls | -0.091 |
flavors | -0.088 |
hike | -0.088 |
stall | -0.085 |
banks | -0.083 |
Token | new |
Token ID | 649 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
weeping | +0.019 |
crying | +0.018 |
bleeding | +0.018 |
Ros | +0.018 |
ir | +0.018 |
Neg logit contributions | |
stalls | -0.023 |
hike | -0.022 |
stall | -0.022 |
banks | -0.021 |
flavors | -0.021 |
Token | modern |
Token ID | 3660 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
weeping | +0.049 |
crying | +0.048 |
Ros | +0.047 |
bleeding | +0.047 |
ir | +0.046 |
Neg logit contributions | |
stalls | -0.072 |
hike | -0.067 |
stall | -0.067 |
banks | -0.067 |
flavors | -0.066 |
Token | t |
Token ID | 256 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
weeping | +0.028 |
crying | +0.028 |
bleeding | +0.027 |
Ros | +0.026 |
microphone | +0.026 |
Neg logit contributions | |
stalls | -0.040 |
hike | -0.038 |
stall | -0.038 |
banks | -0.037 |
fare | -0.037 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
weeping | +0.024 |
crying | +0.023 |
ir | +0.022 |
streaming | +0.022 |
bleeding | +0.022 |
Neg logit contributions | |
stalls | -0.079 |
flavors | -0.078 |
fare | -0.078 |
stall | -0.078 |
belts | -0.076 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
ir | +0.116 |
Ros | +0.115 |
weeping | +0.114 |
apped | +0.112 |
crying | +0.111 |
Neg logit contributions | |
stalls | -0.162 |
flavors | -0.155 |
stall | -0.154 |
hike | -0.153 |
banks | -0.151 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
crying | +0.056 |
weeping | +0.056 |
bleeding | +0.055 |
microphone | +0.053 |
apped | +0.052 |
Neg logit contributions | |
stalls | -0.081 |
hike | -0.078 |
banks | -0.076 |
stall | -0.074 |
fare | -0.074 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.97e-03 |
Pos logit contributions | |
stalls | +0.008 |
stall | +0.008 |
list | +0.007 |
banks | +0.007 |
bank | +0.007 |
Neg logit contributions | |
ir | -0.010 |
w | -0.009 |
bleeding | -0.009 |
ubby | -0.009 |
el | -0.009 |
Token | Once |
Token ID | 7454 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
weeping | +0.011 |
bleeding | +0.010 |
Ros | +0.010 |
crying | +0.010 |
ir | +0.010 |
Neg logit contributions | |
stalls | -0.012 |
stall | -0.012 |
hike | -0.012 |
flavors | -0.011 |
banks | -0.011 |
Token | upon |
Token ID | 2402 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
hike | +0.004 |
stalls | +0.004 |
stall | +0.004 |
list | +0.004 |
flavors | +0.004 |
Neg logit contributions | |
Ros | -0.005 |
bleeding | -0.005 |
streaming | -0.005 |
weeping | -0.005 |
ir | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ir | +0.025 |
Ros | +0.025 |
apped | +0.024 |
weeping | +0.024 |
bleeding | +0.024 |
Neg logit contributions | |
stalls | -0.020 |
stall | -0.018 |
hike | -0.018 |
flavors | -0.017 |
fare | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
ir | +0.026 |
weeping | +0.026 |
Ros | +0.025 |
apped | +0.025 |
bleeding | +0.025 |
Neg logit contributions | |
stalls | -0.019 |
hike | -0.019 |
banks | -0.018 |
flavors | -0.018 |
stall | -0.018 |
Token | lost |
Token ID | 2626 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
weeping | +0.037 |
crying | +0.037 |
bleeding | +0.036 |
Ros | +0.035 |
ir | +0.034 |
Neg logit contributions | |
stalls | -0.054 |
stall | -0.051 |
hike | -0.051 |
banks | -0.050 |
flavors | -0.050 |
Token | her |
Token ID | 607 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
Ros | +0.021 |
apped | +0.020 |
ir | +0.020 |
weeping | +0.020 |
crying | +0.019 |
Neg logit contributions | |
stalls | -0.033 |
stall | -0.031 |
flavors | -0.031 |
banks | -0.030 |
hike | -0.030 |
Token | t |
Token ID | 256 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
Ros | +0.038 |
weeping | +0.038 |
ir | +0.038 |
crying | +0.037 |
bleeding | +0.037 |
Neg logit contributions | |
stalls | -0.041 |
stall | -0.039 |
hike | -0.039 |
flavors | -0.038 |
banks | -0.038 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
Emily | +0.035 |
weeping | +0.035 |
sorry | +0.034 |
streaming | +0.033 |
crying | +0.033 |
Neg logit contributions | |
flavors | -0.071 |
stall | -0.071 |
stalls | -0.071 |
cases | -0.071 |
fare | -0.070 |
Token | bear |
Token ID | 6842 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
ir | +0.131 |
apped | +0.129 |
Ros | +0.126 |
weeping | +0.123 |
apping | +0.121 |
Neg logit contributions | |
stalls | -0.146 |
stall | -0.142 |
flavors | -0.141 |
hike | -0.139 |
banks | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
crying | +0.060 |
weeping | +0.060 |
bleeding | +0.059 |
Ros | +0.055 |
microphone | +0.055 |
Neg logit contributions | |
stalls | -0.083 |
flavors | -0.078 |
hike | -0.077 |
stall | -0.076 |
banks | -0.076 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
ir | +0.034 |
bleeding | +0.032 |
streaming | +0.032 |
microphone | +0.032 |
el | +0.032 |
Neg logit contributions | |
stalls | -0.033 |
banks | -0.032 |
stall | -0.031 |
hike | -0.031 |
list | -0.030 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ir | +0.021 |
Ros | +0.021 |
apped | +0.019 |
streaming | +0.019 |
apping | +0.018 |
Neg logit contributions | |
stalls | -0.019 |
flavors | -0.019 |
stall | -0.019 |
hike | -0.018 |
belts | -0.018 |
Token | told |
Token ID | 1297 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ir | +0.075 |
Ros | +0.071 |
aps | +0.071 |
weeping | +0.071 |
apped | +0.071 |
Neg logit contributions | |
stalls | -0.053 |
stall | -0.050 |
hike | -0.049 |
bank | -0.048 |
flavors | -0.048 |
Token | comfortably |
Token ID | 24341 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
weeping | +0.020 |
crying | +0.019 |
Ros | +0.019 |
ir | +0.019 |
bleeding | +0.019 |
Neg logit contributions | |
stalls | -0.042 |
hike | -0.040 |
stall | -0.040 |
banks | -0.040 |
flavors | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
weeping | +0.006 |
crying | +0.006 |
ir | +0.006 |
bleeding | +0.006 |
Ros | +0.006 |
Neg logit contributions | |
stalls | -0.010 |
flavors | -0.010 |
stall | -0.010 |
fare | -0.010 |
hike | -0.010 |
Token | happily |
Token ID | 18177 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
ir | +0.012 |
Ros | +0.011 |
weeping | +0.011 |
bleeding | +0.011 |
apped | +0.011 |
Neg logit contributions | |
stalls | -0.011 |
hike | -0.011 |
flavors | -0.011 |
banks | -0.011 |
stall | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
weeping | +0.034 |
Ros | +0.033 |
crying | +0.033 |
bleeding | +0.032 |
ir | +0.032 |
Neg logit contributions | |
stalls | -0.054 |
hike | -0.051 |
stall | -0.051 |
banks | -0.050 |
flavors | -0.050 |
Token | its |
Token ID | 663 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
Ros | +0.010 |
weeping | +0.010 |
bleeding | +0.010 |
apped | +0.010 |
ir | +0.010 |
Neg logit contributions | |
stalls | -0.011 |
stall | -0.011 |
flavors | -0.010 |
hike | -0.010 |
banks | -0.010 |
Token | bird |
Token ID | 6512 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
weeping | +0.054 |
crying | +0.053 |
bleeding | +0.053 |
Ros | +0.052 |
ir | +0.052 |
Neg logit contributions | |
stalls | -0.074 |
hike | -0.070 |
stall | -0.069 |
flavors | -0.068 |
banks | -0.068 |
Token | c |
Token ID | 66 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
weeping | +0.122 |
Ros | +0.120 |
bleeding | +0.118 |
crying | +0.118 |
ir | +0.116 |
Neg logit contributions | |
stalls | -0.156 |
stall | -0.148 |
hike | -0.147 |
banks | -0.146 |
flavors | -0.146 |
Token | age |
Token ID | 496 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
weeping | +0.051 |
crying | +0.050 |
bleeding | +0.050 |
Ros | +0.049 |
streaming | +0.048 |
Neg logit contributions | |
stalls | -0.039 |
banks | -0.036 |
stall | -0.036 |
hike | -0.036 |
flavors | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
weeping | +0.051 |
crying | +0.050 |
bleeding | +0.049 |
Ros | +0.049 |
ir | +0.048 |
Neg logit contributions | |
stalls | -0.054 |
hike | -0.051 |
stall | -0.051 |
banks | -0.050 |
flavors | -0.050 |
Token | The |
Token ID | 383 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
weeping | +0.024 |
bleeding | +0.024 |
crying | +0.024 |
Ros | +0.023 |
ir | +0.023 |
Neg logit contributions | |
stalls | -0.033 |
hike | -0.032 |
stall | -0.032 |
banks | -0.031 |
flavors | -0.031 |
Token | boy |
Token ID | 2933 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
Ros | +0.020 |
weeping | +0.020 |
ir | +0.019 |
streaming | +0.019 |
apped | +0.019 |
Neg logit contributions | |
stalls | -0.025 |
stall | -0.024 |
hike | -0.024 |
flavors | -0.024 |
banks | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
Ros | +0.035 |
weeping | +0.034 |
ir | +0.033 |
bleeding | +0.033 |
crying | +0.033 |
Neg logit contributions | |
stalls | -0.062 |
stall | -0.059 |
hike | -0.058 |
banks | -0.058 |
flavors | -0.058 |
Token | feet |
Token ID | 3625 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
Ros | +0.025 |
ir | +0.025 |
weeping | +0.024 |
bleeding | +0.023 |
apped | +0.023 |
Neg logit contributions | |
stalls | -0.034 |
stall | -0.033 |
hike | -0.032 |
banks | -0.031 |
flavors | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
weeping | +0.007 |
Ros | +0.007 |
crying | +0.007 |
bleeding | +0.007 |
ir | +0.007 |
Neg logit contributions | |
stalls | -0.009 |
stall | -0.008 |
hike | -0.008 |
banks | -0.008 |
flavors | -0.008 |
Token | threw |
Token ID | 9617 |
Feature activation | -1.92e-03 |
Pos logit contributions | |
stalls | +0.016 |
hike | +0.015 |
stall | +0.015 |
banks | +0.014 |
flavors | +0.014 |
Neg logit contributions | |
weeping | -0.014 |
crying | -0.014 |
bleeding | -0.014 |
Ros | -0.014 |
ir | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
stalls | +0.004 |
stall | +0.004 |
flavors | +0.004 |
hike | +0.004 |
banks | +0.004 |
Neg logit contributions | |
weeping | -0.002 |
Ros | -0.002 |
crying | -0.002 |
bleeding | -0.002 |
ir | -0.002 |
Token | tant |
Token ID | 24246 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
Ros | +0.024 |
apped | +0.023 |
weeping | +0.023 |
streaming | +0.022 |
ir | +0.022 |
Neg logit contributions | |
stall | -0.037 |
stalls | -0.036 |
bank | -0.034 |
list | -0.034 |
flavors | -0.034 |
Token | rum |
Token ID | 6582 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
weeping | +0.146 |
Ros | +0.145 |
bleeding | +0.144 |
crying | +0.143 |
microphone | +0.140 |
Neg logit contributions | |
stalls | -0.119 |
flavors | -0.118 |
stall | -0.116 |
fare | -0.112 |
nic | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -9.88e-04 |
Pos logit contributions | |
Ros | +0.002 |
weeping | +0.002 |
ir | +0.002 |
crying | +0.002 |
bleeding | +0.002 |
Neg logit contributions | |
stalls | -0.002 |
stall | -0.002 |
hike | -0.002 |
banks | -0.002 |
flavors | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
stalls | +0.002 |
stall | +0.002 |
banks | +0.002 |
hike | +0.002 |
list | +0.002 |
Neg logit contributions | |
bleeding | -0.001 |
Ros | -0.001 |
weeping | -0.001 |
ir | -0.001 |
crying | -0.001 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
stalls | +0.004 |
hike | +0.004 |
stall | +0.004 |
flavors | +0.004 |
banks | +0.004 |
Neg logit contributions | |
weeping | -0.004 |
Ros | -0.004 |
ir | -0.004 |
crying | -0.004 |
bleeding | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
stalls | +0.015 |
stall | +0.014 |
flavors | +0.014 |
banks | +0.013 |
hike | +0.013 |
Neg logit contributions | |
weeping | -0.013 |
Ros | -0.013 |
apping | -0.013 |
apped | -0.013 |
bleeding | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
stalls | +0.027 |
stall | +0.026 |
hike | +0.024 |
list | +0.023 |
banks | +0.023 |
Neg logit contributions | |
ir | -0.028 |
Ros | -0.025 |
ternally | -0.025 |
el | -0.025 |
streaming | -0.025 |
Token | c |
Token ID | 269 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
stalls | +0.005 |
hike | +0.004 |
stall | +0.004 |
banks | +0.004 |
fare | +0.004 |
Neg logit contributions | |
weeping | -0.003 |
crying | -0.003 |
bleeding | -0.003 |
Ros | -0.003 |
apped | -0.003 |
Token | uddled |
Token ID | 32745 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
weeping | +0.026 |
crying | +0.026 |
Emily | +0.026 |
Ros | +0.026 |
Ros | +0.025 |
Neg logit contributions | |
stalls | -0.019 |
belts | -0.018 |
cases | -0.018 |
stall | -0.017 |
flavors | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
ir | +0.029 |
Ros | +0.027 |
el | +0.026 |
weeping | +0.026 |
streaming | +0.026 |
Neg logit contributions | |
stalls | -0.040 |
stall | -0.038 |
hike | -0.036 |
belts | -0.036 |
banks | -0.035 |
Token | t |
Token ID | 256 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
ir | +0.065 |
Ros | +0.063 |
apped | +0.061 |
itt | +0.059 |
streaming | +0.059 |
Neg logit contributions | |
stalls | -0.048 |
belts | -0.048 |
hike | -0.048 |
stall | -0.047 |
flavors | -0.046 |
Token | eddy |
Token ID | 21874 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
Emily | +0.053 |
streaming | +0.051 |
sorry | +0.050 |
weeping | +0.050 |
Ros | +0.048 |
Neg logit contributions | |
belts | -0.081 |
cases | -0.076 |
fare | -0.075 |
belt | -0.074 |
stalls | -0.072 |
Token | bear |
Token ID | 6842 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
ir | +0.148 |
Ros | +0.145 |
apped | +0.140 |
apping | +0.138 |
itt | +0.138 |
Neg logit contributions | |
stalls | -0.128 |
stall | -0.123 |
banks | -0.121 |
hike | -0.121 |
belts | -0.119 |
Token | and |
Token ID | 290 |
Feature activation | -7.06e-04 |
Pos logit contributions | |
weeping | +0.053 |
crying | +0.051 |
bleeding | +0.051 |
Ros | +0.051 |
ir | +0.050 |
Neg logit contributions | |
stalls | -0.075 |
hike | -0.070 |
stall | -0.070 |
flavors | -0.070 |
banks | -0.069 |
Token | read |
Token ID | 1100 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
stalls | +0.001 |
stall | +0.001 |
hike | +0.001 |
banks | +0.001 |
fare | +0.001 |
Neg logit contributions | |
weeping | -0.001 |
crying | -0.001 |
bleeding | -0.001 |
Ros | -0.001 |
blood | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
stalls | +0.031 |
hike | +0.030 |
stall | +0.030 |
banks | +0.030 |
flavors | +0.029 |
Neg logit contributions | |
weeping | -0.015 |
crying | -0.015 |
bleeding | -0.015 |
Ros | -0.015 |
ir | -0.014 |
Token | book |
Token ID | 1492 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ir | +0.008 |
Ros | +0.008 |
weeping | +0.008 |
apped | +0.008 |
crying | +0.008 |
Neg logit contributions | |
stalls | -0.008 |
hike | -0.007 |
flavors | -0.007 |
stall | -0.007 |
belts | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
weeping | +0.028 |
bleeding | +0.027 |
ir | +0.027 |
crying | +0.027 |
streaming | +0.026 |
Neg logit contributions | |
stalls | -0.033 |
stall | -0.031 |
hike | -0.030 |
banks | -0.030 |
flavors | -0.030 |
Token | The |
Token ID | 464 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
weeping | +0.026 |
crying | +0.025 |
bleeding | +0.025 |
ir | +0.024 |
Ros | +0.024 |
Neg logit contributions | |
stalls | -0.032 |
stall | -0.030 |
hike | -0.030 |
flavors | -0.029 |
banks | -0.029 |
Token | end |
Token ID | 886 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
weeping | +0.010 |
crying | +0.010 |
bleeding | +0.009 |
Ros | +0.009 |
microphone | +0.009 |
Neg logit contributions | |
stalls | -0.010 |
stall | -0.009 |
hike | -0.009 |
banks | -0.009 |
flavors | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
crying | +0.037 |
bleeding | +0.037 |
weeping | +0.036 |
Emily | +0.034 |
Sad | +0.034 |
Neg logit contributions | |
stalls | -0.059 |
banks | -0.057 |
bank | -0.055 |
stall | -0.054 |
hike | -0.054 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
weeping | +0.048 |
ir | +0.048 |
bleeding | +0.047 |
crying | +0.046 |
Ros | +0.046 |
Neg logit contributions | |
stalls | -0.049 |
stall | -0.047 |
hike | -0.045 |
fare | -0.045 |
flavors | -0.044 |
Token | Re |
Token ID | 3041 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
weeping | +0.016 |
bleeding | +0.016 |
Ros | +0.016 |
crying | +0.016 |
ir | +0.016 |
Neg logit contributions | |
stalls | -0.019 |
stall | -0.018 |
hike | -0.017 |
banks | -0.017 |
flavors | -0.017 |
Token | becca |
Token ID | 20627 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
stalls | +0.138 |
fare | +0.128 |
banks | +0.128 |
hike | +0.127 |
stall | +0.127 |
Neg logit contributions | |
ir | -0.179 |
el | -0.174 |
apped | -0.172 |
Ros | -0.171 |
weeping | -0.169 |
Token | was |
Token ID | 373 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
fare | +0.085 |
stalls | +0.083 |
banks | +0.080 |
stall | +0.080 |
hike | +0.079 |
Neg logit contributions | |
crying | -0.051 |
weeping | -0.051 |
el | -0.051 |
ir | -0.049 |
apped | -0.048 |
Token | feeling |
Token ID | 4203 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
Ros | +0.028 |
ir | +0.027 |
blood | +0.025 |
accidents | +0.024 |
anish | +0.024 |
Neg logit contributions | |
stalls | -0.027 |
stall | -0.026 |
hike | -0.024 |
packed | -0.024 |
banks | -0.023 |
Token | anxious |
Token ID | 18116 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
weeping | +0.021 |
Ros | +0.021 |
ir | +0.020 |
crying | +0.020 |
bleeding | +0.020 |
Neg logit contributions | |
stalls | -0.032 |
stall | -0.030 |
hike | -0.030 |
banks | -0.030 |
flavors | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
stalls | +0.025 |
stall | +0.024 |
hike | +0.023 |
flavors | +0.023 |
banks | +0.023 |
Neg logit contributions | |
weeping | -0.021 |
crying | -0.021 |
bleeding | -0.019 |
streaming | -0.019 |
apped | -0.019 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
weeping | +0.005 |
crying | +0.005 |
Ros | +0.005 |
bleeding | +0.005 |
ir | +0.005 |
Neg logit contributions | |
stalls | -0.005 |
hike | -0.005 |
stall | -0.005 |
banks | -0.004 |
flavors | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
weeping | +0.027 |
Ros | +0.027 |
crying | +0.027 |
ir | +0.027 |
bleeding | +0.027 |
Neg logit contributions | |
stalls | -0.034 |
stall | -0.032 |
hike | -0.032 |
flavors | -0.031 |
banks | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
stalls | +0.018 |
banks | +0.017 |
fare | +0.017 |
hike | +0.017 |
stall | +0.017 |
Neg logit contributions | |
crying | -0.013 |
weeping | -0.013 |
Ros | -0.013 |
Ros | -0.013 |
bleeding | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
stalls | +0.052 |
hike | +0.050 |
banks | +0.049 |
flavors | +0.049 |
fare | +0.048 |
Neg logit contributions | |
weeping | -0.038 |
crying | -0.038 |
apped | -0.037 |
bleeding | -0.036 |
Ros | -0.036 |
Token | " |
Token ID | 366 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
stalls | +0.044 |
hike | +0.042 |
flavors | +0.042 |
banks | +0.041 |
fare | +0.041 |
Neg logit contributions | |
weeping | -0.042 |
crying | -0.042 |
bleeding | -0.040 |
Ros | -0.039 |
apped | -0.038 |
Token | Money |
Token ID | 26788 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
stalls | +0.014 |
hike | +0.014 |
banks | +0.014 |
stall | +0.014 |
list | +0.013 |
Neg logit contributions | |
Ros | -0.006 |
weeping | -0.005 |
bleeding | -0.005 |
el | -0.005 |
apped | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
hike | +0.210 |
stalls | +0.210 |
banks | +0.205 |
stall | +0.201 |
hikes | +0.194 |
Neg logit contributions | |
el | -0.092 |
ing | -0.085 |
crying | -0.084 |
blood | -0.084 |
bleeding | -0.084 |
Token | like |
Token ID | 588 |
Feature activation | -8.32e-03 |
Pos logit contributions | |
stalls | +0.046 |
hike | +0.046 |
banks | +0.045 |
stall | +0.044 |
fare | +0.042 |
Neg logit contributions | |
Ros | -0.022 |
crying | -0.021 |
weeping | -0.021 |
bleeding | -0.020 |
microphone | -0.019 |
Token | coins |
Token ID | 10796 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
stalls | +0.017 |
stall | +0.016 |
hike | +0.016 |
banks | +0.016 |
fare | +0.016 |
Neg logit contributions | |
weeping | -0.010 |
crying | -0.010 |
bleeding | -0.010 |
Ros | -0.010 |
blood | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
stalls | +0.106 |
hike | +0.106 |
fare | +0.100 |
banks | +0.100 |
stall | +0.099 |
Neg logit contributions | |
crying | -0.060 |
weeping | -0.058 |
bleeding | -0.057 |
microphone | -0.055 |
el | -0.054 |
Token | help |
Token ID | 1037 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
crying | +0.025 |
weeping | +0.025 |
microphone | +0.024 |
el | +0.024 |
bleeding | +0.024 |
Neg logit contributions | |
stalls | -0.039 |
hike | -0.037 |
stall | -0.036 |
banks | -0.036 |
nic | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
stalls | +0.116 |
banks | +0.110 |
flavors | +0.108 |
stall | +0.107 |
hike | +0.107 |
Neg logit contributions | |
weeping | -0.073 |
crying | -0.073 |
Ros | -0.070 |
bleeding | -0.068 |
apped | -0.066 |
Token | help |
Token ID | 1037 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
stalls | +0.090 |
stall | +0.084 |
hike | +0.084 |
banks | +0.083 |
flavors | +0.083 |
Neg logit contributions | |
weeping | -0.084 |
crying | -0.082 |
Ros | -0.082 |
bleeding | -0.082 |
ir | -0.081 |
Token | with |
Token ID | 351 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
stalls | +0.034 |
hike | +0.032 |
stall | +0.032 |
banks | +0.031 |
flavors | +0.031 |
Neg logit contributions | |
weeping | -0.034 |
Ros | -0.033 |
crying | -0.033 |
bleeding | -0.033 |
ir | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
stalls | +0.035 |
stall | +0.033 |
hike | +0.033 |
banks | +0.033 |
flavors | +0.032 |
Neg logit contributions | |
weeping | -0.021 |
crying | -0.020 |
bleeding | -0.020 |
Ros | -0.020 |
ir | -0.020 |
Token | grocery |
Token ID | 16918 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
stalls | +0.051 |
hike | +0.047 |
stall | +0.047 |
banks | +0.047 |
flavors | +0.046 |
Neg logit contributions | |
weeping | -0.049 |
crying | -0.049 |
bleeding | -0.048 |
Ros | -0.048 |
ir | -0.047 |
Token | shopping |
Token ID | 9735 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
land | +0.161 |
flavors | +0.160 |
nic | +0.157 |
hikes | +0.155 |
uries | +0.153 |
Neg logit contributions | |
crying | -0.094 |
together | -0.089 |
ucky | -0.078 |
Ros | -0.077 |
weeping | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -4.94e-04 |
Pos logit contributions | |
hike | +0.208 |
nic | +0.203 |
banks | +0.197 |
hikes | +0.197 |
Street | +0.195 |
Neg logit contributions | |
apped | -0.094 |
together | -0.092 |
crying | -0.084 |
uck | -0.082 |
el | -0.077 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
stalls | +0.001 |
hike | +0.001 |
fare | +0.001 |
flavors | +0.001 |
stall | +0.001 |
Neg logit contributions | |
crying | -0.000 |
Ros | -0.000 |
weeping | -0.000 |
bleeding | -0.000 |
apped | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +6.27e-03 |
Pos logit contributions | |
fare | +0.010 |
stalls | +0.010 |
land | +0.010 |
stall | +0.009 |
banks | +0.009 |
Neg logit contributions | |
crying | -0.006 |
uck | -0.005 |
apped | -0.005 |
Ros | -0.005 |
el | -0.005 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
weeping | +0.009 |
Ros | +0.009 |
crying | +0.008 |
bleeding | +0.008 |
ir | +0.008 |
Neg logit contributions | |
stalls | -0.012 |
stall | -0.011 |
hike | -0.011 |
banks | -0.011 |
flavors | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
stalls | +0.027 |
fare | +0.026 |
banks | +0.026 |
stall | +0.026 |
flavors | +0.025 |
Neg logit contributions | |
crying | -0.016 |
weeping | -0.016 |
bleeding | -0.015 |
Ros | -0.014 |
Emily | -0.014 |
Token | if |
Token ID | 611 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
stalls | +0.094 |
banks | +0.091 |
flavors | +0.091 |
hike | +0.088 |
stall | +0.087 |
Neg logit contributions | |
crying | -0.067 |
weeping | -0.066 |
Emily | -0.058 |
Ros | -0.058 |
microphone | -0.058 |
Token | she |
Token ID | 673 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
crying | +0.025 |
weeping | +0.025 |
Ros | +0.024 |
bleeding | +0.023 |
Ros | +0.023 |
Neg logit contributions | |
stalls | -0.033 |
banks | -0.032 |
stall | -0.032 |
fare | -0.031 |
flavors | -0.031 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
stalls | +0.084 |
stall | +0.078 |
banks | +0.078 |
hike | +0.076 |
fare | +0.074 |
Neg logit contributions | |
weeping | -0.086 |
crying | -0.085 |
bleeding | -0.082 |
Ros | -0.081 |
apped | -0.079 |
Token | to |
Token ID | 284 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
stalls | +0.028 |
stall | +0.027 |
hike | +0.027 |
banks | +0.026 |
flavors | +0.026 |
Neg logit contributions | |
weeping | -0.021 |
crying | -0.021 |
Ros | -0.020 |
bleeding | -0.020 |
ir | -0.020 |
Token | go |
Token ID | 467 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
stalls | +0.049 |
hike | +0.048 |
flavors | +0.047 |
banks | +0.046 |
stall | +0.046 |
Neg logit contributions | |
weeping | -0.051 |
bleeding | -0.050 |
crying | -0.049 |
Ros | -0.049 |
ir | -0.049 |
Token | shopping |
Token ID | 9735 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
weeping | +0.005 |
crying | +0.005 |
Ros | +0.005 |
bleeding | +0.005 |
ir | +0.005 |
Neg logit contributions | |
stalls | -0.008 |
stall | -0.008 |
hike | -0.008 |
flavors | -0.008 |
banks | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
hike | +0.206 |
nic | +0.205 |
banks | +0.203 |
stalls | +0.199 |
pm | +0.192 |
Neg logit contributions | |
together | -0.091 |
crying | -0.089 |
apped | -0.080 |
weeping | -0.077 |
el | -0.077 |
Token | She |
Token ID | 1375 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
stalls | +0.029 |
hike | +0.028 |
flavors | +0.028 |
fare | +0.028 |
banks | +0.027 |
Neg logit contributions | |
weeping | -0.022 |
crying | -0.022 |
Ros | -0.021 |
bleeding | -0.020 |
apped | -0.020 |
Token | nodded |
Token ID | 14464 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
banks | +0.043 |
stalls | +0.043 |
fare | +0.040 |
experiments | +0.039 |
stall | +0.039 |
Neg logit contributions | |
crying | -0.027 |
weeping | -0.026 |
apped | -0.026 |
Emily | -0.025 |
Ros | -0.025 |
Token | vigorously |
Token ID | 31609 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
weeping | +0.012 |
crying | +0.012 |
bleeding | +0.011 |
Ros | +0.011 |
streaming | +0.011 |
Neg logit contributions | |
stalls | -0.018 |
hike | -0.018 |
banks | -0.018 |
stall | -0.017 |
flavors | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
stalls | +0.074 |
flavors | +0.072 |
hike | +0.070 |
banks | +0.069 |
stall | +0.068 |
Neg logit contributions | |
crying | -0.042 |
weeping | -0.039 |
bleeding | -0.034 |
streaming | -0.033 |
apped | -0.032 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
stalls | +0.034 |
stall | +0.032 |
banks | +0.032 |
hike | +0.032 |
flavors | +0.031 |
Neg logit contributions | |
weeping | -0.017 |
crying | -0.017 |
bleeding | -0.016 |
Ros | -0.016 |
microphone | -0.015 |
Token | agreed |
Token ID | 4987 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
crying | +0.022 |
weeping | +0.021 |
bleeding | +0.021 |
streaming | +0.020 |
Ros | +0.020 |
Neg logit contributions | |
stalls | -0.028 |
banks | -0.026 |
stall | -0.026 |
hike | -0.026 |
flavors | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
stalls | +0.066 |
banks | +0.062 |
stall | +0.062 |
hike | +0.061 |
fare | +0.060 |
Neg logit contributions | |
crying | -0.034 |
weeping | -0.031 |
bleeding | -0.028 |
streaming | -0.027 |
Emily | -0.026 |
Token | take |
Token ID | 1011 |
Feature activation | +1.46e-03 |
Pos logit contributions | |
stalls | +0.049 |
stall | +0.044 |
banks | +0.044 |
flavors | +0.043 |
hike | +0.042 |
Neg logit contributions | |
crying | -0.044 |
weeping | -0.044 |
bleeding | -0.042 |
ir | -0.041 |
Ros | -0.041 |
Token | him |
Token ID | 683 |
Feature activation | -6.69e-03 |
Pos logit contributions | |
weeping | +0.002 |
bleeding | +0.002 |
Ros | +0.002 |
ir | +0.002 |
crying | +0.002 |
Neg logit contributions | |
stalls | -0.003 |
hike | -0.002 |
stall | -0.002 |
goods | -0.002 |
fare | -0.002 |
Token | shopping |
Token ID | 9735 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
stalls | +0.015 |
flavors | +0.015 |
stall | +0.015 |
hike | +0.014 |
banks | +0.014 |
Neg logit contributions | |
crying | -0.007 |
weeping | -0.007 |
bleeding | -0.006 |
Ros | -0.006 |
microphone | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
hike | +0.208 |
nic | +0.205 |
banks | +0.198 |
bread | +0.192 |
stalls | +0.191 |
Neg logit contributions | |
together | -0.092 |
crying | -0.089 |
apped | -0.083 |
el | -0.072 |
weeping | -0.072 |
Token | a |
Token ID | 257 |
Feature activation | -9.83e-03 |
Pos logit contributions | |
stalls | +0.029 |
stall | +0.027 |
hike | +0.027 |
banks | +0.027 |
flavors | +0.027 |
Neg logit contributions | |
weeping | -0.017 |
crying | -0.017 |
Ros | -0.017 |
bleeding | -0.016 |
ir | -0.016 |
Token | new |
Token ID | 649 |
Feature activation | -1.39e-03 |
Pos logit contributions | |
stalls | +0.017 |
banks | +0.016 |
flavors | +0.016 |
stall | +0.014 |
fare | +0.014 |
Neg logit contributions | |
crying | -0.016 |
weeping | -0.016 |
Ros | -0.015 |
microphone | -0.015 |
bleeding | -0.014 |
Token | uniform |
Token ID | 8187 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
banks | +0.003 |
stalls | +0.003 |
bread | +0.002 |
pm | +0.002 |
flavors | +0.002 |
Neg logit contributions | |
crying | -0.002 |
microphone | -0.002 |
weeping | -0.002 |
Ros | -0.002 |
laser | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +6.86e-03 |
Pos logit contributions | |
stalls | +0.032 |
hike | +0.031 |
banks | +0.031 |
flavors | +0.030 |
stall | +0.030 |
Neg logit contributions | |
crying | -0.019 |
weeping | -0.018 |
apped | -0.017 |
bleeding | -0.017 |
Ros | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
stalls | +0.115 |
banks | +0.111 |
flavors | +0.108 |
stall | +0.107 |
hike | +0.107 |
Neg logit contributions | |
crying | -0.071 |
weeping | -0.071 |
Ros | -0.067 |
Ros | -0.064 |
bleeding | -0.064 |
Token | help |
Token ID | 1037 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
stalls | +0.079 |
hike | +0.079 |
list | +0.077 |
stall | +0.077 |
flavors | +0.076 |
Neg logit contributions | |
weeping | -0.099 |
bleeding | -0.098 |
crying | -0.095 |
ir | -0.094 |
streaming | -0.093 |
Token | with |
Token ID | 351 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
stalls | +0.038 |
hike | +0.036 |
stall | +0.036 |
banks | +0.035 |
flavors | +0.035 |
Neg logit contributions | |
weeping | -0.031 |
bleeding | -0.030 |
Ros | -0.029 |
crying | -0.029 |
ir | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
stalls | +0.038 |
stall | +0.036 |
hike | +0.036 |
banks | +0.035 |
flavors | +0.035 |
Neg logit contributions | |
weeping | -0.020 |
crying | -0.020 |
Ros | -0.020 |
bleeding | -0.020 |
ir | -0.019 |
Token | grocery |
Token ID | 16918 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
stalls | +0.056 |
hike | +0.053 |
stall | +0.053 |
flavors | +0.053 |
banks | +0.052 |
Neg logit contributions | |
weeping | -0.039 |
Ros | -0.039 |
ir | -0.038 |
bleeding | -0.038 |
crying | -0.038 |
Token | shopping |
Token ID | 9735 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
land | +0.149 |
nic | +0.147 |
flavors | +0.146 |
stalls | +0.142 |
hike | +0.141 |
Neg logit contributions | |
crying | -0.104 |
Ros | -0.098 |
Emily | -0.096 |
together | -0.092 |
microphone | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
hike | +0.199 |
nic | +0.199 |
banks | +0.192 |
Street | +0.191 |
hikes | +0.187 |
Neg logit contributions | |
apped | -0.097 |
together | -0.091 |
crying | -0.089 |
uck | -0.084 |
el | -0.084 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.30e-03 |
Pos logit contributions | |
stalls | +0.007 |
hike | +0.006 |
stall | +0.006 |
flavors | +0.006 |
banks | +0.006 |
Neg logit contributions | |
weeping | -0.003 |
crying | -0.003 |
Ros | -0.003 |
bleeding | -0.003 |
ir | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +5.76e-03 |
Pos logit contributions | |
stalls | +0.009 |
fare | +0.008 |
land | +0.008 |
stall | +0.008 |
banks | +0.008 |
Neg logit contributions | |
crying | -0.006 |
Ros | -0.006 |
weeping | -0.005 |
apped | -0.005 |
el | -0.005 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
weeping | +0.008 |
Ros | +0.008 |
ir | +0.008 |
crying | +0.008 |
bleeding | +0.008 |
Neg logit contributions | |
stalls | -0.011 |
stall | -0.010 |
hike | -0.010 |
flavors | -0.010 |
banks | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
stalls | +0.028 |
stall | +0.026 |
banks | +0.026 |
fare | +0.026 |
hike | +0.026 |
Neg logit contributions | |
crying | -0.018 |
weeping | -0.018 |
bleeding | -0.017 |
Ros | -0.016 |
ir | -0.016 |
Token | him |
Token ID | 683 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
stalls | +0.039 |
stall | +0.037 |
hike | +0.037 |
banks | +0.037 |
flavors | +0.037 |
Neg logit contributions | |
weeping | -0.021 |
crying | -0.020 |
bleeding | -0.020 |
Ros | -0.020 |
ir | -0.019 |
Token | if |
Token ID | 611 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
stalls | +0.100 |
banks | +0.095 |
flavors | +0.094 |
stall | +0.093 |
fare | +0.092 |
Neg logit contributions | |
crying | -0.056 |
weeping | -0.056 |
Ros | -0.053 |
Ros | -0.052 |
Emily | -0.051 |
Token | he |
Token ID | 339 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
crying | +0.024 |
weeping | +0.024 |
Ros | +0.024 |
Ros | +0.024 |
bleeding | +0.023 |
Neg logit contributions | |
stalls | -0.021 |
stall | -0.020 |
banks | -0.020 |
fare | -0.020 |
flavors | -0.019 |
Token | did |
Token ID | 750 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
stalls | +0.095 |
banks | +0.088 |
stall | +0.088 |
fare | +0.086 |
hike | +0.084 |
Neg logit contributions | |
crying | -0.085 |
weeping | -0.084 |
bleeding | -0.083 |
Ros | -0.081 |
apped | -0.080 |
Token | his |
Token ID | 465 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
stalls | +0.094 |
stall | +0.090 |
banks | +0.089 |
fare | +0.086 |
hike | +0.086 |
Neg logit contributions | |
crying | -0.038 |
bleeding | -0.036 |
weeping | -0.034 |
blood | -0.033 |
Ros | -0.031 |
Token | homework |
Token ID | 26131 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
stalls | +0.111 |
stall | +0.102 |
banks | +0.096 |
fare | +0.092 |
nic | +0.091 |
Neg logit contributions | |
crying | -0.103 |
weeping | -0.098 |
bleeding | -0.098 |
microphone | -0.093 |
Ros | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -9.12e-05 |
Pos logit contributions | |
stalls | +0.193 |
banks | +0.183 |
stall | +0.181 |
hike | +0.178 |
flavors | +0.176 |
Neg logit contributions | |
crying | -0.117 |
bleeding | -0.108 |
weeping | -0.106 |
apped | -0.099 |
microphone | -0.098 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
stalls | +0.000 |
fare | +0.000 |
stall | +0.000 |
hike | +0.000 |
banks | +0.000 |
Neg logit contributions | |
crying | -0.000 |
weeping | -0.000 |
Ros | -0.000 |
Ros | -0.000 |
bleeding | -0.000 |
Token | my |
Token ID | 1820 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
weeping | +0.002 |
Ros | +0.002 |
ir | +0.002 |
crying | +0.002 |
bleeding | +0.002 |
Neg logit contributions | |
stalls | -0.004 |
flavors | -0.004 |
hike | -0.004 |
stall | -0.004 |
banks | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
crying | +0.006 |
weeping | +0.006 |
bleeding | +0.006 |
Ros | +0.005 |
apped | +0.005 |
Neg logit contributions | |
stalls | -0.008 |
fare | -0.007 |
stall | -0.007 |
banks | -0.007 |
hike | -0.007 |
Token | no |
Token ID | 645 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
stalls | +0.051 |
banks | +0.048 |
hike | +0.047 |
stall | +0.047 |
fare | +0.046 |
Neg logit contributions | |
crying | -0.048 |
weeping | -0.047 |
bleeding | -0.047 |
Ros | -0.045 |
apped | -0.044 |
Token | Rachel |
Token ID | 15984 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
stalls | +0.038 |
stall | +0.036 |
hike | +0.036 |
flavors | +0.036 |
banks | +0.035 |
Neg logit contributions | |
weeping | -0.016 |
bleeding | -0.016 |
crying | -0.015 |
Ros | -0.015 |
ir | -0.015 |
Token | would |
Token ID | 561 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
fare | +0.023 |
stalls | +0.022 |
stall | +0.021 |
goods | +0.021 |
list | +0.021 |
Neg logit contributions | |
crying | -0.016 |
weeping | -0.016 |
microphone | -0.016 |
Emily | -0.015 |
el | -0.015 |
Token | also |
Token ID | 635 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
crying | +0.019 |
weeping | +0.019 |
bleeding | +0.018 |
ir | +0.017 |
microphone | +0.017 |
Neg logit contributions | |
stalls | -0.025 |
cases | -0.023 |
flavors | -0.023 |
stall | -0.023 |
fare | -0.023 |
Token | teach |
Token ID | 4545 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
stalls | +0.048 |
stall | +0.044 |
flavors | +0.044 |
fare | +0.044 |
banks | +0.044 |
Neg logit contributions | |
weeping | -0.041 |
crying | -0.041 |
bleeding | -0.039 |
ir | -0.038 |
streaming | -0.038 |
Token | Jack |
Token ID | 3619 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
stalls | +0.029 |
hike | +0.027 |
flavors | +0.027 |
stall | +0.027 |
experiments | +0.026 |
Neg logit contributions | |
bleeding | -0.020 |
weeping | -0.019 |
Ros | -0.019 |
ir | -0.019 |
apped | -0.019 |
Token | maths |
Token ID | 47761 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
stalls | +0.046 |
fare | +0.045 |
stall | +0.044 |
banks | +0.044 |
hike | +0.043 |
Neg logit contributions | |
crying | -0.025 |
weeping | -0.024 |
Emily | -0.022 |
bleeding | -0.021 |
aps | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
stalls | +0.184 |
ranc | +0.183 |
banks | +0.182 |
hike | +0.181 |
stall | +0.179 |
Neg logit contributions | |
crying | -0.101 |
microphone | -0.098 |
together | -0.096 |
aps | -0.096 |
accidents | -0.094 |
Token | stories |
Token ID | 3923 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
stalls | +0.027 |
stall | +0.026 |
hike | +0.025 |
banks | +0.025 |
fare | +0.025 |
Neg logit contributions | |
weeping | -0.024 |
crying | -0.024 |
Ros | -0.024 |
bleeding | -0.023 |
apped | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
stalls | +0.087 |
banks | +0.086 |
stall | +0.082 |
hike | +0.082 |
ranc | +0.080 |
Neg logit contributions | |
crying | -0.050 |
weeping | -0.049 |
apped | -0.048 |
streaming | -0.048 |
bleeding | -0.047 |
Token | Jack |
Token ID | 3619 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
stalls | +0.023 |
stall | +0.021 |
hike | +0.021 |
banks | +0.021 |
flavors | +0.021 |
Neg logit contributions | |
weeping | -0.015 |
bleeding | -0.015 |
crying | -0.015 |
ir | -0.015 |
Ros | -0.015 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
weeping | +0.006 |
crying | +0.006 |
apped | +0.006 |
el | +0.006 |
microphone | +0.006 |
Neg logit contributions | |
stalls | -0.007 |
fare | -0.007 |
stall | -0.007 |
list | -0.007 |
hike | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
stalls | +0.011 |
experiments | +0.011 |
hike | +0.011 |
list | +0.011 |
banks | +0.011 |
Neg logit contributions | |
ir | -0.013 |
bleeding | -0.013 |
weeping | -0.012 |
w | -0.012 |
blood | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -7.86e-04 |
Pos logit contributions | |
hike | +0.013 |
stalls | +0.012 |
stall | +0.012 |
books | +0.011 |
experiments | +0.011 |
Neg logit contributions | |
bleeding | -0.021 |
streaming | -0.021 |
weeping | -0.021 |
crying | -0.020 |
blood | -0.019 |
Token | After |
Token ID | 3260 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
stalls | +0.001 |
hike | +0.001 |
stall | +0.001 |
banks | +0.001 |
nic | +0.001 |
Neg logit contributions | |
weeping | -0.001 |
crying | -0.001 |
bleeding | -0.001 |
blood | -0.001 |
streaming | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
stalls | +0.042 |
stall | +0.039 |
hike | +0.039 |
flavors | +0.039 |
banks | +0.039 |
Neg logit contributions | |
weeping | -0.032 |
crying | -0.031 |
Ros | -0.031 |
bleeding | -0.030 |
ir | -0.030 |
Token | finished |
Token ID | 5201 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
stalls | +0.095 |
banks | +0.089 |
fare | +0.088 |
flavors | +0.088 |
stall | +0.087 |
Neg logit contributions | |
ir | -0.077 |
weeping | -0.076 |
crying | -0.075 |
Ros | -0.075 |
el | -0.075 |
Token | shopping |
Token ID | 9735 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
stalls | +0.041 |
fare | +0.041 |
flavors | +0.040 |
banks | +0.040 |
nic | +0.039 |
Neg logit contributions | |
weeping | -0.028 |
crying | -0.027 |
el | -0.025 |
ir | -0.025 |
Ros | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +9.34e-03 |
Pos logit contributions | |
nic | +0.185 |
hike | +0.180 |
banks | +0.179 |
stalls | +0.178 |
fare | +0.175 |
Neg logit contributions | |
crying | -0.110 |
apped | -0.110 |
weeping | -0.104 |
el | -0.100 |
Ros | -0.097 |
Token | they |
Token ID | 484 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
ir | +0.012 |
ez | +0.011 |
bleeding | +0.011 |
ivering | +0.011 |
weeping | +0.011 |
Neg logit contributions | |
experiments | -0.019 |
hike | -0.019 |
stalls | -0.018 |
shelves | -0.017 |
list | -0.017 |
Token | went |
Token ID | 1816 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
stalls | +0.046 |
fare | +0.045 |
flavors | +0.044 |
banks | +0.044 |
experiments | +0.043 |
Neg logit contributions | |
apped | -0.038 |
weeping | -0.038 |
crying | -0.038 |
Ros | -0.037 |
ir | -0.036 |
Token | home |
Token ID | 1363 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
weeping | +0.011 |
crying | +0.011 |
Ros | +0.011 |
bleeding | +0.010 |
apped | +0.010 |
Neg logit contributions | |
stalls | -0.020 |
flavors | -0.019 |
hike | -0.019 |
banks | -0.019 |
stall | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
stalls | +0.025 |
hike | +0.024 |
flavors | +0.024 |
banks | +0.024 |
stall | +0.024 |
Neg logit contributions | |
crying | -0.019 |
weeping | -0.019 |
bleeding | -0.018 |
apped | -0.017 |
Ros | -0.017 |
Token | could |
Token ID | 714 |
Feature activation | +9.17e-04 |
Pos logit contributions | |
stalls | +0.058 |
hike | +0.054 |
stall | +0.053 |
flavors | +0.053 |
banks | +0.052 |
Neg logit contributions | |
weeping | -0.074 |
Ros | -0.073 |
crying | -0.073 |
bleeding | -0.072 |
ir | -0.072 |
Token | only |
Token ID | 691 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
weeping | +0.001 |
crying | +0.001 |
bleeding | +0.001 |
Ros | +0.001 |
ir | +0.001 |
Neg logit contributions | |
stalls | -0.002 |
stall | -0.001 |
hike | -0.001 |
flavors | -0.001 |
banks | -0.001 |
Token | watch |
Token ID | 2342 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
stalls | +0.085 |
stall | +0.079 |
hike | +0.077 |
banks | +0.077 |
flavors | +0.077 |
Neg logit contributions | |
weeping | -0.079 |
crying | -0.078 |
bleeding | -0.077 |
Ros | -0.075 |
ir | -0.075 |
Token | TV |
Token ID | 3195 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
stalls | +0.059 |
hike | +0.056 |
stall | +0.056 |
flavors | +0.055 |
banks | +0.055 |
Neg logit contributions | |
weeping | -0.041 |
Ros | -0.041 |
crying | -0.040 |
ir | -0.040 |
bleeding | -0.040 |
Token | for |
Token ID | 329 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
stalls | +0.116 |
stall | +0.110 |
flavors | +0.109 |
banks | +0.109 |
hike | +0.106 |
Neg logit contributions | |
crying | -0.073 |
weeping | -0.071 |
bleeding | -0.069 |
microphone | -0.068 |
Ros | -0.065 |
Token | 30 |
Token ID | 1542 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
stalls | +0.030 |
hike | +0.029 |
flavors | +0.028 |
stall | +0.028 |
banks | +0.028 |
Neg logit contributions | |
weeping | -0.027 |
apped | -0.026 |
Ros | -0.026 |
bleeding | -0.026 |
crying | -0.026 |
Token | minutes |
Token ID | 2431 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
banks | +0.158 |
fare | +0.158 |
stalls | +0.157 |
stall | +0.155 |
hike | +0.153 |
Neg logit contributions | |
crying | -0.123 |
ir | -0.121 |
el | -0.120 |
bleeding | -0.120 |
itt | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | -3.68e-03 |
Pos logit contributions | |
stalls | +0.086 |
hike | +0.082 |
stall | +0.082 |
flavors | +0.081 |
banks | +0.080 |
Neg logit contributions | |
crying | -0.075 |
weeping | -0.074 |
bleeding | -0.072 |
apped | -0.071 |
ir | -0.071 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
stalls | +0.008 |
hike | +0.007 |
stall | +0.007 |
banks | +0.007 |
flavors | +0.007 |
Neg logit contributions | |
weeping | -0.004 |
crying | -0.004 |
Ros | -0.004 |
bleeding | -0.004 |
ir | -0.004 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
stalls | +0.013 |
fare | +0.013 |
stall | +0.013 |
hike | +0.012 |
banks | +0.012 |
Neg logit contributions | |
crying | -0.009 |
weeping | -0.009 |
bleeding | -0.009 |
Ros | -0.009 |
apped | -0.009 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
stalls | +0.030 |
stall | +0.028 |
hike | +0.028 |
banks | +0.028 |
flavors | +0.028 |
Neg logit contributions | |
weeping | -0.012 |
crying | -0.012 |
Ros | -0.012 |
bleeding | -0.012 |
ir | -0.012 |
Token | " |
Token ID | 1 |
Feature activation | +2.31e-03 |
Pos logit contributions | |
Ros | +0.023 |
ir | +0.020 |
Sad | +0.019 |
apped | +0.019 |
Emily | +0.019 |
Neg logit contributions | |
flavors | -0.028 |
stalls | -0.028 |
list | -0.028 |
hike | -0.028 |
fare | -0.028 |
Token | Do |
Token ID | 5211 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
weeping | +0.003 |
crying | +0.003 |
bleeding | +0.003 |
ir | +0.003 |
Ros | +0.003 |
Neg logit contributions | |
stalls | -0.005 |
stall | -0.005 |
hike | -0.005 |
flavors | -0.005 |
banks | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
stalls | +0.041 |
stall | +0.040 |
banks | +0.039 |
fare | +0.039 |
bank | +0.038 |
Neg logit contributions | |
Ros | -0.007 |
ir | -0.006 |
crying | -0.006 |
Ros | -0.005 |
weeping | -0.005 |
Token | really |
Token ID | 1107 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
stalls | +0.071 |
stall | +0.067 |
belts | +0.064 |
flavors | +0.063 |
fare | +0.063 |
Neg logit contributions | |
ir | -0.062 |
weeping | -0.060 |
crying | -0.058 |
Ros | -0.057 |
Emily | -0.056 |
Token | do |
Token ID | 466 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
stalls | +0.100 |
stall | +0.096 |
belts | +0.095 |
cases | +0.094 |
fare | +0.092 |
Neg logit contributions | |
weeping | -0.065 |
crying | -0.065 |
ir | -0.060 |
bleeding | -0.058 |
Ros | -0.055 |
Token | maths |
Token ID | 47761 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
stalls | +0.057 |
stall | +0.053 |
hike | +0.053 |
banks | +0.052 |
flavors | +0.052 |
Neg logit contributions | |
weeping | -0.031 |
crying | -0.031 |
Ros | -0.030 |
microphone | -0.029 |
ir | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
stalls | +0.193 |
stall | +0.186 |
banks | +0.184 |
hike | +0.184 |
fare | +0.181 |
Neg logit contributions | |
crying | -0.097 |
microphone | -0.096 |
weeping | -0.094 |
Ros | -0.093 |
Emily | -0.091 |
Token | here |
Token ID | 994 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
weeping | +0.007 |
crying | +0.007 |
Ros | +0.007 |
ir | +0.006 |
bleeding | +0.006 |
Neg logit contributions | |
stalls | -0.011 |
hike | -0.010 |
stall | -0.010 |
banks | -0.010 |
flavors | -0.010 |
Token | ?" |
Token ID | 1701 |
Feature activation | +9.26e-03 |
Pos logit contributions | |
stalls | +0.033 |
hike | +0.030 |
banks | +0.030 |
fare | +0.030 |
stall | +0.030 |
Neg logit contributions | |
weeping | -0.019 |
crying | -0.019 |
Ros | -0.018 |
ir | -0.018 |
bleeding | -0.018 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
weeping | +0.016 |
crying | +0.016 |
Ros | +0.015 |
bleeding | +0.015 |
ir | +0.015 |
Neg logit contributions | |
stalls | -0.014 |
hike | -0.014 |
stall | -0.013 |
flavors | -0.013 |
fare | -0.013 |
Token | Amanda |
Token ID | 23040 |
Feature activation | -6.60e-03 |
Pos logit contributions | |
weeping | +0.019 |
bleeding | +0.019 |
Ros | +0.018 |
crying | +0.018 |
ir | +0.018 |
Neg logit contributions | |
stalls | -0.025 |
stall | -0.023 |
hike | -0.023 |
flavors | -0.023 |
banks | -0.023 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.94e-03 |
Pos logit contributions | |
stalls | +0.077 |
stall | +0.073 |
hike | +0.073 |
banks | +0.073 |
flavors | +0.072 |
Neg logit contributions | |
weeping | -0.043 |
crying | -0.042 |
Ros | -0.042 |
bleeding | -0.041 |
ir | -0.040 |
Token | if |
Token ID | 611 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
stalls | +0.017 |
banks | +0.017 |
flavors | +0.017 |
stall | +0.017 |
hike | +0.017 |
Neg logit contributions | |
weeping | -0.009 |
crying | -0.009 |
Ros | -0.008 |
bleeding | -0.008 |
Ros | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
crying | +0.013 |
weeping | +0.013 |
bleeding | +0.012 |
Ros | +0.012 |
Ros | +0.012 |
Neg logit contributions | |
stalls | -0.019 |
banks | -0.019 |
stall | -0.018 |
fare | -0.018 |
flavors | -0.018 |
Token | could |
Token ID | 714 |
Feature activation | -5.95e-03 |
Pos logit contributions | |
stalls | +0.110 |
banks | +0.104 |
fare | +0.103 |
stall | +0.101 |
hike | +0.099 |
Neg logit contributions | |
crying | -0.074 |
apped | -0.074 |
weeping | -0.074 |
Ros | -0.072 |
Ros | -0.070 |
Token | try |
Token ID | 1949 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
stalls | +0.011 |
stall | +0.010 |
flavors | +0.010 |
banks | +0.010 |
fare | +0.010 |
Neg logit contributions | |
weeping | -0.009 |
crying | -0.008 |
Ros | -0.008 |
ir | -0.008 |
el | -0.008 |
Token | yoga |
Token ID | 20351 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
stalls | +0.049 |
stall | +0.047 |
hike | +0.047 |
fare | +0.046 |
banks | +0.046 |
Neg logit contributions | |
weeping | -0.033 |
crying | -0.032 |
bleeding | -0.031 |
Ros | -0.031 |
ir | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -7.25e-03 |
Pos logit contributions | |
stalls | +0.198 |
fare | +0.193 |
banks | +0.189 |
ranc | +0.185 |
hike | +0.184 |
Neg logit contributions | |
together | -0.093 |
crying | -0.092 |
microphone | -0.092 |
aps | -0.091 |
Emily | -0.090 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
stalls | +0.014 |
stall | +0.014 |
hike | +0.014 |
flavors | +0.013 |
banks | +0.013 |
Neg logit contributions | |
weeping | -0.009 |
bleeding | -0.009 |
crying | -0.009 |
Ros | -0.009 |
ir | -0.009 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
stalls | +0.032 |
stall | +0.030 |
hike | +0.030 |
flavors | +0.030 |
banks | +0.030 |
Neg logit contributions | |
weeping | -0.019 |
Ros | -0.018 |
crying | -0.018 |
bleeding | -0.018 |
ir | -0.018 |
Token | said |
Token ID | 531 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
crying | +0.019 |
weeping | +0.019 |
Ros | +0.019 |
bleeding | +0.019 |
apped | +0.018 |
Neg logit contributions | |
stalls | -0.021 |
banks | -0.019 |
stall | -0.019 |
hike | -0.019 |
fare | -0.019 |
Token | yes |
Token ID | 3763 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
stalls | +0.057 |
banks | +0.055 |
hike | +0.053 |
fare | +0.052 |
stall | +0.052 |
Neg logit contributions | |
crying | -0.054 |
weeping | -0.053 |
bleeding | -0.052 |
apped | -0.050 |
microphone | -0.049 |
Token | Bob |
Token ID | 5811 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
stalls | +0.001 |
hike | +0.001 |
stall | +0.001 |
flavors | +0.001 |
banks | +0.001 |
Neg logit contributions | |
weeping | -0.001 |
crying | -0.001 |
Ros | -0.001 |
bleeding | -0.001 |
ir | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
stalls | +0.009 |
fare | +0.009 |
stall | +0.009 |
flavors | +0.009 |
hike | +0.009 |
Neg logit contributions | |
crying | -0.008 |
weeping | -0.008 |
el | -0.008 |
bleeding | -0.007 |
Ros | -0.007 |
Token | grandma |
Token ID | 49890 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
stalls | +0.024 |
stall | +0.023 |
hike | +0.023 |
flavors | +0.023 |
banks | +0.023 |
Neg logit contributions | |
weeping | -0.017 |
Ros | -0.017 |
bleeding | -0.017 |
crying | -0.017 |
ir | -0.017 |
Token | took |
Token ID | 1718 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
crying | +0.017 |
weeping | +0.017 |
Emily | +0.016 |
streaming | +0.016 |
Ros | +0.016 |
Neg logit contributions | |
stalls | -0.022 |
fare | -0.022 |
banks | -0.022 |
stall | -0.021 |
hike | -0.021 |
Token | him |
Token ID | 683 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
weeping | +0.013 |
Ros | +0.012 |
crying | +0.012 |
bleeding | +0.012 |
ir | +0.012 |
Neg logit contributions | |
stalls | -0.022 |
hike | -0.021 |
stall | -0.020 |
flavors | -0.020 |
banks | -0.020 |
Token | shopping |
Token ID | 9735 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
stalls | +0.023 |
flavors | +0.022 |
stall | +0.022 |
banks | +0.021 |
hike | +0.021 |
Neg logit contributions | |
crying | -0.013 |
weeping | -0.013 |
bleeding | -0.013 |
Ros | -0.013 |
ir | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
nic | +0.205 |
hike | +0.203 |
banks | +0.192 |
Street | +0.190 |
pm | +0.187 |
Neg logit contributions | |
together | -0.083 |
apped | -0.082 |
crying | -0.082 |
el | -0.077 |
microphone | -0.070 |
Token | clothes |
Token ID | 8242 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
stalls | +0.041 |
banks | +0.039 |
stall | +0.039 |
hike | +0.039 |
flavors | +0.038 |
Neg logit contributions | |
crying | -0.019 |
weeping | -0.018 |
Ros | -0.018 |
bleeding | -0.018 |
ir | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +8.79e-04 |
Pos logit contributions | |
stalls | +0.077 |
hike | +0.075 |
flavors | +0.075 |
nic | +0.074 |
stall | +0.073 |
Neg logit contributions | |
crying | -0.045 |
weeping | -0.042 |
bleeding | -0.041 |
streaming | -0.040 |
el | -0.039 |
Token | She |
Token ID | 1375 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
crying | +0.001 |
weeping | +0.001 |
Ros | +0.001 |
apped | +0.001 |
streaming | +0.001 |
Neg logit contributions | |
stalls | -0.002 |
flavors | -0.002 |
hike | -0.002 |
belts | -0.002 |
fare | -0.002 |
Token | showed |
Token ID | 3751 |
Feature activation | -3.11e-03 |
Pos logit contributions | |
stalls | +0.024 |
fare | +0.024 |
banks | +0.024 |
hike | +0.023 |
stall | +0.023 |
Neg logit contributions | |
crying | -0.018 |
apped | -0.017 |
weeping | -0.017 |
Ros | -0.017 |
Emily | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
stalls | +0.018 |
hike | +0.017 |
stall | +0.017 |
banks | +0.016 |
list | +0.016 |
Neg logit contributions | |
weeping | -0.021 |
streaming | -0.021 |
bleeding | -0.021 |
crying | -0.020 |
ir | -0.020 |
Token | After |
Token ID | 3260 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
stalls | +0.007 |
stall | +0.007 |
hike | +0.007 |
fare | +0.006 |
flavors | +0.006 |
Neg logit contributions | |
Ros | -0.006 |
weeping | -0.005 |
bleeding | -0.005 |
crying | -0.005 |
ir | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
stalls | +0.028 |
hike | +0.026 |
stall | +0.026 |
banks | +0.026 |
flavors | +0.026 |
Neg logit contributions | |
weeping | -0.025 |
Ros | -0.025 |
crying | -0.024 |
bleeding | -0.024 |
ir | -0.024 |
Token | completed |
Token ID | 5668 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
stalls | +0.095 |
experiments | +0.090 |
banks | +0.090 |
fare | +0.087 |
flavors | +0.087 |
Neg logit contributions | |
el | -0.083 |
ir | -0.081 |
streaming | -0.080 |
apped | -0.079 |
crying | -0.077 |
Token | their |
Token ID | 511 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
stalls | +0.060 |
hike | +0.057 |
flavors | +0.057 |
fare | +0.056 |
banks | +0.056 |
Neg logit contributions | |
weeping | -0.033 |
crying | -0.033 |
bleeding | -0.031 |
ir | -0.031 |
Ros | -0.030 |
Token | shopping |
Token ID | 9735 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
stalls | +0.068 |
fare | +0.066 |
land | +0.063 |
belts | +0.061 |
nic | +0.060 |
Neg logit contributions | |
el | -0.097 |
crying | -0.095 |
weeping | -0.095 |
microphone | -0.090 |
bleeding | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | +5.76e-03 |
Pos logit contributions | |
nic | +0.206 |
hike | +0.185 |
uries | +0.183 |
fare | +0.181 |
land | +0.181 |
Neg logit contributions | |
crying | -0.092 |
el | -0.091 |
apped | -0.089 |
heart | -0.083 |
weeping | -0.082 |
Token | they |
Token ID | 484 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
ir | +0.008 |
weeping | +0.008 |
bleeding | +0.008 |
el | +0.008 |
Ros | +0.007 |
Neg logit contributions | |
stalls | -0.011 |
hike | -0.010 |
stall | -0.010 |
banks | -0.010 |
list | -0.010 |
Token | went |
Token ID | 1816 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
stalls | +0.048 |
fare | +0.047 |
flavors | +0.047 |
banks | +0.046 |
experiments | +0.046 |
Neg logit contributions | |
apped | -0.040 |
Ros | -0.040 |
weeping | -0.040 |
crying | -0.040 |
ir | -0.039 |
Token | home |
Token ID | 1363 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
crying | +0.015 |
weeping | +0.014 |
apped | +0.013 |
bleeding | +0.013 |
Ros | +0.013 |
Neg logit contributions | |
flavors | -0.029 |
stalls | -0.029 |
banks | -0.028 |
hike | -0.028 |
fare | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e-03 |
Pos logit contributions | |
stalls | +0.022 |
hike | +0.021 |
flavors | +0.021 |
banks | +0.021 |
fare | +0.020 |
Neg logit contributions | |
crying | -0.014 |
weeping | -0.013 |
bleeding | -0.012 |
apped | -0.012 |
Ros | -0.012 |
Token | mum |
Token ID | 25682 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
stalls | +0.091 |
banks | +0.087 |
flavors | +0.085 |
fare | +0.085 |
hike | +0.085 |
Neg logit contributions | |
weeping | -0.042 |
crying | -0.041 |
Ros | -0.038 |
bleeding | -0.038 |
microphone | -0.037 |
Token | if |
Token ID | 611 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
stalls | +0.039 |
flavors | +0.039 |
banks | +0.039 |
fare | +0.038 |
hike | +0.038 |
Neg logit contributions | |
crying | -0.026 |
weeping | -0.026 |
Emily | -0.023 |
Ros | -0.023 |
el | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
crying | +0.021 |
weeping | +0.020 |
Ros | +0.019 |
bleeding | +0.019 |
Ros | +0.019 |
Neg logit contributions | |
stalls | -0.032 |
banks | -0.032 |
fare | -0.031 |
stall | -0.031 |
flavors | -0.031 |
Token | could |
Token ID | 714 |
Feature activation | -3.79e-03 |
Pos logit contributions | |
stalls | +0.107 |
banks | +0.101 |
fare | +0.099 |
stall | +0.098 |
hike | +0.096 |
Neg logit contributions | |
crying | -0.069 |
weeping | -0.068 |
apped | -0.068 |
bleeding | -0.065 |
el | -0.065 |
Token | try |
Token ID | 1949 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
stalls | +0.007 |
stall | +0.007 |
banks | +0.007 |
belts | +0.006 |
flavors | +0.006 |
Neg logit contributions | |
crying | -0.005 |
weeping | -0.005 |
ir | -0.005 |
bleeding | -0.005 |
Ros | -0.005 |
Token | yoga |
Token ID | 20351 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
stalls | +0.045 |
fare | +0.043 |
stall | +0.043 |
banks | +0.042 |
hike | +0.042 |
Neg logit contributions | |
crying | -0.029 |
weeping | -0.029 |
bleeding | -0.027 |
blood | -0.026 |
ir | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
stalls | +0.192 |
fare | +0.187 |
banks | +0.183 |
ranc | +0.181 |
hike | +0.181 |
Neg logit contributions | |
crying | -0.095 |
together | -0.094 |
microphone | -0.093 |
Emily | -0.093 |
aps | -0.092 |
Token | her |
Token ID | 607 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
stalls | +0.048 |
stall | +0.046 |
fare | +0.045 |
banks | +0.044 |
hike | +0.043 |
Neg logit contributions | |
crying | -0.035 |
weeping | -0.034 |
bleeding | -0.033 |
Emily | -0.032 |
Ros | -0.031 |
Token | mum |
Token ID | 25682 |
Feature activation | +8.91e-03 |
Pos logit contributions | |
stalls | +0.034 |
banks | +0.032 |
fare | +0.032 |
stall | +0.031 |
hike | +0.031 |
Neg logit contributions | |
crying | -0.018 |
weeping | -0.018 |
bleeding | -0.017 |
microphone | -0.017 |
apped | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
crying | +0.011 |
Emily | +0.011 |
apped | +0.010 |
weeping | +0.010 |
bleeding | +0.010 |
Neg logit contributions | |
stalls | -0.019 |
banks | -0.019 |
hike | -0.018 |
stall | -0.018 |
fare | -0.018 |
Token | yes |
Token ID | 3763 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
stalls | +0.052 |
banks | +0.050 |
hike | +0.049 |
stall | +0.047 |
fare | +0.047 |
Neg logit contributions | |
crying | -0.046 |
weeping | -0.045 |
bleeding | -0.044 |
apped | -0.043 |
microphone | -0.042 |
Token | wall |
Token ID | 3355 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
stalls | +0.034 |
hike | +0.033 |
flavors | +0.032 |
stall | +0.031 |
banks | +0.031 |
Neg logit contributions | |
crying | -0.033 |
bleeding | -0.033 |
weeping | -0.033 |
microphone | -0.033 |
Ros | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
stalls | +0.015 |
hike | +0.015 |
flavors | +0.015 |
banks | +0.014 |
fare | +0.014 |
Neg logit contributions | |
crying | -0.011 |
weeping | -0.011 |
bleeding | -0.010 |
microphone | -0.010 |
streaming | -0.010 |
Token | It |
Token ID | 632 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
apped | +0.004 |
crying | +0.004 |
uck | +0.004 |
aps | +0.004 |
Ow | +0.004 |
Neg logit contributions | |
experiments | -0.012 |
hike | -0.012 |
fare | -0.012 |
Street | -0.012 |
nic | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
Ros | +0.005 |
crying | +0.005 |
weeping | +0.005 |
bleeding | +0.005 |
Ros | +0.005 |
Neg logit contributions | |
stalls | -0.007 |
stall | -0.007 |
hike | -0.007 |
fare | -0.007 |
banks | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
stalls | +0.060 |
hike | +0.056 |
banks | +0.056 |
flavors | +0.056 |
stall | +0.056 |
Neg logit contributions | |
weeping | -0.054 |
crying | -0.053 |
Ros | -0.052 |
bleeding | -0.051 |
ir | -0.051 |
Token | DO |
Token ID | 18227 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
stalls | +0.020 |
stall | +0.019 |
hike | +0.018 |
flavors | +0.018 |
fare | +0.018 |
Neg logit contributions | |
weeping | -0.016 |
crying | -0.015 |
bleeding | -0.015 |
Ros | -0.015 |
ir | -0.015 |
Token | NOT |
Token ID | 5626 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
stalls | +0.191 |
flavors | +0.185 |
stall | +0.183 |
hike | +0.177 |
fare | +0.177 |
Neg logit contributions | |
ir | -0.107 |
Ros | -0.104 |
streaming | -0.100 |
bleeding | -0.099 |
weeping | -0.097 |
Token | T |
Token ID | 309 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
stalls | +0.076 |
hike | +0.071 |
stall | +0.071 |
flavors | +0.071 |
banks | +0.070 |
Neg logit contributions | |
weeping | -0.059 |
crying | -0.058 |
Ros | -0.058 |
bleeding | -0.057 |
ir | -0.057 |
Token | OU |
Token ID | 2606 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
stalls | +0.030 |
banks | +0.028 |
flavors | +0.028 |
stall | +0.028 |
hike | +0.028 |
Neg logit contributions | |
ir | -0.023 |
weeping | -0.022 |
crying | -0.021 |
apped | -0.021 |
Ros | -0.021 |
Token | CH |
Token ID | 3398 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
stalls | +0.033 |
hike | +0.032 |
stall | +0.032 |
banks | +0.031 |
flavors | +0.031 |
Neg logit contributions | |
weeping | -0.027 |
crying | -0.026 |
Ros | -0.026 |
bleeding | -0.026 |
ir | -0.026 |
Token | ". |
Token ID | 1911 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
stalls | +0.036 |
stall | +0.035 |
hike | +0.035 |
banks | +0.034 |
fare | +0.034 |
Neg logit contributions | |
weeping | -0.029 |
Ros | -0.029 |
crying | -0.028 |
bleeding | -0.028 |
ir | -0.027 |
Token | who |
Token ID | 508 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
weeping | +0.048 |
Ros | +0.048 |
bleeding | +0.047 |
ir | +0.047 |
streaming | +0.046 |
Neg logit contributions | |
stalls | -0.057 |
stall | -0.055 |
hike | -0.053 |
banks | -0.052 |
flavors | -0.052 |
Token | really |
Token ID | 1107 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
stalls | +0.011 |
stall | +0.010 |
hike | +0.010 |
flavors | +0.010 |
banks | +0.010 |
Neg logit contributions | |
weeping | -0.015 |
Ros | -0.015 |
ir | -0.014 |
crying | -0.014 |
bleeding | -0.014 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
stalls | +0.027 |
stall | +0.025 |
hike | +0.025 |
banks | +0.025 |
flavors | +0.025 |
Neg logit contributions | |
weeping | -0.029 |
crying | -0.028 |
Ros | -0.028 |
bleeding | -0.028 |
ir | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
crying | +0.013 |
weeping | +0.013 |
bleeding | +0.012 |
blood | +0.012 |
Ros | +0.012 |
Neg logit contributions | |
stalls | -0.021 |
banks | -0.020 |
stall | -0.020 |
fare | -0.020 |
hike | -0.020 |
Token | try |
Token ID | 1949 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
stalls | +0.030 |
cases | +0.027 |
stall | +0.027 |
fare | +0.027 |
belts | +0.027 |
Neg logit contributions | |
crying | -0.024 |
weeping | -0.024 |
Ros | -0.024 |
microphone | -0.024 |
Ros | -0.023 |
Token | yoga |
Token ID | 20351 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
stalls | +0.031 |
fare | +0.031 |
banks | +0.030 |
stall | +0.030 |
flavors | +0.029 |
Neg logit contributions | |
crying | -0.017 |
weeping | -0.017 |
blood | -0.016 |
bleeding | -0.016 |
microphone | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
stalls | +0.197 |
fare | +0.195 |
flavors | +0.187 |
banks | +0.186 |
stall | +0.182 |
Neg logit contributions | |
together | -0.094 |
microphone | -0.092 |
aps | -0.090 |
crying | -0.089 |
Emily | -0.086 |
Token | She |
Token ID | 1375 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
weeping | +0.004 |
Ros | +0.004 |
Ros | +0.004 |
crying | +0.004 |
apped | +0.004 |
Neg logit contributions | |
stalls | -0.014 |
hike | -0.013 |
flavors | -0.013 |
banks | -0.013 |
fare | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
fare | +0.027 |
stalls | +0.026 |
stall | +0.025 |
goods | +0.024 |
banks | +0.024 |
Neg logit contributions | |
crying | -0.016 |
Ros | -0.016 |
bleeding | -0.016 |
el | -0.016 |
apped | -0.016 |
Token | only |
Token ID | 691 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
weeping | +0.014 |
Ros | +0.014 |
crying | +0.014 |
ir | +0.014 |
bleeding | +0.014 |
Neg logit contributions | |
stalls | -0.020 |
stall | -0.019 |
hike | -0.019 |
banks | -0.019 |
flavors | -0.019 |
Token | three |
Token ID | 1115 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
stalls | +0.055 |
banks | +0.053 |
hike | +0.053 |
flavors | +0.052 |
stall | +0.052 |
Neg logit contributions | |
crying | -0.022 |
weeping | -0.022 |
bleeding | -0.021 |
apped | -0.020 |
Ros | -0.019 |
Token | red |
Token ID | 2266 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
Ros | +0.024 |
bleeding | +0.023 |
weeping | +0.023 |
ir | +0.023 |
apped | +0.023 |
Neg logit contributions | |
stalls | -0.027 |
stall | -0.026 |
hike | -0.026 |
flavors | -0.025 |
list | -0.025 |
Token | button |
Token ID | 4936 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
stalls | +0.005 |
stall | +0.004 |
hike | +0.004 |
flavors | +0.004 |
banks | +0.004 |
Neg logit contributions | |
weeping | -0.004 |
Ros | -0.004 |
bleeding | -0.004 |
crying | -0.004 |
ir | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
stalls | +0.026 |
hike | +0.025 |
stall | +0.025 |
banks | +0.024 |
flavors | +0.024 |
Neg logit contributions | |
weeping | -0.013 |
crying | -0.013 |
Ros | -0.012 |
bleeding | -0.012 |
ir | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
weeping | +0.022 |
crying | +0.022 |
Ros | +0.022 |
bleeding | +0.021 |
ir | +0.021 |
Neg logit contributions | |
stalls | -0.023 |
stall | -0.022 |
hike | -0.022 |
banks | -0.021 |
flavors | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
stalls | +0.038 |
hike | +0.035 |
banks | +0.035 |
stall | +0.035 |
flavors | +0.035 |
Neg logit contributions | |
weeping | -0.041 |
crying | -0.040 |
Ros | -0.039 |
bleeding | -0.039 |
ir | -0.039 |
Token | DO |
Token ID | 18227 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
stalls | +0.017 |
flavors | +0.016 |
fare | +0.016 |
stall | +0.016 |
hike | +0.016 |
Neg logit contributions | |
weeping | -0.015 |
crying | -0.014 |
bleeding | -0.014 |
blood | -0.013 |
apped | -0.013 |
Token | NOT |
Token ID | 5626 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
stalls | +0.186 |
flavors | +0.176 |
stall | +0.175 |
hike | +0.171 |
fare | +0.169 |
Neg logit contributions | |
ir | -0.117 |
Ros | -0.111 |
bleeding | -0.111 |
weeping | -0.111 |
streaming | -0.109 |
Token | PRESS |
Token ID | 44310 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
stalls | +0.080 |
stall | +0.076 |
hike | +0.076 |
banks | +0.075 |
flavors | +0.074 |
Neg logit contributions | |
weeping | -0.060 |
Ros | -0.059 |
crying | -0.059 |
bleeding | -0.059 |
ir | -0.057 |
Token | ." |
Token ID | 526 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
stalls | +0.110 |
flavors | +0.103 |
hike | +0.102 |
stall | +0.101 |
fare | +0.100 |
Neg logit contributions | |
ir | -0.105 |
weeping | -0.105 |
apped | -0.103 |
Ros | -0.103 |
crying | -0.102 |
Token | She |
Token ID | 1375 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
stalls | +0.025 |
stall | +0.024 |
hike | +0.024 |
banks | +0.024 |
flavors | +0.024 |
Neg logit contributions | |
weeping | -0.015 |
Ros | -0.014 |
bleeding | -0.014 |
ir | -0.014 |
crying | -0.014 |
Token | couldn |
Token ID | 3521 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
stalls | +0.026 |
fare | +0.024 |
stall | +0.024 |
hike | +0.024 |
banks | +0.023 |
Neg logit contributions | |
Ros | -0.023 |
crying | -0.023 |
weeping | -0.023 |
bleeding | -0.022 |
apped | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -7.73e-04 |
Pos logit contributions | |
stalls | +0.046 |
hike | +0.044 |
stall | +0.044 |
flavors | +0.043 |
banks | +0.043 |
Neg logit contributions | |
weeping | -0.021 |
Ros | -0.021 |
bleeding | -0.020 |
ir | -0.020 |
crying | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
stalls | +0.001 |
stall | +0.001 |
hike | +0.001 |
list | +0.001 |
flavors | +0.001 |
Neg logit contributions | |
ir | -0.001 |
Ros | -0.001 |
weeping | -0.001 |
bleeding | -0.001 |
streaming | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | +7.51e-03 |
Pos logit contributions | |
weeping | +0.035 |
ir | +0.035 |
bleeding | +0.035 |
Ros | +0.035 |
blood | +0.034 |
Neg logit contributions | |
stalls | -0.025 |
hike | -0.024 |
stall | -0.023 |
banks | -0.022 |
flavors | -0.022 |
Token | went |
Token ID | 1816 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
weeping | +0.014 |
bleeding | +0.014 |
Ros | +0.014 |
crying | +0.013 |
ir | +0.013 |
Neg logit contributions | |
stalls | -0.011 |
hike | -0.010 |
stall | -0.010 |
banks | -0.010 |
flavors | -0.009 |
Token | grocery |
Token ID | 16918 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
Ros | +0.024 |
weeping | +0.024 |
ir | +0.024 |
bleeding | +0.024 |
crying | +0.023 |
Neg logit contributions | |
stalls | -0.028 |
hike | -0.027 |
stall | -0.027 |
banks | -0.026 |
fare | -0.025 |
Token | shopping |
Token ID | 9735 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
flavors | +0.181 |
nic | +0.174 |
fare | +0.174 |
land | +0.172 |
uries | +0.168 |
Neg logit contributions | |
crying | -0.089 |
together | -0.079 |
weeping | -0.074 |
Ros | -0.071 |
Ros | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
nic | +0.193 |
hike | +0.192 |
flavors | +0.186 |
fare | +0.186 |
banks | +0.184 |
Neg logit contributions | |
apped | -0.093 |
crying | -0.093 |
together | -0.091 |
weeping | -0.080 |
aps | -0.080 |
Token | Laura |
Token ID | 16753 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
flavors | +0.027 |
stalls | +0.027 |
fare | +0.027 |
banks | +0.027 |
hike | +0.027 |
Neg logit contributions | |
weeping | -0.018 |
crying | -0.018 |
apped | -0.017 |
Emily | -0.017 |
Ros | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +5.07e-03 |
Pos logit contributions | |
fare | +0.046 |
flavors | +0.044 |
stalls | +0.043 |
land | +0.043 |
experiments | +0.041 |
Neg logit contributions | |
crying | -0.025 |
weeping | -0.022 |
apped | -0.022 |
Emily | -0.022 |
el | -0.021 |
Token | having |
Token ID | 1719 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
crying | +0.006 |
weeping | +0.006 |
bleeding | +0.006 |
apped | +0.005 |
Ros | +0.005 |
Neg logit contributions | |
stalls | -0.011 |
flavors | -0.011 |
hike | -0.011 |
banks | -0.010 |
fare | -0.010 |
Token | lots |
Token ID | 6041 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
crying | +0.003 |
weeping | +0.003 |
Ros | +0.003 |
bleeding | +0.003 |
Ros | +0.003 |
Neg logit contributions | |
stalls | -0.006 |
stall | -0.006 |
fare | -0.006 |
banks | -0.006 |
hike | -0.006 |
Token | some |
Token ID | 617 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
stalls | +0.121 |
hike | +0.119 |
stall | +0.117 |
list | +0.115 |
banks | +0.115 |
Neg logit contributions | |
crying | -0.060 |
blood | -0.060 |
Ros | -0.058 |
el | -0.058 |
weeping | -0.058 |
Token | food |
Token ID | 2057 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
stalls | +0.079 |
cases | +0.078 |
hike | +0.077 |
fare | +0.076 |
stall | +0.075 |
Neg logit contributions | |
microphone | -0.068 |
el | -0.067 |
blood | -0.067 |
weeping | -0.066 |
bleeding | -0.066 |
Token | at |
Token ID | 379 |
Feature activation | -7.25e-03 |
Pos logit contributions | |
stalls | +0.101 |
hike | +0.100 |
banks | +0.100 |
fare | +0.099 |
cases | +0.098 |
Neg logit contributions | |
together | -0.040 |
Ros | -0.038 |
microphone | -0.036 |
ucky | -0.035 |
crying | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
stalls | +0.015 |
flavors | +0.014 |
hike | +0.014 |
fare | +0.014 |
stall | +0.014 |
Neg logit contributions | |
weeping | -0.008 |
crying | -0.008 |
ir | -0.008 |
el | -0.008 |
bleeding | -0.008 |
Token | farm |
Token ID | 5318 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
cases | +0.016 |
flavors | +0.014 |
belts | +0.014 |
nic | +0.014 |
books | +0.014 |
Neg logit contributions | |
microphone | -0.021 |
crying | -0.020 |
weeping | -0.020 |
bleeding | -0.020 |
el | -0.019 |
Token | cafe |
Token ID | 26725 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
cases | +0.101 |
fare | +0.100 |
nic | +0.100 |
hike | +0.098 |
flavors | +0.097 |
Neg logit contributions | |
together | -0.039 |
crying | -0.036 |
microphone | -0.034 |
Emily | -0.031 |
Ros | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
hike | +0.216 |
banks | +0.213 |
fare | +0.205 |
quest | +0.205 |
nic | +0.203 |
Neg logit contributions | |
together | -0.066 |
on | -0.050 |
in | -0.049 |
ing | -0.047 |
ful | -0.046 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
stalls | +0.014 |
stall | +0.013 |
hike | +0.013 |
banks | +0.012 |
flavors | +0.012 |
Neg logit contributions | |
weeping | -0.012 |
bleeding | -0.012 |
ir | -0.012 |
crying | -0.011 |
streaming | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
fare | +0.004 |
experiments | +0.004 |
land | +0.004 |
stalls | +0.004 |
banks | +0.004 |
Neg logit contributions | |
crying | -0.001 |
Emily | -0.001 |
apped | -0.001 |
weeping | -0.001 |
el | -0.001 |
Token | Sam |
Token ID | 3409 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
stalls | +0.066 |
fare | +0.063 |
stall | +0.063 |
banks | +0.062 |
flavors | +0.062 |
Neg logit contributions | |
crying | -0.017 |
weeping | -0.016 |
el | -0.016 |
ir | -0.016 |
Emily | -0.016 |
Token | were |
Token ID | 547 |
Feature activation | +2.48e-04 |
Pos logit contributions | |
land | +0.056 |
experiments | +0.055 |
rink | +0.053 |
fare | +0.053 |
pm | +0.052 |
Neg logit contributions | |
both | -0.022 |
apped | -0.018 |
el | -0.018 |
wiped | -0.016 |
together | -0.015 |
Token | From |
Token ID | 3574 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
bleeding | +0.025 |
ir | +0.025 |
weeping | +0.025 |
Ros | +0.024 |
crying | +0.024 |
Neg logit contributions | |
stalls | -0.025 |
stall | -0.024 |
hike | -0.022 |
banks | -0.022 |
flavors | -0.022 |
Token | then |
Token ID | 788 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
stalls | +0.035 |
hike | +0.033 |
stall | +0.033 |
banks | +0.033 |
fare | +0.033 |
Neg logit contributions | |
weeping | -0.028 |
crying | -0.028 |
Ros | -0.027 |
bleeding | -0.027 |
ir | -0.027 |
Token | on |
Token ID | 319 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
weeping | +0.018 |
crying | +0.017 |
Ros | +0.017 |
blood | +0.016 |
bleeding | +0.016 |
Neg logit contributions | |
stalls | -0.032 |
hike | -0.031 |
stall | -0.031 |
list | -0.030 |
fare | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
stalls | +0.021 |
hike | +0.019 |
stall | +0.019 |
flavors | +0.019 |
banks | +0.019 |
Neg logit contributions | |
weeping | -0.020 |
crying | -0.019 |
Ros | -0.019 |
bleeding | -0.019 |
ir | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
bleeding | +0.038 |
weeping | +0.038 |
ir | +0.037 |
Ros | +0.037 |
crying | +0.036 |
Neg logit contributions | |
stalls | -0.034 |
hike | -0.032 |
stall | -0.032 |
flavors | -0.031 |
banks | -0.030 |
Token | whole |
Token ID | 2187 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
weeping | +0.014 |
ir | +0.013 |
Ros | +0.013 |
bleeding | +0.013 |
crying | +0.013 |
Neg logit contributions | |
stalls | -0.022 |
hike | -0.021 |
stall | -0.021 |
flavors | -0.021 |
banks | -0.021 |
Token | family |
Token ID | 1641 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
bleeding | +0.090 |
weeping | +0.089 |
Ros | +0.089 |
ir | +0.088 |
crying | +0.087 |
Neg logit contributions | |
stalls | -0.079 |
hike | -0.074 |
stall | -0.074 |
flavors | -0.071 |
list | -0.069 |
Token | could |
Token ID | 714 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
weeping | +0.057 |
crying | +0.056 |
Ros | +0.056 |
bleeding | +0.055 |
ir | +0.055 |
Neg logit contributions | |
stalls | -0.059 |
stall | -0.055 |
hike | -0.055 |
banks | -0.054 |
flavors | -0.054 |
Token | come |
Token ID | 1282 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
weeping | +0.067 |
crying | +0.066 |
Ros | +0.065 |
ir | +0.064 |
apped | +0.063 |
Neg logit contributions | |
stalls | -0.081 |
stall | -0.076 |
flavors | -0.074 |
fare | -0.073 |
banks | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
weeping | +0.029 |
bleeding | +0.029 |
ir | +0.029 |
Ros | +0.029 |
crying | +0.028 |
Neg logit contributions | |
stalls | -0.046 |
hike | -0.044 |
stall | -0.043 |
banks | -0.043 |
fare | -0.043 |
Token | play |
Token ID | 711 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
weeping | +0.006 |
crying | +0.006 |
Ros | +0.006 |
bleeding | +0.006 |
ir | +0.006 |
Neg logit contributions | |
stalls | -0.007 |
stall | -0.007 |
hike | -0.007 |
flavors | -0.007 |
banks | -0.007 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
stalls | +0.030 |
stall | +0.029 |
flavors | +0.028 |
banks | +0.027 |
fare | +0.027 |
Neg logit contributions | |
Ros | -0.031 |
ir | -0.030 |
bleeding | -0.029 |
blood | -0.029 |
streaming | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
weeping | +0.064 |
crying | +0.063 |
bleeding | +0.060 |
Ros | +0.059 |
streaming | +0.058 |
Neg logit contributions | |
stalls | -0.083 |
hike | -0.079 |
stall | -0.079 |
banks | -0.078 |
fare | -0.078 |
Token | She |
Token ID | 1375 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
weeping | +0.033 |
bleeding | +0.033 |
crying | +0.032 |
ir | +0.032 |
Ros | +0.032 |
Neg logit contributions | |
stalls | -0.045 |
stall | -0.043 |
hike | -0.042 |
banks | -0.041 |
flavors | -0.041 |
Token | hugged |
Token ID | 41130 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
weeping | +0.013 |
crying | +0.012 |
Ros | +0.012 |
bleeding | +0.012 |
ir | +0.012 |
Neg logit contributions | |
stalls | -0.014 |
stall | -0.013 |
hike | -0.013 |
banks | -0.012 |
flavors | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
bleeding | +0.071 |
aps | +0.070 |
Ros | +0.069 |
apped | +0.069 |
apping | +0.069 |
Neg logit contributions | |
stalls | -0.049 |
stall | -0.048 |
hike | -0.046 |
banks | -0.045 |
bank | -0.044 |
Token | fairy |
Token ID | 25607 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
ir | +0.025 |
apped | +0.024 |
Ros | +0.024 |
bleeding | +0.023 |
weeping | +0.023 |
Neg logit contributions | |
stalls | -0.042 |
stall | -0.041 |
hike | -0.040 |
banks | -0.040 |
flavors | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
weeping | +0.082 |
crying | +0.081 |
Ros | +0.080 |
bleeding | +0.080 |
ir | +0.079 |
Neg logit contributions | |
stalls | -0.112 |
hike | -0.105 |
stall | -0.105 |
flavors | -0.104 |
banks | -0.104 |
Token | thanked |
Token ID | 26280 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
weeping | +0.010 |
Ros | +0.010 |
ir | +0.010 |
bleeding | +0.010 |
crying | +0.010 |
Neg logit contributions | |
stalls | -0.010 |
hike | -0.009 |
stall | -0.009 |
flavors | -0.009 |
banks | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
apped | +0.056 |
bleeding | +0.056 |
Ros | +0.053 |
weeping | +0.052 |
aps | +0.052 |
Neg logit contributions | |
stalls | -0.052 |
hike | -0.050 |
stall | -0.049 |
flavors | -0.047 |
banks | -0.046 |
Token | for |
Token ID | 329 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
stalls | +0.009 |
hike | +0.009 |
stall | +0.009 |
flavors | +0.009 |
banks | +0.009 |
Neg logit contributions | |
weeping | -0.007 |
crying | -0.007 |
Ros | -0.007 |
bleeding | -0.007 |
ir | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
stalls | +0.005 |
stall | +0.005 |
hike | +0.004 |
fare | +0.004 |
flavors | +0.004 |
Neg logit contributions | |
ir | -0.004 |
Ros | -0.004 |
apped | -0.004 |
el | -0.004 |
ucky | -0.004 |
Token | experience |
Token ID | 1998 |
Feature activation | -7.13e-03 |
Pos logit contributions | |
crying | +0.002 |
weeping | +0.002 |
bleeding | +0.002 |
streaming | +0.002 |
Ros | +0.002 |
Neg logit contributions | |
stalls | -0.003 |
stall | -0.002 |
banks | -0.002 |
fare | -0.002 |
flavors | -0.002 |
Token | outside |
Token ID | 2354 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
stalls | +0.015 |
banks | +0.015 |
stall | +0.015 |
fare | +0.014 |
hike | +0.014 |
Neg logit contributions | |
crying | -0.008 |
weeping | -0.008 |
bleeding | -0.008 |
streaming | -0.007 |
microphone | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
weeping | +0.005 |
crying | +0.005 |
bleeding | +0.004 |
streaming | +0.004 |
ir | +0.004 |
Neg logit contributions | |
stalls | -0.006 |
stall | -0.006 |
hike | -0.006 |
banks | -0.006 |
flavors | -0.006 |
Token | shooting |
Token ID | 4395 |
Feature activation | -9.58e-03 |
Pos logit contributions | |
weeping | +0.041 |
crying | +0.041 |
bleeding | +0.040 |
Ros | +0.039 |
ir | +0.039 |
Neg logit contributions | |
stalls | -0.058 |
stall | -0.055 |
hike | -0.055 |
banks | -0.054 |
flavors | -0.054 |
Token | his |
Token ID | 465 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
stalls | +0.018 |
stall | +0.017 |
hike | +0.017 |
banks | +0.017 |
flavors | +0.017 |
Neg logit contributions | |
weeping | -0.013 |
crying | -0.013 |
bleeding | -0.012 |
Ros | -0.012 |
ir | -0.012 |
Token | arrow |
Token ID | 15452 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
weeping | +0.028 |
Ros | +0.027 |
ir | +0.027 |
crying | +0.027 |
bleeding | +0.027 |
Neg logit contributions | |
stalls | -0.029 |
hike | -0.027 |
stall | -0.027 |
banks | -0.027 |
flavors | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
weeping | +0.065 |
crying | +0.065 |
bleeding | +0.063 |
streaming | +0.061 |
Ros | +0.059 |
Neg logit contributions | |
stalls | -0.091 |
flavors | -0.087 |
stall | -0.085 |
fare | -0.084 |
hike | -0.084 |
Token | He |
Token ID | 679 |
Feature activation | +7.36e-03 |
Pos logit contributions | |
weeping | +0.029 |
crying | +0.028 |
Ros | +0.028 |
bleeding | +0.028 |
apped | +0.027 |
Neg logit contributions | |
stalls | -0.040 |
hike | -0.037 |
stall | -0.037 |
banks | -0.037 |
flavors | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
weeping | +0.011 |
crying | +0.011 |
bleeding | +0.011 |
Ros | +0.011 |
apped | +0.010 |
Neg logit contributions | |
stalls | -0.013 |
stall | -0.012 |
fare | -0.012 |
banks | -0.012 |
hike | -0.012 |
Token | excited |
Token ID | 6568 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
weeping | +0.028 |
Ros | +0.027 |
crying | +0.027 |
bleeding | +0.027 |
ir | +0.026 |
Neg logit contributions | |
stalls | -0.040 |
stall | -0.037 |
hike | -0.037 |
banks | -0.037 |
flavors | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
crying | +0.004 |
weeping | +0.004 |
bleeding | +0.004 |
streaming | +0.004 |
el | +0.004 |
Neg logit contributions | |
stalls | -0.007 |
stall | -0.007 |
banks | -0.007 |
fare | -0.007 |
flavors | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
crying | +0.017 |
weeping | +0.016 |
Emily | +0.015 |
el | +0.015 |
ir | +0.015 |
Neg logit contributions | |
flavors | -0.025 |
stalls | -0.025 |
fare | -0.025 |
hike | -0.025 |
banks | -0.024 |
Token | One |
Token ID | 1881 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
weeping | +0.015 |
Ros | +0.015 |
crying | +0.015 |
Ros | +0.014 |
Emily | +0.014 |
Neg logit contributions | |
stalls | -0.021 |
flavors | -0.020 |
hike | -0.020 |
fare | -0.020 |
banks | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
stalls | +0.064 |
banks | +0.059 |
stall | +0.059 |
flavors | +0.059 |
hike | +0.058 |
Neg logit contributions | |
weeping | -0.063 |
crying | -0.062 |
bleeding | -0.061 |
Ros | -0.061 |
ir | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
weeping | +0.017 |
Ros | +0.017 |
crying | +0.017 |
bleeding | +0.016 |
ir | +0.016 |
Neg logit contributions | |
stalls | -0.016 |
hike | -0.015 |
stall | -0.015 |
flavors | -0.015 |
banks | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -3.67e-03 |
Pos logit contributions | |
weeping | +0.005 |
ir | +0.005 |
Ros | +0.005 |
bleeding | +0.005 |
streaming | +0.005 |
Neg logit contributions | |
stalls | -0.004 |
stall | -0.004 |
hike | -0.004 |
flavors | -0.004 |
banks | -0.004 |
Token | bird |
Token ID | 6512 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
stalls | +0.006 |
stall | +0.006 |
hike | +0.006 |
flavors | +0.006 |
fare | +0.006 |
Neg logit contributions | |
streaming | -0.006 |
ir | -0.006 |
weeping | -0.006 |
Ros | -0.006 |
bleeding | -0.006 |
Token | came |
Token ID | 1625 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
weeping | +0.077 |
crying | +0.075 |
Ros | +0.075 |
bleeding | +0.075 |
ir | +0.074 |
Neg logit contributions | |
stalls | -0.076 |
stall | -0.071 |
hike | -0.071 |
banks | -0.069 |
flavors | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
Ros | +0.059 |
bleeding | +0.059 |
ir | +0.059 |
blood | +0.058 |
itt | +0.058 |
Neg logit contributions | |
stalls | -0.037 |
hike | -0.036 |
stall | -0.035 |
banks | -0.034 |
bank | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -7.49e-03 |
Pos logit contributions | |
stalls | +0.004 |
hike | +0.004 |
stall | +0.004 |
flavors | +0.004 |
banks | +0.004 |
Neg logit contributions | |
weeping | -0.003 |
bleeding | -0.003 |
Ros | -0.003 |
crying | -0.003 |
apped | -0.003 |
Token | palace |
Token ID | 20562 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
stalls | +0.011 |
hike | +0.011 |
stall | +0.011 |
flavors | +0.011 |
banks | +0.010 |
Neg logit contributions | |
weeping | -0.013 |
crying | -0.013 |
Ros | -0.013 |
bleeding | -0.013 |
ir | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +3.83e-03 |
Pos logit contributions | |
stalls | +0.042 |
flavors | +0.042 |
hike | +0.040 |
fare | +0.040 |
nic | +0.040 |
Neg logit contributions | |
crying | -0.026 |
weeping | -0.026 |
apped | -0.024 |
bleeding | -0.024 |
ir | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
crying | +0.040 |
weeping | +0.040 |
Ros | +0.038 |
bleeding | +0.038 |
apped | +0.038 |
Neg logit contributions | |
stalls | -0.057 |
fare | -0.053 |
hike | -0.053 |
stall | -0.053 |
banks | -0.052 |
Token | so |
Token ID | 523 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
Ros | +0.033 |
ir | +0.032 |
weeping | +0.032 |
bleeding | +0.031 |
crying | +0.031 |
Neg logit contributions | |
stalls | -0.039 |
stall | -0.037 |
hike | -0.036 |
banks | -0.035 |
flavors | -0.035 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
stalls | +0.020 |
stall | +0.019 |
flavors | +0.018 |
list | +0.018 |
fare | +0.017 |
Neg logit contributions | |
Ros | -0.024 |
ir | -0.024 |
blood | -0.023 |
el | -0.023 |
bleeding | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
weeping | +0.059 |
crying | +0.059 |
bleeding | +0.056 |
Ros | +0.055 |
ir | +0.054 |
Neg logit contributions | |
stalls | -0.082 |
stall | -0.077 |
hike | -0.077 |
banks | -0.077 |
fare | -0.076 |
Token | have |
Token ID | 423 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
bleeding | +0.058 |
weeping | +0.057 |
Ros | +0.056 |
apped | +0.056 |
streaming | +0.056 |
Neg logit contributions | |
hike | -0.048 |
stalls | -0.047 |
stall | -0.046 |
banks | -0.046 |
fare | -0.046 |
Token | returned |
Token ID | 4504 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
weeping | +0.064 |
crying | +0.063 |
Ros | +0.062 |
bleeding | +0.061 |
ir | +0.060 |
Neg logit contributions | |
stalls | -0.091 |
stall | -0.087 |
hike | -0.087 |
banks | -0.086 |
fare | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
crying | +0.057 |
weeping | +0.057 |
bleeding | +0.054 |
Ros | +0.053 |
Ros | +0.052 |
Neg logit contributions | |
stalls | -0.094 |
hike | -0.092 |
banks | -0.089 |
flavors | -0.089 |
stall | -0.089 |
Token | button |
Token ID | 4936 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
weeping | +0.049 |
Ros | +0.049 |
ir | +0.048 |
bleeding | +0.047 |
crying | +0.047 |
Neg logit contributions | |
stalls | -0.047 |
hike | -0.044 |
stall | -0.044 |
flavors | -0.044 |
fare | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
weeping | +0.040 |
crying | +0.039 |
bleeding | +0.038 |
Ros | +0.038 |
ir | +0.037 |
Neg logit contributions | |
stalls | -0.054 |
hike | -0.051 |
flavors | -0.051 |
stall | -0.050 |
banks | -0.050 |
Token | her |
Token ID | 607 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
weeping | +0.029 |
Ros | +0.029 |
crying | +0.029 |
bleeding | +0.028 |
ir | +0.028 |
Neg logit contributions | |
stalls | -0.031 |
hike | -0.029 |
stall | -0.029 |
flavors | -0.028 |
banks | -0.028 |
Token | dad |
Token ID | 9955 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
weeping | +0.037 |
Ros | +0.036 |
crying | +0.036 |
bleeding | +0.036 |
ir | +0.035 |
Neg logit contributions | |
stalls | -0.049 |
stall | -0.046 |
hike | -0.046 |
flavors | -0.045 |
banks | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +3.84e-03 |
Pos logit contributions | |
stalls | +0.001 |
hike | +0.001 |
banks | +0.001 |
fare | +0.001 |
stall | +0.001 |
Neg logit contributions | |
bleeding | -0.001 |
weeping | -0.001 |
crying | -0.001 |
Ros | -0.001 |
ir | -0.001 |
Token | clipboard |
Token ID | 47999 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Ros | +0.006 |
ir | +0.006 |
apped | +0.006 |
weeping | +0.006 |
crying | +0.006 |
Neg logit contributions | |
stalls | -0.006 |
stall | -0.006 |
hike | -0.006 |
banks | -0.006 |
flavors | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
stalls | +0.034 |
hike | +0.034 |
banks | +0.032 |
flavors | +0.031 |
fare | +0.031 |
Neg logit contributions | |
crying | -0.022 |
weeping | -0.021 |
bleeding | -0.020 |
el | -0.020 |
streaming | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
stalls | +0.026 |
stall | +0.024 |
hike | +0.024 |
flavors | +0.024 |
banks | +0.024 |
Neg logit contributions | |
weeping | -0.021 |
crying | -0.020 |
bleeding | -0.020 |
Ros | -0.020 |
ir | -0.020 |
Token | There |
Token ID | 1858 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
weeping | +0.003 |
crying | +0.003 |
ir | +0.002 |
bleeding | +0.002 |
apped | +0.002 |
Neg logit contributions | |
stalls | -0.004 |
stall | -0.003 |
flavors | -0.003 |
hike | -0.003 |
fare | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
crying | +0.039 |
weeping | +0.039 |
el | +0.038 |
bleeding | +0.037 |
ir | +0.037 |
Neg logit contributions | |
stalls | -0.057 |
stall | -0.054 |
hike | -0.054 |
fare | -0.053 |
banks | -0.053 |
Token | you |
Token ID | 345 |
Feature activation | +1.04e-03 |
Pos logit contributions | |
stalls | +0.005 |
hike | +0.004 |
stall | +0.004 |
flavors | +0.004 |
fare | +0.004 |
Neg logit contributions | |
weeping | -0.003 |
Ros | -0.003 |
ir | -0.003 |
crying | -0.003 |
bleeding | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
weeping | +0.002 |
Ros | +0.002 |
crying | +0.002 |
bleeding | +0.002 |
ir | +0.002 |
Neg logit contributions | |
stalls | -0.002 |
hike | -0.002 |
banks | -0.002 |
fare | -0.001 |
stall | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
weeping | +0.006 |
crying | +0.006 |
bleeding | +0.006 |
Ros | +0.006 |
ir | +0.006 |
Neg logit contributions | |
stalls | -0.009 |
hike | -0.009 |
stall | -0.009 |
banks | -0.009 |
flavors | -0.009 |
Token | fixed |
Token ID | 5969 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
Ros | +0.039 |
ir | +0.038 |
weeping | +0.038 |
apped | +0.037 |
crying | +0.037 |
Neg logit contributions | |
stalls | -0.056 |
stall | -0.053 |
flavors | -0.053 |
hike | -0.053 |
banks | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
bleeding | +0.036 |
weeping | +0.035 |
crying | +0.035 |
el | +0.035 |
ir | +0.034 |
Neg logit contributions | |
stalls | -0.048 |
hike | -0.046 |
stall | -0.046 |
fare | -0.044 |
banks | -0.044 |
Token | day |
Token ID | 1110 |
Feature activation | +7.71e-03 |
Pos logit contributions | |
stalls | +0.048 |
flavors | +0.046 |
appet | +0.044 |
nic | +0.043 |
banks | +0.043 |
Neg logit contributions | |
el | -0.056 |
crying | -0.056 |
weeping | -0.053 |
microphone | -0.052 |
bleeding | -0.052 |
Token | of |
Token ID | 286 |
Feature activation | +8.33e-05 |
Pos logit contributions | |
weeping | +0.007 |
crying | +0.007 |
Ros | +0.007 |
bleeding | +0.007 |
ir | +0.007 |
Neg logit contributions | |
stalls | -0.018 |
stall | -0.017 |
hike | -0.017 |
flavors | -0.017 |
banks | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
Ros | +0.000 |
bleeding | +0.000 |
apped | +0.000 |
ir | +0.000 |
weeping | +0.000 |
Neg logit contributions | |
hike | -0.000 |
stalls | -0.000 |
stall | -0.000 |
list | -0.000 |
flavors | -0.000 |
Token | delivery |
Token ID | 7585 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
stalls | +0.025 |
banks | +0.024 |
flavors | +0.023 |
nic | +0.022 |
belts | +0.022 |
Neg logit contributions | |
crying | -0.033 |
el | -0.032 |
weeping | -0.032 |
microphone | -0.031 |
bleeding | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +2.95e-04 |
Pos logit contributions | |
banks | +0.057 |
stalls | +0.056 |
flavors | +0.054 |
nic | +0.053 |
hike | +0.053 |
Neg logit contributions | |
crying | -0.057 |
weeping | -0.054 |
microphone | -0.053 |
el | -0.053 |
apped | -0.052 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ir | +0.000 |
weeping | +0.000 |
bleeding | +0.000 |
el | +0.000 |
crying | +0.000 |
Neg logit contributions | |
stalls | -0.001 |
hike | -0.001 |
stall | -0.001 |
banks | -0.001 |
flavors | -0.001 |
Token | waited |
Token ID | 13488 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
crying | +0.017 |
weeping | +0.016 |
Ros | +0.016 |
bleeding | +0.015 |
el | +0.015 |
Neg logit contributions | |
fare | -0.021 |
stalls | -0.021 |
flavors | -0.021 |
stall | -0.020 |
hike | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
stalls | +0.063 |
flavors | +0.061 |
stall | +0.060 |
hike | +0.060 |
fare | +0.060 |
Neg logit contributions | |
weeping | -0.045 |
crying | -0.044 |
bleeding | -0.042 |
ir | -0.041 |
streaming | -0.041 |
Token | waited |
Token ID | 13488 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
stalls | +0.029 |
stall | +0.028 |
banks | +0.027 |
hike | +0.027 |
flavors | +0.027 |
Neg logit contributions | |
weeping | -0.037 |
crying | -0.037 |
Ros | -0.036 |
bleeding | -0.036 |
ir | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
stalls | +0.067 |
flavors | +0.064 |
stall | +0.063 |
hike | +0.062 |
fare | +0.062 |
Neg logit contributions | |
weeping | -0.055 |
crying | -0.054 |
bleeding | -0.053 |
ir | -0.052 |
Ros | -0.051 |
Token | Finally |
Token ID | 9461 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
stalls | +0.017 |
stall | +0.016 |
hike | +0.016 |
banks | +0.016 |
fare | +0.015 |
Neg logit contributions | |
weeping | -0.017 |
bleeding | -0.017 |
ir | -0.017 |
crying | -0.017 |
Ros | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
weeping | +0.037 |
Ros | +0.037 |
crying | +0.036 |
bleeding | +0.035 |
ir | +0.035 |
Neg logit contributions | |
stalls | -0.070 |
stall | -0.066 |
hike | -0.066 |
flavors | -0.065 |
banks | -0.065 |
Token | determined |
Token ID | 5295 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
weeping | +0.013 |
Ros | +0.013 |
crying | +0.013 |
bleeding | +0.013 |
ir | +0.013 |
Neg logit contributions | |
stalls | -0.014 |
hike | -0.013 |
stall | -0.013 |
banks | -0.012 |
flavors | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
stalls | +0.021 |
stall | +0.020 |
flavors | +0.020 |
hike | +0.020 |
banks | +0.019 |
Neg logit contributions | |
crying | -0.010 |
weeping | -0.009 |
bleeding | -0.009 |
blood | -0.009 |
streaming | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +7.52e-03 |
Pos logit contributions | |
weeping | +0.034 |
crying | +0.034 |
bleeding | +0.032 |
Ros | +0.031 |
streaming | +0.030 |
Neg logit contributions | |
stalls | -0.050 |
stall | -0.047 |
hike | -0.046 |
flavors | -0.046 |
banks | -0.046 |
Token | be |
Token ID | 307 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
weeping | +0.012 |
crying | +0.012 |
bleeding | +0.011 |
Ros | +0.011 |
ir | +0.011 |
Neg logit contributions | |
stalls | -0.013 |
stall | -0.012 |
hike | -0.012 |
flavors | -0.012 |
banks | -0.012 |
Token | scared |
Token ID | 12008 |
Feature activation | +6.24e-03 |
Pos logit contributions | |
weeping | +0.034 |
Ros | +0.034 |
crying | +0.033 |
ir | +0.033 |
bleeding | +0.033 |
Neg logit contributions | |
stalls | -0.059 |
stall | -0.056 |
hike | -0.056 |
flavors | -0.055 |
banks | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
Ros | +0.009 |
weeping | +0.009 |
ir | +0.009 |
apped | +0.009 |
bleeding | +0.009 |
Neg logit contributions | |
stalls | -0.011 |
hike | -0.010 |
stall | -0.010 |
banks | -0.010 |
flavors | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
weeping | +0.052 |
crying | +0.051 |
bleeding | +0.050 |
Ros | +0.050 |
ir | +0.050 |
Neg logit contributions | |
stalls | -0.077 |
hike | -0.073 |
stall | -0.073 |
banks | -0.072 |
flavors | -0.071 |
Token | earthquake |
Token ID | 16295 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
Ros | +0.036 |
apped | +0.035 |
ir | +0.033 |
streaming | +0.033 |
weeping | +0.032 |
Neg logit contributions | |
stalls | -0.043 |
hike | -0.042 |
banks | -0.041 |
stall | -0.040 |
flavors | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
crying | +0.048 |
weeping | +0.047 |
bleeding | +0.045 |
streaming | +0.043 |
ir | +0.041 |
Neg logit contributions | |
stalls | -0.063 |
hike | -0.059 |
flavors | -0.059 |
stall | -0.059 |
banks | -0.058 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
weeping | +0.037 |
crying | +0.036 |
Ros | +0.036 |
bleeding | +0.035 |
ir | +0.035 |
Neg logit contributions | |
stalls | -0.053 |
hike | -0.050 |
stall | -0.050 |
flavors | -0.049 |
banks | -0.049 |
Token | Lily |
Token ID | 20037 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
stalls | +0.002 |
hike | +0.002 |
stall | +0.002 |
flavors | +0.002 |
list | +0.002 |
Neg logit contributions | |
ir | -0.002 |
weeping | -0.002 |
streaming | -0.002 |
aps | -0.002 |
ez | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
weeping | +0.010 |
crying | +0.010 |
Ros | +0.010 |
bleeding | +0.010 |
ir | +0.009 |
Neg logit contributions | |
stalls | -0.010 |
fare | -0.010 |
stall | -0.010 |
hike | -0.010 |
flavors | -0.010 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
stalls | +0.013 |
stall | +0.013 |
hike | +0.013 |
banks | +0.013 |
flavors | +0.013 |
Neg logit contributions | |
ir | -0.013 |
Ros | -0.012 |
weeping | -0.012 |
streaming | -0.011 |
bleeding | -0.011 |
Token | my |
Token ID | 1820 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
weeping | +0.038 |
Ros | +0.037 |
ir | +0.037 |
bleeding | +0.037 |
crying | +0.037 |
Neg logit contributions | |
stalls | -0.040 |
hike | -0.038 |
stall | -0.037 |
flavors | -0.037 |
banks | -0.037 |
Token | noticed |
Token ID | 6810 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
crying | +0.022 |
weeping | +0.022 |
Ros | +0.022 |
bleeding | +0.021 |
Ros | +0.020 |
Neg logit contributions | |
stalls | -0.027 |
fare | -0.026 |
stall | -0.025 |
banks | -0.025 |
flavors | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
apped | +0.008 |
ir | +0.008 |
aps | +0.008 |
weeping | +0.008 |
apping | +0.008 |
Neg logit contributions | |
stalls | -0.006 |
flavors | -0.006 |
hike | -0.005 |
experiments | -0.005 |
stall | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -4.86e-03 |
Pos logit contributions | |
ir | +0.024 |
Ros | +0.023 |
apped | +0.023 |
weeping | +0.023 |
el | +0.022 |
Neg logit contributions | |
stalls | -0.035 |
hike | -0.033 |
flavors | -0.033 |
stall | -0.033 |
banks | -0.031 |
Token | f |
Token ID | 277 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
stalls | +0.009 |
banks | +0.009 |
flavors | +0.008 |
bank | +0.008 |
stall | +0.008 |
Neg logit contributions | |
ir | -0.007 |
Ros | -0.007 |
apped | -0.007 |
weeping | -0.007 |
Emily | -0.006 |
Token | auc |
Token ID | 14272 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
stalls | +0.048 |
cases | +0.048 |
banks | +0.047 |
flavors | +0.044 |
experiments | +0.043 |
Neg logit contributions | |
weeping | -0.055 |
crying | -0.054 |
Ros | -0.054 |
bleeding | -0.053 |
Ros | -0.052 |
Token | et |
Token ID | 316 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
stalls | +0.039 |
banks | +0.035 |
flavors | +0.035 |
hike | +0.035 |
stall | +0.035 |
Neg logit contributions | |
weeping | -0.070 |
Ros | -0.069 |
crying | -0.068 |
bleeding | -0.067 |
ir | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
stalls | +0.005 |
stall | +0.005 |
hike | +0.005 |
flavors | +0.005 |
banks | +0.005 |
Neg logit contributions | |
weeping | -0.005 |
crying | -0.005 |
bleeding | -0.005 |
Ros | -0.005 |
ir | -0.005 |
Token | big |
Token ID | 1263 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ir | +0.034 |
apped | +0.033 |
ez | +0.032 |
umbled | +0.032 |
streaming | +0.032 |
Neg logit contributions | |
stall | -0.028 |
list | -0.027 |
stalls | -0.026 |
hike | -0.026 |
ticket | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +2.69e-03 |
Pos logit contributions | |
Ros | +0.033 |
ir | +0.032 |
weeping | +0.032 |
bleeding | +0.032 |
apped | +0.031 |
Neg logit contributions | |
stalls | -0.033 |
stall | -0.032 |
hike | -0.032 |
flavors | -0.031 |
banks | -0.031 |
Token | brown |
Token ID | 7586 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
ir | +0.004 |
apped | +0.004 |
weeping | +0.004 |
Ros | +0.004 |
crying | +0.004 |
Neg logit contributions | |
stalls | -0.004 |
stall | -0.004 |
hike | -0.004 |
flavors | -0.004 |
fare | -0.004 |
Token | t |
Token ID | 256 |
Feature activation | +9.16e-03 |
Pos logit contributions | |
Ros | +0.011 |
ir | +0.011 |
streaming | +0.011 |
weeping | +0.011 |
apped | +0.011 |
Neg logit contributions | |
stalls | -0.012 |
stall | -0.012 |
hike | -0.012 |
bank | -0.011 |
banks | -0.011 |
Token | eddy |
Token ID | 21874 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
weeping | +0.009 |
Emily | +0.009 |
streaming | +0.009 |
bleeding | +0.009 |
crying | +0.009 |
Neg logit contributions | |
stall | -0.020 |
stalls | -0.020 |
belts | -0.019 |
flavors | -0.019 |
cases | -0.019 |
Token | bear |
Token ID | 6842 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ir | +0.111 |
apped | +0.105 |
apping | +0.104 |
Ros | +0.104 |
streaming | +0.103 |
Neg logit contributions | |
stall | -0.081 |
stalls | -0.080 |
bank | -0.079 |
flavors | -0.078 |
belts | -0.076 |
Token | that |
Token ID | 326 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
weeping | +0.022 |
crying | +0.022 |
bleeding | +0.021 |
Ros | +0.021 |
ir | +0.021 |
Neg logit contributions | |
stalls | -0.037 |
hike | -0.036 |
flavors | -0.035 |
stall | -0.035 |
banks | -0.035 |
Token | she |
Token ID | 673 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
weeping | +0.047 |
crying | +0.047 |
Ros | +0.045 |
bleeding | +0.045 |
Ros | +0.045 |
Neg logit contributions | |
stalls | -0.059 |
banks | -0.056 |
fare | -0.055 |
stall | -0.055 |
hike | -0.055 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
weeping | +0.029 |
crying | +0.029 |
Ros | +0.029 |
bleeding | +0.028 |
ir | +0.027 |
Neg logit contributions | |
stalls | -0.033 |
stall | -0.031 |
hike | -0.031 |
fare | -0.031 |
banks | -0.030 |
Token | very |
Token ID | 845 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
weeping | +0.037 |
crying | +0.036 |
bleeding | +0.035 |
Ros | +0.035 |
ir | +0.033 |
Neg logit contributions | |
stalls | -0.057 |
stall | -0.054 |
hike | -0.054 |
banks | -0.054 |
fare | -0.053 |
Token | much |
Token ID | 881 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
stalls | +0.092 |
stall | +0.088 |
hike | +0.087 |
flavors | +0.086 |
banks | +0.086 |
Neg logit contributions | |
weeping | -0.062 |
crying | -0.060 |
bleeding | -0.060 |
Ros | -0.059 |
ir | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -6.49e-05 |
Pos logit contributions | |
stalls | +0.011 |
hike | +0.010 |
stall | +0.010 |
banks | +0.009 |
flavors | +0.009 |
Neg logit contributions | |
Ros | -0.015 |
weeping | -0.015 |
bleeding | -0.015 |
streaming | -0.015 |
ir | -0.015 |
Token | there |
Token ID | 612 |
Feature activation | +7.06e-03 |
Pos logit contributions | |
hike | +0.000 |
stall | +0.000 |
stalls | +0.000 |
banks | +0.000 |
flavors | +0.000 |
Neg logit contributions | |
Ros | -0.000 |
streaming | -0.000 |
ir | -0.000 |
weeping | -0.000 |
microphone | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
weeping | +0.012 |
Ros | +0.012 |
crying | +0.012 |
bleeding | +0.012 |
ir | +0.011 |
Neg logit contributions | |
stalls | -0.011 |
hike | -0.010 |
stall | -0.010 |
flavors | -0.010 |
banks | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
weeping | +0.034 |
streaming | +0.033 |
ir | +0.033 |
bleeding | +0.032 |
Ros | +0.032 |
Neg logit contributions | |
stalls | -0.028 |
hike | -0.027 |
stall | -0.026 |
flavors | -0.026 |
banks | -0.024 |
Token | big |
Token ID | 1263 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
streaming | +0.019 |
ir | +0.019 |
apped | +0.019 |
el | +0.018 |
weeping | +0.018 |
Neg logit contributions | |
stall | -0.022 |
stalls | -0.022 |
hike | -0.022 |
list | -0.020 |
flavors | -0.020 |
Token | park |
Token ID | 3952 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
Ros | +0.034 |
streaming | +0.033 |
ir | +0.033 |
apped | +0.032 |
weeping | +0.032 |
Neg logit contributions | |
stalls | -0.031 |
stall | -0.030 |
hike | -0.030 |
flavors | -0.028 |
list | -0.028 |
Token | with |
Token ID | 351 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
stalls | +0.071 |
banks | +0.068 |
flavors | +0.068 |
fare | +0.068 |
hike | +0.067 |
Neg logit contributions | |
crying | -0.024 |
apped | -0.024 |
weeping | -0.023 |
Ros | -0.022 |
bleeding | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
stalls | +0.013 |
flavors | +0.012 |
stall | +0.012 |
hike | +0.012 |
banks | +0.011 |
Neg logit contributions | |
weeping | -0.010 |
crying | -0.009 |
bleeding | -0.009 |
ir | -0.009 |
Ros | -0.009 |
Token | large |
Token ID | 1588 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
weeping | +0.017 |
ir | +0.017 |
streaming | +0.017 |
bleeding | +0.017 |
Ros | +0.017 |
Neg logit contributions | |
stalls | -0.020 |
stall | -0.019 |
hike | -0.019 |
flavors | -0.019 |
banks | -0.018 |
Token | playground |
Token ID | 24817 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
weeping | +0.018 |
crying | +0.018 |
ir | +0.017 |
bleeding | +0.017 |
microphone | +0.017 |
Neg logit contributions | |
stalls | -0.016 |
fare | -0.015 |
banks | -0.015 |
cases | -0.015 |
flavors | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
hike | +0.070 |
stalls | +0.069 |
fare | +0.068 |
flavors | +0.067 |
banks | +0.066 |
Neg logit contributions | |
apped | -0.045 |
crying | -0.043 |
weeping | -0.040 |
aps | -0.039 |
bleeding | -0.039 |
Token | € |
Token ID | 26391 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
stalls | +0.111 |
stall | +0.098 |
belts | +0.095 |
flavors | +0.094 |
cases | +0.093 |
Neg logit contributions | |
ir | -0.116 |
el | -0.115 |
uck | -0.113 |
w | -0.110 |
Ros | -0.110 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | +2.70e-03 |
Pos logit contributions | |
stalls | +0.078 |
flavors | +0.073 |
stall | +0.072 |
banks | +0.072 |
hike | +0.071 |
Neg logit contributions | |
crying | -0.050 |
Ros | -0.047 |
apped | -0.047 |
weeping | -0.046 |
aps | -0.046 |
Token | t |
Token ID | 83 |
Feature activation | -1.17e-04 |
Pos logit contributions | |
crying | +0.004 |
weeping | +0.004 |
ir | +0.004 |
bleeding | +0.004 |
Ros | +0.004 |
Neg logit contributions | |
stalls | -0.005 |
hike | -0.005 |
flavors | -0.005 |
banks | -0.005 |
stall | -0.005 |
Token | speak |
Token ID | 2740 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
stalls | +0.000 |
stall | +0.000 |
flavors | +0.000 |
belts | +0.000 |
banks | +0.000 |
Neg logit contributions | |
weeping | -0.000 |
crying | -0.000 |
ir | -0.000 |
bleeding | -0.000 |
Ros | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +5.03e-03 |
Pos logit contributions | |
stalls | +0.033 |
hike | +0.032 |
stall | +0.031 |
banks | +0.030 |
flavors | +0.030 |
Neg logit contributions | |
weeping | -0.023 |
crying | -0.023 |
bleeding | -0.022 |
streaming | -0.021 |
ir | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
weeping | +0.007 |
crying | +0.007 |
Ros | +0.007 |
bleeding | +0.007 |
Ros | +0.007 |
Neg logit contributions | |
stalls | -0.009 |
hike | -0.009 |
flavors | -0.009 |
stall | -0.009 |
banks | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -6.74e-04 |
Pos logit contributions | |
stalls | +0.016 |
hike | +0.015 |
stall | +0.015 |
flavors | +0.015 |
banks | +0.015 |
Neg logit contributions | |
weeping | -0.010 |
Ros | -0.010 |
crying | -0.010 |
bleeding | -0.010 |
ir | -0.010 |
Token | But |
Token ID | 1537 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
stalls | +0.001 |
flavors | +0.001 |
hike | +0.001 |
stall | +0.001 |
fare | +0.001 |
Neg logit contributions | |
Ros | -0.001 |
ir | -0.001 |
bleeding | -0.001 |
crying | -0.001 |
weeping | -0.001 |
Token | then |
Token ID | 788 |
Feature activation | +9.80e-03 |
Pos logit contributions | |
stalls | +0.020 |
flavors | +0.018 |
stall | +0.018 |
hike | +0.018 |
fare | +0.018 |
Neg logit contributions | |
crying | -0.014 |
weeping | -0.014 |
bleeding | -0.014 |
Ros | -0.013 |
Ros | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
crying | +0.014 |
Ros | +0.014 |
weeping | +0.014 |
bleeding | +0.013 |
Ros | +0.013 |
Neg logit contributions | |
stalls | -0.018 |
stall | -0.017 |
fare | -0.017 |
banks | -0.017 |
flavors | -0.017 |
Token | baker |
Token ID | 46412 |
Feature activation | -3.85e-04 |
Pos logit contributions | |
stalls | +0.006 |
stall | +0.006 |
hike | +0.006 |
flavors | +0.006 |
fare | +0.006 |
Neg logit contributions | |
ir | -0.006 |
Ros | -0.006 |
weeping | -0.006 |
streaming | -0.006 |
apped | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
stalls | +0.031 |
flavors | +0.030 |
hike | +0.030 |
fare | +0.030 |
banks | +0.029 |
Neg logit contributions | |
crying | -0.018 |
weeping | -0.018 |
apped | -0.017 |
bleeding | -0.017 |
Ros | -0.017 |
Token | started |
Token ID | 2067 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
stalls | +0.029 |
stall | +0.027 |
hike | +0.027 |
banks | +0.027 |
flavors | +0.027 |
Neg logit contributions | |
weeping | -0.029 |
crying | -0.028 |
Ros | -0.028 |
bleeding | -0.028 |
ir | -0.028 |
Token | looking |
Token ID | 2045 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
stalls | +0.003 |
fare | +0.002 |
banks | +0.002 |
flavors | +0.002 |
stall | +0.002 |
Neg logit contributions | |
crying | -0.002 |
weeping | -0.002 |
Ros | -0.001 |
bleeding | -0.001 |
streaming | -0.001 |
Token | at |
Token ID | 379 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
stalls | +0.058 |
fare | +0.057 |
hike | +0.057 |
flavors | +0.057 |
stall | +0.056 |
Neg logit contributions | |
weeping | -0.026 |
crying | -0.026 |
apped | -0.026 |
bleeding | -0.024 |
ir | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
Ros | +0.009 |
weeping | +0.009 |
bleeding | +0.008 |
crying | +0.008 |
ir | +0.008 |
Neg logit contributions | |
stalls | -0.011 |
stall | -0.011 |
flavors | -0.011 |
hike | -0.011 |
banks | -0.011 |
Token | pictures |
Token ID | 5986 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
stalls | +0.023 |
stall | +0.021 |
hike | +0.021 |
flavors | +0.021 |
banks | +0.021 |
Neg logit contributions | |
weeping | -0.019 |
crying | -0.019 |
Ros | -0.019 |
bleeding | -0.019 |
ir | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -7.77e-03 |
Pos logit contributions | |
stalls | +0.052 |
hike | +0.051 |
banks | +0.051 |
ranc | +0.049 |
fare | +0.049 |
Neg logit contributions | |
crying | -0.036 |
weeping | -0.035 |
apped | -0.035 |
bleeding | -0.034 |
streaming | -0.034 |
Token | He |
Token ID | 679 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
stalls | +0.016 |
hike | +0.015 |
banks | +0.015 |
nic | +0.015 |
flavors | +0.015 |
Neg logit contributions | |
apped | -0.009 |
crying | -0.008 |
Emily | -0.008 |
Ros | -0.008 |
weeping | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.60e-03 |
Pos logit contributions | |
stalls | +0.024 |
fare | +0.023 |
stall | +0.022 |
hike | +0.022 |
banks | +0.022 |
Neg logit contributions | |
weeping | -0.019 |
crying | -0.019 |
Ros | -0.019 |
apped | -0.018 |
bleeding | -0.018 |
Token | animals |
Token ID | 4695 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
weeping | +0.004 |
ir | +0.004 |
Ros | +0.003 |
bleeding | +0.003 |
crying | +0.003 |
Neg logit contributions | |
stalls | -0.005 |
stall | -0.005 |
flavors | -0.005 |
hike | -0.005 |
banks | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
stalls | +0.035 |
fare | +0.035 |
flavors | +0.034 |
hike | +0.034 |
banks | +0.034 |
Neg logit contributions | |
crying | -0.024 |
weeping | -0.024 |
bleeding | -0.022 |
streaming | -0.022 |
microphone | -0.022 |
Token | not |
Token ID | 407 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
crying | +0.007 |
weeping | +0.007 |
bleeding | +0.007 |
blood | +0.007 |
Ros | +0.007 |
Neg logit contributions | |
stalls | -0.010 |
stall | -0.009 |
hike | -0.009 |
banks | -0.009 |
fare | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
stalls | +0.019 |
stall | +0.018 |
hike | +0.018 |
fare | +0.018 |
flavors | +0.018 |
Neg logit contributions | |
weeping | -0.013 |
crying | -0.013 |
bleeding | -0.013 |
Ros | -0.012 |
ir | -0.012 |
Token | turn |
Token ID | 1210 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
stalls | +0.031 |
stall | +0.028 |
hike | +0.028 |
flavors | +0.028 |
fare | +0.027 |
Neg logit contributions | |
weeping | -0.029 |
crying | -0.029 |
bleeding | -0.028 |
Ros | -0.028 |
ir | -0.028 |
Token | over |
Token ID | 625 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
stalls | +0.023 |
hike | +0.022 |
banks | +0.022 |
flavors | +0.022 |
stall | +0.022 |
Neg logit contributions | |
Ros | -0.016 |
apped | -0.016 |
weeping | -0.016 |
ir | -0.015 |
bleeding | -0.015 |
Token | any |
Token ID | 597 |
Feature activation | -3.45e-03 |
Pos logit contributions | |
weeping | +0.031 |
crying | +0.031 |
bleeding | +0.030 |
ir | +0.030 |
blood | +0.029 |
Neg logit contributions | |
stalls | -0.049 |
hike | -0.047 |
stall | -0.047 |
fare | -0.047 |
banks | -0.046 |
Token | sm |
Token ID | 895 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
stalls | +0.006 |
hike | +0.005 |
stall | +0.005 |
banks | +0.005 |
flavors | +0.005 |
Neg logit contributions | |
Ros | -0.006 |
weeping | -0.006 |
crying | -0.005 |
bleeding | -0.005 |
ir | -0.005 |
Token | elly |
Token ID | 6148 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
stalls | +0.045 |
flavors | +0.043 |
stall | +0.042 |
banks | +0.042 |
hike | +0.042 |
Neg logit contributions | |
weeping | -0.021 |
bleeding | -0.021 |
Ros | -0.021 |
crying | -0.021 |
microphone | -0.020 |
Token | worms |
Token ID | 29174 |
Feature activation | -8.73e-03 |
Pos logit contributions | |
fare | +0.027 |
stalls | +0.027 |
stall | +0.026 |
cases | +0.026 |
nic | +0.026 |
Neg logit contributions | |
weeping | -0.022 |
crying | -0.022 |
blood | -0.022 |
bleeding | -0.021 |
bug | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -6.11e-03 |
Pos logit contributions | |
stalls | +0.018 |
flavors | +0.018 |
fare | +0.017 |
stall | +0.017 |
belts | +0.017 |
Neg logit contributions | |
crying | -0.011 |
weeping | -0.011 |
bleeding | -0.010 |
ir | -0.010 |
streaming | -0.010 |
Token | then |
Token ID | 788 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
stalls | +0.010 |
stall | +0.009 |
hike | +0.009 |
fare | +0.009 |
flavors | +0.009 |
Neg logit contributions | |
weeping | -0.010 |
crying | -0.010 |
bleeding | -0.010 |
Ros | -0.010 |
blood | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
weeping | +0.042 |
crying | +0.042 |
bleeding | +0.041 |
Ros | +0.040 |
blood | +0.039 |
Neg logit contributions | |
stalls | -0.039 |
stall | -0.037 |
fare | -0.036 |
hike | -0.036 |
flavors | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
crying | +0.011 |
weeping | +0.010 |
bleeding | +0.010 |
blood | +0.010 |
apped | +0.010 |
Neg logit contributions | |
stalls | -0.019 |
hike | -0.018 |
fare | -0.018 |
banks | -0.018 |
flavors | -0.018 |
Token | Ben |
Token ID | 3932 |
Feature activation | -8.05e-04 |
Pos logit contributions | |
stalls | +0.063 |
flavors | +0.061 |
fare | +0.060 |
banks | +0.060 |
stall | +0.059 |
Neg logit contributions | |
crying | -0.018 |
weeping | -0.018 |
ir | -0.017 |
blood | -0.016 |
bleeding | -0.016 |
Token | are |
Token ID | 389 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
stalls | +0.002 |
flavors | +0.002 |
stall | +0.002 |
hike | +0.001 |
banks | +0.001 |
Neg logit contributions | |
crying | -0.001 |
weeping | -0.001 |
bleeding | -0.001 |
ir | -0.001 |
blood | -0.001 |
Token | shocked |
Token ID | 11472 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
weeping | +0.005 |
Ros | +0.005 |
crying | +0.005 |
ir | +0.005 |
bleeding | +0.005 |
Neg logit contributions | |
stalls | -0.008 |
stall | -0.008 |
hike | -0.008 |
flavors | -0.008 |
banks | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
Ros | +0.032 |
weeping | +0.032 |
ir | +0.031 |
bleeding | +0.031 |
crying | +0.030 |
Neg logit contributions | |
stalls | -0.021 |
stall | -0.019 |
flavors | -0.019 |
hike | -0.019 |
banks | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
stalls | +0.004 |
hike | +0.004 |
stall | +0.004 |
flavors | +0.004 |
banks | +0.004 |
Neg logit contributions | |
weeping | -0.003 |
crying | -0.003 |
Ros | -0.003 |
bleeding | -0.003 |
apped | -0.003 |
Token | see |
Token ID | 766 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
stalls | +0.026 |
stall | +0.024 |
flavors | +0.024 |
hike | +0.023 |
fare | +0.023 |
Neg logit contributions | |
weeping | -0.021 |
crying | -0.021 |
bleeding | -0.020 |
ir | -0.020 |
blood | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
stalls | +0.006 |
stall | +0.006 |
hike | +0.006 |
banks | +0.006 |
flavors | +0.006 |
Neg logit contributions | |
Ros | -0.005 |
ir | -0.005 |
weeping | -0.005 |
streaming | -0.004 |
bleeding | -0.004 |
Token | toys |
Token ID | 14958 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
weeping | +0.003 |
crying | +0.003 |
bleeding | +0.003 |
Ros | +0.003 |
ir | +0.003 |
Neg logit contributions | |
stalls | -0.004 |
hike | -0.004 |
stall | -0.004 |
banks | -0.004 |
flavors | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -9.72e-03 |
Pos logit contributions | |
stalls | +0.043 |
flavors | +0.041 |
hike | +0.041 |
banks | +0.041 |
nic | +0.040 |
Neg logit contributions | |
crying | -0.023 |
weeping | -0.023 |
bleeding | -0.022 |
blood | -0.021 |
microphone | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
stalls | +0.018 |
hike | +0.017 |
stall | +0.017 |
flavors | +0.017 |
banks | +0.017 |
Neg logit contributions | |
weeping | -0.013 |
crying | -0.013 |
Ros | -0.013 |
bleeding | -0.013 |
ir | -0.013 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
stalls | +0.037 |
fare | +0.037 |
banks | +0.035 |
products | +0.035 |
stall | +0.035 |
Neg logit contributions | |
crying | -0.025 |
Ros | -0.025 |
weeping | -0.025 |
apped | -0.024 |
Emily | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
weeping | +0.036 |
crying | +0.035 |
Ros | +0.035 |
bleeding | +0.035 |
ir | +0.034 |
Neg logit contributions | |
stalls | -0.051 |
hike | -0.048 |
stall | -0.048 |
banks | -0.048 |
flavors | -0.048 |
Token | whispered |
Token ID | 25029 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
stalls | +0.019 |
fare | +0.018 |
stall | +0.018 |
banks | +0.018 |
hike | +0.018 |
Neg logit contributions | |
crying | -0.017 |
weeping | -0.017 |
apped | -0.017 |
Ros | -0.016 |
bleeding | -0.016 |
Token | : |
Token ID | 25 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
stalls | +0.047 |
flavors | +0.045 |
banks | +0.045 |
hike | +0.045 |
stall | +0.044 |
Neg logit contributions | |
weeping | -0.033 |
crying | -0.033 |
bleeding | -0.031 |
apped | -0.031 |
Ros | -0.030 |
Token | � |
Token ID | 6184 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
stalls | +0.035 |
flavors | +0.033 |
banks | +0.033 |
hike | +0.032 |
fare | +0.032 |
Neg logit contributions | |
weeping | -0.039 |
crying | -0.039 |
Ros | -0.038 |
bleeding | -0.037 |
ir | -0.037 |
Token | � |
Token ID | 95 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
stalls | +0.107 |
flavors | +0.100 |
banks | +0.093 |
fare | +0.092 |
cases | +0.092 |
Neg logit contributions | |
weeping | -0.100 |
crying | -0.095 |
ir | -0.095 |
Ros | -0.092 |
Ros | -0.090 |
Token | € |
Token ID | 26391 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
stalls | +0.100 |
cases | +0.094 |
flavors | +0.092 |
belts | +0.091 |
hike | +0.091 |
Neg logit contributions | |
Ros | -0.070 |
weeping | -0.069 |
crying | -0.066 |
bleeding | -0.064 |
Emily | -0.063 |
Token | � |
Token ID | 129 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
stalls | +0.024 |
banks | +0.023 |
fare | +0.023 |
flavors | +0.023 |
stall | +0.022 |
Neg logit contributions | |
Ros | -0.020 |
crying | -0.019 |
weeping | -0.019 |
bleeding | -0.018 |
Ros | -0.018 |
Token | � |
Token ID | 241 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
stalls | +0.063 |
flavors | +0.061 |
cases | +0.057 |
fare | +0.056 |
belts | +0.055 |
Neg logit contributions | |
weeping | -0.074 |
ir | -0.073 |
crying | -0.071 |
el | -0.068 |
bleeding | -0.065 |
Token | Once |
Token ID | 7454 |
Feature activation | -4.83e-03 |
Pos logit contributions | |
stalls | +0.024 |
banks | +0.023 |
hike | +0.023 |
stall | +0.023 |
list | +0.022 |
Neg logit contributions | |
crying | -0.012 |
weeping | -0.012 |
Ros | -0.012 |
bleeding | -0.011 |
ir | -0.011 |
Token | upon |
Token ID | 2402 |
Feature activation | -8.76e-04 |
Pos logit contributions | |
stalls | +0.008 |
stall | +0.008 |
hike | +0.008 |
banks | +0.008 |
flavors | +0.008 |
Neg logit contributions | |
weeping | -0.007 |
crying | -0.007 |
Ros | -0.007 |
bleeding | -0.007 |
ir | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-03 |
Pos logit contributions | |
stalls | +0.041 |
hike | +0.039 |
stall | +0.038 |
flavors | +0.037 |
banks | +0.037 |
Neg logit contributions | |
ir | -0.039 |
Ros | -0.038 |
apped | -0.036 |
el | -0.036 |
weeping | -0.035 |
Token | window |
Token ID | 4324 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
weeping | +0.003 |
crying | +0.003 |
Ros | +0.003 |
bleeding | +0.003 |
ir | +0.003 |
Neg logit contributions | |
stalls | -0.003 |
hike | -0.003 |
stall | -0.003 |
flavors | -0.003 |
banks | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
weeping | +0.006 |
crying | +0.006 |
bleeding | +0.006 |
ir | +0.006 |
el | +0.006 |
Neg logit contributions | |
stalls | -0.007 |
hike | -0.007 |
stall | -0.007 |
flavors | -0.007 |
banks | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
stalls | +0.003 |
stall | +0.003 |
fare | +0.003 |
banks | +0.003 |
hike | +0.003 |
Neg logit contributions | |
ir | -0.003 |
weeping | -0.003 |
streaming | -0.003 |
bleeding | -0.003 |
Ros | -0.003 |
Token | tells |
Token ID | 4952 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
stalls | +0.013 |
stall | +0.013 |
hike | +0.013 |
banks | +0.012 |
fare | +0.012 |
Neg logit contributions | |
weeping | -0.013 |
crying | -0.013 |
bleeding | -0.012 |
blood | -0.012 |
Ros | -0.012 |
Token | them |
Token ID | 606 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
stalls | +0.051 |
hike | +0.049 |
stall | +0.048 |
banks | +0.048 |
flavors | +0.048 |
Neg logit contributions | |
weeping | -0.033 |
Ros | -0.033 |
bleeding | -0.032 |
crying | -0.032 |
ir | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
stalls | +0.122 |
stall | +0.121 |
fare | +0.115 |
banks | +0.115 |
hike | +0.115 |
Neg logit contributions | |
crying | -0.067 |
weeping | -0.065 |
bleeding | -0.062 |
blood | -0.061 |
microphone | -0.057 |
Token | spray |
Token ID | 11662 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
stalls | +0.068 |
hike | +0.063 |
stall | +0.063 |
banks | +0.062 |
flavors | +0.062 |
Neg logit contributions | |
weeping | -0.071 |
crying | -0.070 |
Ros | -0.070 |
bleeding | -0.069 |
ir | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | +2.75e-03 |
Pos logit contributions | |
stalls | +0.060 |
banks | +0.057 |
flavors | +0.057 |
stall | +0.056 |
hike | +0.056 |
Neg logit contributions | |
weeping | -0.053 |
Ros | -0.053 |
crying | -0.050 |
bleeding | -0.049 |
ir | -0.049 |
Token | water |
Token ID | 1660 |
Feature activation | -4.03e-03 |
Pos logit contributions | |
weeping | +0.004 |
crying | +0.004 |
bleeding | +0.004 |
Ros | +0.004 |
ir | +0.004 |
Neg logit contributions | |
stalls | -0.005 |
hike | -0.004 |
stall | -0.004 |
flavors | -0.004 |
banks | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | +2.51e-04 |
Pos logit contributions | |
stalls | +0.008 |
hike | +0.007 |
stall | +0.007 |
flavors | +0.007 |
banks | +0.007 |
Neg logit contributions | |
weeping | -0.006 |
crying | -0.005 |
bleeding | -0.005 |
Ros | -0.005 |
ir | -0.005 |
Token | mouth |
Token ID | 5422 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
weeping | +0.014 |
crying | +0.014 |
bleeding | +0.013 |
Ros | +0.013 |
ir | +0.013 |
Neg logit contributions | |
stalls | -0.024 |
hike | -0.023 |
stall | -0.023 |
flavors | -0.023 |
banks | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
stalls | +0.023 |
hike | +0.022 |
fare | +0.022 |
nic | +0.022 |
flavors | +0.021 |
Neg logit contributions | |
crying | -0.012 |
bleeding | -0.012 |
weeping | -0.012 |
streaming | -0.011 |
apped | -0.011 |
Token | |
Token ID | 220 |
Feature activation | +6.42e-04 |
Pos logit contributions | |
fare | +0.004 |
stalls | +0.004 |
hike | +0.004 |
nic | +0.004 |
belts | +0.004 |
Neg logit contributions | |
crying | -0.002 |
weeping | -0.002 |
apped | -0.002 |
ucky | -0.002 |
Emily | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -5.57e-03 |
Pos logit contributions | |
weeping | +0.001 |
crying | +0.001 |
Ros | +0.001 |
bleeding | +0.001 |
apped | +0.001 |
Neg logit contributions | |
stalls | -0.001 |
hike | -0.001 |
stall | -0.001 |
flavors | -0.001 |
banks | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -6.97e-03 |
Pos logit contributions | |
stalls | +0.013 |
banks | +0.013 |
flavors | +0.013 |
hike | +0.013 |
fare | +0.013 |
Neg logit contributions | |
Ros | -0.005 |
crying | -0.004 |
apped | -0.004 |
weeping | -0.004 |
aps | -0.004 |
Token | One |
Token ID | 3198 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
fare | +0.013 |
banks | +0.013 |
experiments | +0.013 |
bank | +0.013 |
hike | +0.013 |
Neg logit contributions | |
apping | -0.008 |
Ros | -0.008 |
ucky | -0.007 |
apped | -0.007 |
crying | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | -5.24e-03 |
Pos logit contributions | |
stalls | +0.088 |
banks | +0.082 |
stall | +0.081 |
fare | +0.081 |
flavors | +0.081 |
Neg logit contributions | |
weeping | -0.081 |
crying | -0.080 |
bleeding | -0.079 |
ir | -0.077 |
Ros | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
fare | +0.011 |
banks | +0.011 |
stalls | +0.011 |
hike | +0.010 |
stall | +0.010 |
Neg logit contributions | |
crying | -0.006 |
apped | -0.006 |
bleeding | -0.005 |
weeping | -0.005 |
streaming | -0.005 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
stalls | +0.030 |
fare | +0.029 |
banks | +0.029 |
hike | +0.028 |
stall | +0.028 |
Neg logit contributions | |
crying | -0.017 |
bleeding | -0.017 |
weeping | -0.017 |
apped | -0.016 |
streaming | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
stalls | +0.005 |
fare | +0.005 |
flavors | +0.005 |
stall | +0.005 |
hike | +0.005 |
Neg logit contributions | |
crying | -0.005 |
weeping | -0.004 |
bleeding | -0.004 |
Ros | -0.004 |
apped | -0.004 |
Token | alone |
Token ID | 3436 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
Ros | +0.023 |
ir | +0.023 |
el | +0.022 |
weeping | +0.021 |
bleeding | +0.021 |
Neg logit contributions | |
stalls | -0.037 |
stall | -0.035 |
hike | -0.035 |
banks | -0.034 |
bank | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
stalls | +0.059 |
flavors | +0.056 |
stall | +0.056 |
hike | +0.056 |
banks | +0.055 |
Neg logit contributions | |
weeping | -0.036 |
crying | -0.035 |
bleeding | -0.035 |
Ros | -0.034 |
ir | -0.034 |
Token | whip |
Token ID | 22972 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
stalls | +0.019 |
stall | +0.018 |
hike | +0.018 |
flavors | +0.017 |
banks | +0.017 |
Neg logit contributions | |
weeping | -0.015 |
Ros | -0.014 |
crying | -0.014 |
ir | -0.014 |
bleeding | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
stalls | +0.050 |
flavors | +0.048 |
hike | +0.047 |
banks | +0.046 |
stall | +0.045 |
Neg logit contributions | |
crying | -0.039 |
weeping | -0.039 |
bleeding | -0.038 |
microphone | -0.036 |
streaming | -0.036 |
Token | It |
Token ID | 632 |
Feature activation | +1.84e-03 |
Pos logit contributions | |
stalls | +0.007 |
stall | +0.006 |
hike | +0.006 |
flavors | +0.006 |
banks | +0.006 |
Neg logit contributions | |
weeping | -0.003 |
crying | -0.003 |
bleeding | -0.003 |
Ros | -0.003 |
ir | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
bleeding | +0.003 |
weeping | +0.003 |
crying | +0.003 |
Ros | +0.003 |
streaming | +0.002 |
Neg logit contributions | |
stalls | -0.003 |
stall | -0.003 |
fare | -0.003 |
hike | -0.003 |
banks | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
stalls | +0.015 |
hike | +0.014 |
banks | +0.014 |
stall | +0.014 |
fare | +0.014 |
Neg logit contributions | |
weeping | -0.008 |
bleeding | -0.008 |
crying | -0.008 |
Ros | -0.008 |
streaming | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
stalls | +0.101 |
fare | +0.096 |
banks | +0.095 |
hike | +0.095 |
stall | +0.093 |
Neg logit contributions | |
weeping | -0.068 |
crying | -0.067 |
bleeding | -0.067 |
ir | -0.064 |
Ros | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
stalls | +0.042 |
fare | +0.041 |
hike | +0.040 |
flavors | +0.040 |
stall | +0.040 |
Neg logit contributions | |
crying | -0.020 |
weeping | -0.019 |
bleeding | -0.018 |
streaming | -0.017 |
blood | -0.016 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
stalls | +0.026 |
hike | +0.025 |
banks | +0.025 |
stall | +0.025 |
fare | +0.025 |
Neg logit contributions | |
bleeding | -0.019 |
weeping | -0.019 |
crying | -0.019 |
Ros | -0.018 |
streaming | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-03 |
Pos logit contributions | |
stalls | +0.040 |
hike | +0.040 |
fare | +0.038 |
stall | +0.038 |
banks | +0.037 |
Neg logit contributions | |
bleeding | -0.029 |
weeping | -0.029 |
crying | -0.029 |
streaming | -0.028 |
el | -0.028 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
weeping | +0.002 |
ir | +0.002 |
bleeding | +0.002 |
crying | +0.002 |
Ros | +0.002 |
Neg logit contributions | |
stalls | -0.003 |
hike | -0.003 |
stall | -0.003 |
flavors | -0.003 |
banks | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
stalls | +0.023 |
stall | +0.022 |
hike | +0.022 |
flavors | +0.021 |
fare | +0.021 |
Neg logit contributions | |
ir | -0.016 |
weeping | -0.016 |
Ros | -0.016 |
bleeding | -0.015 |
crying | -0.015 |
Token | took |
Token ID | 1718 |
Feature activation | +7.28e-03 |
Pos logit contributions | |
crying | +0.029 |
weeping | +0.029 |
Ros | +0.028 |
bleeding | +0.028 |
el | +0.026 |
Neg logit contributions | |
stalls | -0.037 |
banks | -0.035 |
stall | -0.035 |
fare | -0.035 |
hike | -0.035 |
Token | him |
Token ID | 683 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
weeping | +0.012 |
Ros | +0.011 |
bleeding | +0.011 |
ir | +0.011 |
apped | +0.011 |
Neg logit contributions | |
stalls | -0.012 |
hike | -0.012 |
goods | -0.011 |
stall | -0.011 |
banks | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
stalls | +0.036 |
stall | +0.034 |
hike | +0.034 |
flavors | +0.034 |
banks | +0.034 |
Neg logit contributions | |
weeping | -0.027 |
crying | -0.026 |
Ros | -0.026 |
bleeding | -0.026 |
ir | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
stalls | +0.070 |
banks | +0.066 |
stall | +0.066 |
flavors | +0.066 |
fare | +0.065 |
Neg logit contributions | |
crying | -0.036 |
weeping | -0.036 |
bleeding | -0.034 |
Ros | -0.034 |
blood | -0.033 |
Token | library |
Token ID | 5888 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
stalls | +0.035 |
banks | +0.033 |
flavors | +0.032 |
hike | +0.031 |
fare | +0.031 |
Neg logit contributions | |
weeping | -0.059 |
crying | -0.059 |
Ros | -0.058 |
bleeding | -0.058 |
microphone | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
flavors | +0.157 |
banks | +0.151 |
stalls | +0.148 |
hike | +0.146 |
flavours | +0.143 |
Neg logit contributions | |
crying | -0.067 |
apped | -0.061 |
together | -0.059 |
apping | -0.058 |
aps | -0.055 |
Token | pick |
Token ID | 2298 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
stalls | +0.045 |
banks | +0.043 |
flavors | +0.042 |
cases | +0.042 |
belts | +0.041 |
Neg logit contributions | |
crying | -0.040 |
weeping | -0.039 |
Ros | -0.039 |
Ros | -0.038 |
bleeding | -0.037 |
Token | out |
Token ID | 503 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
stalls | +0.046 |
hike | +0.045 |
banks | +0.044 |
stall | +0.044 |
fare | +0.043 |
Neg logit contributions | |
weeping | -0.023 |
crying | -0.023 |
bleeding | -0.022 |
Ros | -0.022 |
el | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
stalls | +0.069 |
hike | +0.069 |
banks | +0.068 |
stall | +0.067 |
fare | +0.066 |
Neg logit contributions | |
weeping | -0.033 |
crying | -0.033 |
bleeding | -0.032 |
blood | -0.032 |
el | -0.032 |
Token | new |
Token ID | 649 |
Feature activation | +5.23e-04 |
Pos logit contributions | |
stalls | +0.016 |
banks | +0.016 |
hike | +0.015 |
flavors | +0.015 |
fare | +0.015 |
Neg logit contributions | |
weeping | -0.012 |
crying | -0.012 |
bleeding | -0.011 |
Ros | -0.011 |
microphone | -0.011 |