Token |
|
Token ID | 198 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
istered | +0.034 |
ls | +0.031 |
ve | +0.030 |
iqu | +0.027 |
apy | +0.027 |
Neg logit contributions | |
afternoon | -0.025 |
weekend | -0.025 |
day | -0.025 |
p | -0.024 |
morning | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
istered | +0.004 |
ls | +0.004 |
ve | +0.004 |
iqu | +0.004 |
ashamed | +0.003 |
Neg logit contributions | |
afternoon | -0.004 |
p | -0.004 |
day | -0.004 |
weekend | -0.004 |
morning | -0.003 |
Token | Mom |
Token ID | 29252 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
istered | +0.020 |
ls | +0.019 |
ve | +0.018 |
apy | +0.017 |
ashamed | +0.017 |
Neg logit contributions | |
weekend | -0.019 |
afternoon | -0.019 |
et | -0.018 |
p | -0.018 |
day | -0.018 |
Token | heard |
Token ID | 2982 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
istered | +0.008 |
ls | +0.007 |
apy | +0.007 |
ve | +0.007 |
iqu | +0.006 |
Neg logit contributions | |
et | -0.008 |
p | -0.008 |
afternoon | -0.008 |
ah | -0.008 |
weekend | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
istered | +0.018 |
ve | +0.016 |
ls | +0.016 |
uddle | +0.015 |
iqu | +0.015 |
Neg logit contributions | |
p | -0.012 |
afternoon | -0.012 |
weekend | -0.012 |
et | -0.012 |
day | -0.012 |
Token | comm |
Token ID | 725 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
istered | +0.010 |
ls | +0.009 |
apy | +0.009 |
iqu | +0.008 |
ve | +0.008 |
Neg logit contributions | |
day | -0.006 |
afternoon | -0.006 |
p | -0.006 |
weekend | -0.006 |
man | -0.006 |
Token | otion |
Token ID | 9650 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
istered | +0.129 |
ls | +0.103 |
uddle | +0.101 |
iqu | +0.100 |
ashamed | +0.094 |
Neg logit contributions | |
p | -0.159 |
weekend | -0.158 |
et | -0.156 |
afternoon | -0.155 |
day | -0.154 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
weekend | +0.009 |
afternoon | +0.009 |
et | +0.008 |
p | +0.008 |
day | +0.008 |
Neg logit contributions | |
istered | -0.010 |
ls | -0.010 |
ve | -0.009 |
apy | -0.009 |
ashamed | -0.009 |
Token | came |
Token ID | 1625 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
istered | +0.038 |
ls | +0.033 |
uddle | +0.032 |
ve | +0.032 |
apy | +0.031 |
Neg logit contributions | |
p | -0.023 |
et | -0.022 |
afternoon | -0.021 |
day | -0.021 |
weekend | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
istered | +0.050 |
ls | +0.047 |
apy | +0.044 |
ve | +0.043 |
ashamed | +0.042 |
Neg logit contributions | |
p | -0.027 |
weekend | -0.027 |
afternoon | -0.027 |
day | -0.026 |
et | -0.025 |
Token | see |
Token ID | 766 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
istered | +0.078 |
ls | +0.075 |
uddle | +0.068 |
ve | +0.067 |
apy | +0.067 |
Neg logit contributions | |
weekend | -0.054 |
afternoon | -0.053 |
day | -0.052 |
p | -0.052 |
et | -0.051 |
Token | me |
Token ID | 502 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
afternoon | +0.004 |
weekend | +0.004 |
et | +0.004 |
ah | +0.004 |
p | +0.004 |
Neg logit contributions | |
ls | -0.004 |
istered | -0.004 |
ve | -0.004 |
ashamed | -0.004 |
guilty | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
istered | +0.006 |
ls | +0.006 |
ve | +0.005 |
ashamed | +0.005 |
guilty | +0.005 |
Neg logit contributions | |
afternoon | -0.006 |
weekend | -0.006 |
et | -0.006 |
ah | -0.006 |
p | -0.005 |
Token | do |
Token ID | 466 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
istered | +0.016 |
ls | +0.016 |
ve | +0.014 |
apy | +0.013 |
ashamed | +0.013 |
Neg logit contributions | |
afternoon | -0.018 |
weekend | -0.018 |
et | -0.017 |
p | -0.017 |
day | -0.017 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
afternoon | +0.016 |
et | +0.016 |
weekend | +0.016 |
ah | +0.016 |
p | +0.015 |
Neg logit contributions | |
ls | -0.011 |
istered | -0.011 |
ve | -0.010 |
ashamed | -0.009 |
guilty | -0.009 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
istered | +0.088 |
ls | +0.078 |
ve | +0.074 |
iqu | +0.072 |
uddle | +0.072 |
Neg logit contributions | |
afternoon | -0.071 |
p | -0.071 |
weekend | -0.070 |
day | -0.070 |
morning | -0.067 |
Token | Fl |
Token ID | 1610 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
istered | +0.059 |
ls | +0.056 |
ve | +0.052 |
apy | +0.050 |
iqu | +0.049 |
Neg logit contributions | |
weekend | -0.046 |
afternoon | -0.046 |
p | -0.044 |
et | -0.044 |
day | -0.044 |
Token | uffy |
Token ID | 15352 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
guilty | +0.099 |
ls | +0.098 |
ashamed | +0.097 |
istered | +0.096 |
nam | +0.096 |
Neg logit contributions | |
ah | -0.165 |
p | -0.163 |
iny | -0.159 |
man | -0.157 |
age | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
istered | +0.035 |
ls | +0.034 |
ve | +0.030 |
apy | +0.030 |
uddle | +0.029 |
Neg logit contributions | |
p | -0.046 |
et | -0.045 |
afternoon | -0.045 |
weekend | -0.045 |
day | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
istered | +0.012 |
ls | +0.011 |
ve | +0.010 |
iqu | +0.009 |
uddle | +0.009 |
Neg logit contributions | |
weekend | -0.011 |
p | -0.011 |
afternoon | -0.011 |
day | -0.011 |
et | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
istered | +0.006 |
ls | +0.005 |
ve | +0.005 |
ashamed | +0.005 |
apy | +0.005 |
Neg logit contributions | |
weekend | -0.006 |
afternoon | -0.006 |
p | -0.006 |
day | -0.006 |
et | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
istered | +0.022 |
ls | +0.021 |
ve | +0.020 |
apy | +0.019 |
uddle | +0.018 |
Neg logit contributions | |
weekend | -0.024 |
afternoon | -0.023 |
et | -0.023 |
day | -0.022 |
ah | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
weekend | +0.005 |
day | +0.005 |
afternoon | +0.005 |
morning | +0.005 |
Wednesday | +0.005 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.009 |
ve | -0.009 |
iqu | -0.008 |
vell | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
day | +0.001 |
weekend | +0.001 |
afternoon | +0.001 |
p | +0.001 |
morning | +0.001 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
vell | -0.002 |
sters | -0.002 |
iqu | -0.002 |
Token | Mom |
Token ID | 29252 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
istered | +0.014 |
ls | +0.013 |
iqu | +0.012 |
ve | +0.012 |
ashamed | +0.012 |
Neg logit contributions | |
afternoon | -0.009 |
weekend | -0.009 |
day | -0.009 |
p | -0.008 |
et | -0.008 |
Token | heard |
Token ID | 2982 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
et | +0.001 |
p | +0.001 |
afternoon | +0.001 |
weekend | +0.001 |
ah | +0.001 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.001 |
apy | -0.001 |
ve | -0.001 |
iqu | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
istered | +0.023 |
ve | +0.021 |
ls | +0.020 |
iqu | +0.020 |
vell | +0.019 |
Neg logit contributions | |
afternoon | -0.012 |
weekend | -0.012 |
day | -0.012 |
p | -0.011 |
morning | -0.011 |
Token | comm |
Token ID | 725 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
istered | +0.001 |
ls | +0.001 |
apy | +0.001 |
iqu | +0.001 |
uffed | +0.001 |
Neg logit contributions | |
day | -0.001 |
weekend | -0.001 |
afternoon | -0.001 |
p | -0.001 |
morning | -0.001 |
Token | otion |
Token ID | 9650 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
istered | +0.142 |
iqu | +0.121 |
uddle | +0.113 |
ls | +0.109 |
ashamed | +0.102 |
Neg logit contributions | |
weekend | -0.142 |
day | -0.138 |
afternoon | -0.137 |
p | -0.137 |
et | -0.131 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
p | +0.011 |
et | +0.011 |
ah | +0.011 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.013 |
ve | -0.011 |
ashamed | -0.011 |
apy | -0.011 |
Token | came |
Token ID | 1625 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
istered | +0.041 |
ls | +0.036 |
ve | +0.035 |
uddle | +0.034 |
apy | +0.034 |
Neg logit contributions | |
p | -0.024 |
et | -0.023 |
weekend | -0.023 |
afternoon | -0.023 |
day | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
istered | +0.055 |
ls | +0.051 |
apy | +0.048 |
ve | +0.047 |
ashamed | +0.046 |
Neg logit contributions | |
weekend | -0.027 |
p | -0.027 |
afternoon | -0.027 |
day | -0.026 |
et | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
istered | +0.080 |
ls | +0.077 |
ve | +0.070 |
apy | +0.069 |
uddle | +0.069 |
Neg logit contributions | |
weekend | -0.055 |
afternoon | -0.053 |
day | -0.052 |
p | -0.051 |
et | -0.049 |
Token | dance |
Token ID | 9280 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
weekend | +0.016 |
afternoon | +0.016 |
et | +0.016 |
ah | +0.015 |
day | +0.015 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.013 |
ve | -0.012 |
apy | -0.012 |
ashamed | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
weekend | +0.016 |
afternoon | +0.016 |
et | +0.016 |
p | +0.015 |
ah | +0.015 |
Neg logit contributions | |
ls | -0.013 |
istered | -0.012 |
ve | -0.011 |
uddle | -0.011 |
dizz | -0.010 |
Token | me |
Token ID | 502 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
et | +0.003 |
p | +0.003 |
day | +0.003 |
Neg logit contributions | |
istered | -0.005 |
ls | -0.005 |
ve | -0.005 |
apy | -0.005 |
ashamed | -0.004 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ls | +0.023 |
istered | +0.020 |
ve | +0.019 |
uddle | +0.018 |
ashamed | +0.017 |
Neg logit contributions | |
afternoon | -0.038 |
weekend | -0.038 |
et | -0.037 |
p | -0.035 |
day | -0.035 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
istered | +0.092 |
ls | +0.080 |
ve | +0.077 |
iqu | +0.073 |
uddle | +0.073 |
Neg logit contributions | |
p | -0.083 |
weekend | -0.082 |
afternoon | -0.082 |
day | -0.081 |
morning | -0.078 |
Token | Fl |
Token ID | 1610 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
istered | +0.061 |
ls | +0.056 |
ve | +0.052 |
apy | +0.049 |
uddle | +0.049 |
Neg logit contributions | |
weekend | -0.061 |
afternoon | -0.061 |
p | -0.061 |
day | -0.059 |
et | -0.058 |
Token | utter |
Token ID | 10381 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
istered | +0.115 |
guilty | +0.112 |
ashamed | +0.111 |
nam | +0.103 |
ls | +0.102 |
Neg logit contributions | |
ah | -0.153 |
p | -0.149 |
afternoon | -0.137 |
et | -0.136 |
day | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
weekend | +0.022 |
afternoon | +0.022 |
et | +0.020 |
day | +0.020 |
morning | +0.019 |
Neg logit contributions | |
ls | -0.013 |
istered | -0.011 |
ashamed | -0.010 |
ve | -0.010 |
apy | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
istered | +0.029 |
ls | +0.026 |
ve | +0.024 |
iqu | +0.023 |
uddle | +0.023 |
Neg logit contributions | |
p | -0.027 |
weekend | -0.027 |
afternoon | -0.026 |
day | -0.026 |
ah | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
istered | +0.019 |
ls | +0.018 |
ve | +0.016 |
ashamed | +0.016 |
apy | +0.015 |
Neg logit contributions | |
weekend | -0.021 |
afternoon | -0.021 |
p | -0.021 |
day | -0.020 |
et | -0.020 |
Token | " |
Token ID | 1 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
istered | +0.028 |
ls | +0.027 |
ve | +0.025 |
apy | +0.024 |
ashamed | +0.022 |
Neg logit contributions | |
weekend | -0.032 |
afternoon | -0.032 |
et | -0.031 |
day | -0.030 |
p | -0.030 |
Token | my |
Token ID | 1820 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.009 |
p | +0.008 |
day | +0.008 |
hour | +0.008 |
Neg logit contributions | |
istered | -0.014 |
ls | -0.014 |
ashamed | -0.013 |
ve | -0.013 |
s | -0.013 |
Token | 's |
Token ID | 338 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
weekend | +0.007 |
afternoon | +0.007 |
et | +0.007 |
p | +0.006 |
day | +0.006 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.006 |
ve | -0.006 |
apy | -0.006 |
iqu | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
istered | +0.002 |
ls | +0.001 |
ve | +0.001 |
iqu | +0.001 |
oled | +0.001 |
Neg logit contributions | |
day | -0.002 |
afternoon | -0.002 |
weekend | -0.002 |
morning | -0.002 |
et | -0.002 |
Token | heard |
Token ID | 2982 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
istered | +0.005 |
ls | +0.004 |
apy | +0.004 |
ve | +0.004 |
uddle | +0.004 |
Neg logit contributions | |
et | -0.004 |
afternoon | -0.003 |
p | -0.003 |
weekend | -0.003 |
day | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
istered | +0.017 |
ls | +0.016 |
ve | +0.015 |
apy | +0.014 |
ashamed | +0.014 |
Neg logit contributions | |
weekend | -0.018 |
afternoon | -0.018 |
et | -0.017 |
p | -0.017 |
day | -0.017 |
Token | comm |
Token ID | 725 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
istered | +0.016 |
ls | +0.015 |
apy | +0.014 |
ve | +0.013 |
uffed | +0.013 |
Neg logit contributions | |
day | -0.013 |
afternoon | -0.013 |
weekend | -0.013 |
p | -0.012 |
morning | -0.012 |
Token | otion |
Token ID | 9650 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
istered | +0.116 |
ls | +0.101 |
uddle | +0.093 |
iqu | +0.092 |
ashamed | +0.085 |
Neg logit contributions | |
weekend | -0.155 |
afternoon | -0.151 |
day | -0.150 |
p | -0.150 |
et | -0.147 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.009 |
p | +0.009 |
et | +0.009 |
ah | +0.009 |
Neg logit contributions | |
istered | -0.010 |
ls | -0.010 |
ve | -0.009 |
ashamed | -0.009 |
guilty | -0.008 |
Token | came |
Token ID | 1625 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
istered | +0.035 |
ls | +0.031 |
uddle | +0.030 |
apy | +0.029 |
ve | +0.028 |
Neg logit contributions | |
p | -0.017 |
et | -0.017 |
day | -0.016 |
afternoon | -0.016 |
weekend | -0.016 |
Token | into |
Token ID | 656 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
istered | +0.047 |
ls | +0.045 |
ve | +0.041 |
apy | +0.041 |
ashamed | +0.039 |
Neg logit contributions | |
weekend | -0.027 |
afternoon | -0.027 |
p | -0.026 |
day | -0.026 |
et | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
istered | +0.053 |
ls | +0.051 |
uddle | +0.047 |
ve | +0.046 |
iqu | +0.046 |
Neg logit contributions | |
afternoon | -0.027 |
weekend | -0.026 |
day | -0.026 |
p | -0.025 |
et | -0.024 |
Token | Can |
Token ID | 1680 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
istered | +0.021 |
ls | +0.020 |
ve | +0.018 |
apy | +0.017 |
ashamed | +0.017 |
Neg logit contributions | |
weekend | -0.020 |
afternoon | -0.019 |
p | -0.019 |
et | -0.019 |
day | -0.019 |
Token | I |
Token ID | 314 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
istered | +0.026 |
ls | +0.022 |
ve | +0.021 |
uddle | +0.020 |
oled | +0.020 |
Neg logit contributions | |
p | -0.027 |
weekend | -0.026 |
day | -0.026 |
afternoon | -0.025 |
morning | -0.025 |
Token | touch |
Token ID | 3638 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
istered | +0.026 |
ls | +0.024 |
ve | +0.022 |
oled | +0.021 |
apy | +0.021 |
Neg logit contributions | |
p | -0.021 |
day | -0.021 |
ah | -0.020 |
weekend | -0.020 |
et | -0.020 |
Token | you |
Token ID | 345 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
istered | +0.036 |
ls | +0.032 |
ve | +0.030 |
apy | +0.029 |
iqu | +0.029 |
Neg logit contributions | |
weekend | -0.033 |
afternoon | -0.033 |
p | -0.033 |
et | -0.032 |
day | -0.032 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
ls | +0.037 |
istered | +0.036 |
ve | +0.033 |
uddle | +0.030 |
ashamed | +0.030 |
Neg logit contributions | |
afternoon | -0.047 |
weekend | -0.047 |
et | -0.045 |
day | -0.043 |
p | -0.043 |
Token | Fl |
Token ID | 1610 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
istered | +0.061 |
ls | +0.057 |
ve | +0.052 |
apy | +0.050 |
ashamed | +0.048 |
Neg logit contributions | |
weekend | -0.068 |
afternoon | -0.068 |
p | -0.066 |
et | -0.065 |
day | -0.065 |
Token | uffy |
Token ID | 15352 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ashamed | +0.088 |
guilty | +0.088 |
ls | +0.087 |
istered | +0.086 |
nam | +0.080 |
Neg logit contributions | |
ah | -0.161 |
p | -0.156 |
man | -0.151 |
afternoon | -0.150 |
iny | -0.150 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
istered | +0.060 |
ls | +0.056 |
ve | +0.052 |
apy | +0.051 |
uddle | +0.050 |
Neg logit contributions | |
p | -0.053 |
et | -0.051 |
afternoon | -0.050 |
ah | -0.050 |
day | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
istered | +0.038 |
ls | +0.036 |
ve | +0.032 |
apy | +0.031 |
uddle | +0.030 |
Neg logit contributions | |
afternoon | -0.045 |
weekend | -0.045 |
p | -0.045 |
et | -0.044 |
day | -0.044 |
Token | |
Token ID | 220 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
istered | +0.024 |
ls | +0.023 |
ve | +0.021 |
iqu | +0.020 |
apy | +0.020 |
Neg logit contributions | |
weekend | -0.023 |
afternoon | -0.023 |
p | -0.023 |
day | -0.022 |
et | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
istered | +0.094 |
ls | +0.083 |
ve | +0.078 |
iqu | +0.077 |
ashamed | +0.076 |
Neg logit contributions | |
weekend | -0.066 |
day | -0.065 |
p | -0.065 |
afternoon | -0.064 |
morning | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
istered | +0.000 |
ls | +0.000 |
ve | +0.000 |
iqu | +0.000 |
vell | +0.000 |
Neg logit contributions | |
weekend | -0.000 |
day | -0.000 |
afternoon | -0.000 |
p | -0.000 |
morning | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
istered | +0.018 |
ls | +0.017 |
ve | +0.015 |
iqu | +0.015 |
ashamed | +0.015 |
Neg logit contributions | |
afternoon | -0.012 |
weekend | -0.012 |
p | -0.012 |
day | -0.011 |
et | -0.011 |
Token | farmer |
Token ID | 18739 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
weekend | +0.005 |
afternoon | +0.005 |
day | +0.005 |
et | +0.005 |
p | +0.005 |
Neg logit contributions | |
istered | -0.006 |
ls | -0.005 |
apy | -0.005 |
ve | -0.005 |
uffed | -0.005 |
Token | hears |
Token ID | 23180 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
istered | +0.008 |
ls | +0.007 |
ve | +0.007 |
apy | +0.007 |
iqu | +0.006 |
Neg logit contributions | |
afternoon | -0.009 |
et | -0.009 |
weekend | -0.009 |
p | -0.009 |
day | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
istered | +0.015 |
ls | +0.013 |
ve | +0.013 |
iqu | +0.012 |
uddle | +0.012 |
Neg logit contributions | |
weekend | -0.011 |
p | -0.011 |
afternoon | -0.011 |
day | -0.011 |
et | -0.011 |
Token | comm |
Token ID | 725 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
p | +0.002 |
day | +0.002 |
et | +0.002 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
apy | -0.003 |
ve | -0.002 |
uffed | -0.002 |
Token | otion |
Token ID | 9650 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
istered | +0.124 |
iqu | +0.103 |
uddle | +0.097 |
ls | +0.096 |
ashamed | +0.090 |
Neg logit contributions | |
p | -0.147 |
weekend | -0.145 |
day | -0.142 |
afternoon | -0.141 |
et | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
weekend | +0.004 |
afternoon | +0.004 |
et | +0.004 |
p | +0.004 |
day | +0.004 |
Neg logit contributions | |
istered | -0.005 |
ls | -0.005 |
ve | -0.004 |
apy | -0.004 |
ashamed | -0.004 |
Token | comes |
Token ID | 2058 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
istered | +0.036 |
ve | +0.031 |
apy | +0.030 |
ls | +0.030 |
uddle | +0.029 |
Neg logit contributions | |
p | -0.024 |
et | -0.024 |
afternoon | -0.022 |
day | -0.022 |
weekend | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
istered | +0.066 |
ls | +0.062 |
apy | +0.059 |
ve | +0.058 |
iqu | +0.057 |
Neg logit contributions | |
p | -0.030 |
weekend | -0.028 |
afternoon | -0.028 |
day | -0.028 |
et | -0.026 |
Token | see |
Token ID | 766 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
istered | +0.075 |
ls | +0.072 |
ve | +0.066 |
apy | +0.065 |
uddle | +0.064 |
Neg logit contributions | |
weekend | -0.056 |
afternoon | -0.055 |
p | -0.053 |
day | -0.053 |
et | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.010 |
et | +0.010 |
p | +0.010 |
day | +0.010 |
Neg logit contributions | |
istered | -0.010 |
ls | -0.010 |
ve | -0.009 |
apy | -0.008 |
ashamed | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
weekend | +0.014 |
afternoon | +0.014 |
et | +0.014 |
p | +0.013 |
day | +0.013 |
Neg logit contributions | |
istered | -0.012 |
ls | -0.011 |
ve | -0.010 |
apy | -0.010 |
ashamed | -0.009 |
Token | little |
Token ID | 1310 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
weekend | +0.016 |
afternoon | +0.016 |
day | +0.016 |
et | +0.015 |
p | +0.015 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.016 |
ve | -0.015 |
apy | -0.014 |
iqu | -0.014 |
Token | boy |
Token ID | 2933 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
et | +0.002 |
p | +0.002 |
day | +0.002 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
ve | -0.002 |
apy | -0.002 |
ashamed | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
weekend | +0.001 |
afternoon | +0.001 |
et | +0.001 |
p | +0.001 |
day | +0.001 |
Neg logit contributions | |
istered | -0.001 |
ls | -0.001 |
ve | -0.001 |
apy | -0.001 |
ashamed | -0.001 |
Token | comm |
Token ID | 725 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
weekend | +0.005 |
afternoon | +0.005 |
et | +0.005 |
ah | +0.005 |
p | +0.005 |
Neg logit contributions | |
istered | -0.004 |
ashamed | -0.004 |
ve | -0.004 |
shocked | -0.004 |
ls | -0.004 |
Token | ended |
Token ID | 1631 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
istered | +0.125 |
ls | +0.114 |
uddle | +0.104 |
ashamed | +0.093 |
iqu | +0.093 |
Neg logit contributions | |
weekend | -0.140 |
et | -0.136 |
p | -0.135 |
afternoon | -0.133 |
day | -0.132 |
Token | for |
Token ID | 329 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
weekend | +0.082 |
afternoon | +0.079 |
p | +0.076 |
day | +0.075 |
et | +0.075 |
Neg logit contributions | |
istered | -0.062 |
ls | -0.060 |
ve | -0.054 |
ashamed | -0.052 |
apy | -0.052 |
Token | his |
Token ID | 465 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
weekend | +0.015 |
afternoon | +0.015 |
et | +0.015 |
p | +0.015 |
day | +0.014 |
Neg logit contributions | |
istered | -0.018 |
ls | -0.018 |
ve | -0.016 |
apy | -0.016 |
ashamed | -0.015 |
Token | bravery |
Token ID | 37808 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.010 |
day | +0.009 |
et | +0.009 |
p | +0.009 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.009 |
ve | -0.008 |
apy | -0.008 |
ashamed | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
weekend | +0.036 |
afternoon | +0.036 |
p | +0.035 |
et | +0.035 |
ah | +0.034 |
Neg logit contributions | |
istered | -0.025 |
ls | -0.024 |
ve | -0.022 |
ashamed | -0.020 |
apy | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
weekend | +0.009 |
afternoon | +0.009 |
et | +0.008 |
p | +0.008 |
day | +0.008 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.009 |
ve | -0.008 |
apy | -0.008 |
ashamed | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.003 |
ve | +0.003 |
apy | +0.003 |
ashamed | +0.003 |
Neg logit contributions | |
weekend | -0.004 |
afternoon | -0.004 |
p | -0.004 |
day | -0.004 |
et | -0.004 |
Token | Jen |
Token ID | 44875 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
istered | +0.015 |
ls | +0.014 |
ve | +0.013 |
apy | +0.013 |
ashamed | +0.012 |
Neg logit contributions | |
weekend | -0.016 |
afternoon | -0.016 |
et | -0.016 |
p | -0.015 |
day | -0.015 |
Token | heard |
Token ID | 2982 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
weekend | +0.019 |
afternoon | +0.019 |
et | +0.018 |
p | +0.018 |
day | +0.018 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.016 |
ve | -0.015 |
apy | -0.014 |
ashamed | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
istered | +0.019 |
ls | +0.019 |
apy | +0.017 |
ve | +0.017 |
ashamed | +0.017 |
Neg logit contributions | |
weekend | -0.019 |
afternoon | -0.019 |
et | -0.018 |
day | -0.018 |
p | -0.018 |
Token | comm |
Token ID | 725 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
istered | +0.024 |
ls | +0.022 |
ve | +0.021 |
apy | +0.020 |
oled | +0.020 |
Neg logit contributions | |
afternoon | -0.019 |
day | -0.019 |
weekend | -0.019 |
p | -0.019 |
morning | -0.018 |
Token | otion |
Token ID | 9650 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
istered | +0.111 |
ls | +0.093 |
uddle | +0.085 |
iqu | +0.085 |
ashamed | +0.081 |
Neg logit contributions | |
p | -0.153 |
weekend | -0.152 |
et | -0.151 |
afternoon | -0.150 |
day | -0.148 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
weekend | +0.004 |
afternoon | +0.003 |
p | +0.003 |
et | +0.003 |
ah | +0.003 |
Neg logit contributions | |
ls | -0.004 |
istered | -0.004 |
ve | -0.003 |
ashamed | -0.003 |
apy | -0.003 |
Token | came |
Token ID | 1625 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
istered | +0.036 |
ls | +0.032 |
ve | +0.031 |
uddle | +0.030 |
� | +0.029 |
Neg logit contributions | |
p | -0.022 |
et | -0.022 |
afternoon | -0.020 |
ah | -0.020 |
day | -0.020 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
istered | +0.061 |
ls | +0.058 |
ve | +0.053 |
apy | +0.053 |
ashamed | +0.052 |
Neg logit contributions | |
p | -0.034 |
afternoon | -0.034 |
weekend | -0.034 |
day | -0.032 |
et | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
istered | +0.044 |
ls | +0.041 |
ve | +0.038 |
iqu | +0.036 |
apy | +0.036 |
Neg logit contributions | |
afternoon | -0.048 |
weekend | -0.048 |
day | -0.047 |
p | -0.046 |
et | -0.045 |
Token | my |
Token ID | 1820 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
weekend | +0.008 |
afternoon | +0.007 |
p | +0.007 |
day | +0.007 |
morning | +0.006 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.013 |
ve | -0.013 |
ashamed | -0.013 |
shocked | -0.012 |
Token | 's |
Token ID | 338 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
istered | +0.007 |
ls | +0.006 |
ve | +0.006 |
apy | +0.006 |
iqu | +0.005 |
Neg logit contributions | |
afternoon | -0.006 |
weekend | -0.006 |
et | -0.006 |
p | -0.006 |
day | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
afternoon | +0.034 |
weekend | +0.033 |
day | +0.033 |
et | +0.032 |
p | +0.032 |
Neg logit contributions | |
istered | -0.024 |
ls | -0.023 |
ve | -0.021 |
apy | -0.019 |
oled | -0.018 |
Token | heard |
Token ID | 2982 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
istered | +0.007 |
ls | +0.006 |
apy | +0.006 |
ve | +0.005 |
uddle | +0.005 |
Neg logit contributions | |
et | -0.005 |
afternoon | -0.005 |
p | -0.005 |
weekend | -0.005 |
day | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
istered | +0.008 |
ls | +0.008 |
ve | +0.007 |
apy | +0.007 |
ashamed | +0.007 |
Neg logit contributions | |
weekend | -0.008 |
afternoon | -0.008 |
et | -0.008 |
p | -0.008 |
day | -0.008 |
Token | comm |
Token ID | 725 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
istered | +0.010 |
ls | +0.010 |
apy | +0.009 |
oms | +0.008 |
uffed | +0.008 |
Neg logit contributions | |
day | -0.008 |
afternoon | -0.008 |
weekend | -0.008 |
p | -0.008 |
man | -0.007 |
Token | otion |
Token ID | 9650 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
istered | +0.117 |
ls | +0.098 |
uddle | +0.093 |
iqu | +0.091 |
ashamed | +0.084 |
Neg logit contributions | |
weekend | -0.147 |
day | -0.143 |
afternoon | -0.143 |
p | -0.142 |
et | -0.142 |
Token | and |
Token ID | 290 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
p | +0.011 |
et | +0.011 |
day | +0.011 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.013 |
ve | -0.012 |
ashamed | -0.012 |
apy | -0.011 |
Token | came |
Token ID | 1625 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
istered | +0.027 |
ls | +0.024 |
uddle | +0.023 |
ve | +0.022 |
� | +0.022 |
Neg logit contributions | |
p | -0.013 |
et | -0.013 |
day | -0.013 |
afternoon | -0.013 |
weekend | -0.012 |
Token | running |
Token ID | 2491 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
istered | +0.042 |
ls | +0.040 |
ve | +0.037 |
apy | +0.037 |
ashamed | +0.036 |
Neg logit contributions | |
weekend | -0.022 |
afternoon | -0.022 |
p | -0.022 |
day | -0.021 |
et | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
istered | +0.012 |
ls | +0.012 |
ve | +0.011 |
apy | +0.011 |
iqu | +0.011 |
Neg logit contributions | |
afternoon | -0.007 |
weekend | -0.007 |
p | -0.006 |
et | -0.006 |
day | -0.006 |
Token | came |
Token ID | 1625 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
istered | +0.005 |
ls | +0.005 |
apy | +0.004 |
ve | +0.004 |
uddle | +0.004 |
Neg logit contributions | |
et | -0.005 |
p | -0.005 |
weekend | -0.005 |
afternoon | -0.004 |
ah | -0.004 |
Token | quickly |
Token ID | 2952 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
istered | +0.060 |
ls | +0.057 |
ve | +0.053 |
apy | +0.052 |
ashamed | +0.050 |
Neg logit contributions | |
weekend | -0.038 |
afternoon | -0.038 |
p | -0.037 |
et | -0.036 |
day | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
istered | +0.020 |
ls | +0.019 |
apy | +0.018 |
ve | +0.017 |
iqu | +0.017 |
Neg logit contributions | |
weekend | -0.011 |
afternoon | -0.011 |
p | -0.011 |
day | -0.011 |
et | -0.011 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
istered | +0.040 |
ls | +0.035 |
uddle | +0.034 |
apy | +0.033 |
ve | +0.033 |
Neg logit contributions | |
p | -0.030 |
et | -0.029 |
weekend | -0.029 |
afternoon | -0.028 |
day | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
istered | +0.017 |
ve | +0.015 |
ls | +0.015 |
uddle | +0.014 |
apy | +0.014 |
Neg logit contributions | |
weekend | -0.010 |
et | -0.009 |
day | -0.009 |
p | -0.009 |
afternoon | -0.009 |
Token | comm |
Token ID | 725 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
istered | +0.021 |
ls | +0.020 |
apy | +0.019 |
ve | +0.019 |
uffed | +0.018 |
Neg logit contributions | |
weekend | -0.020 |
day | -0.020 |
afternoon | -0.020 |
morning | -0.019 |
et | -0.018 |
Token | otion |
Token ID | 9650 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
istered | +0.122 |
uddle | +0.098 |
iqu | +0.098 |
ls | +0.096 |
ashamed | +0.092 |
Neg logit contributions | |
weekend | -0.141 |
day | -0.136 |
afternoon | -0.136 |
p | -0.136 |
et | -0.131 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
weekend | +0.013 |
afternoon | +0.013 |
et | +0.012 |
p | +0.012 |
day | +0.012 |
Neg logit contributions | |
istered | -0.012 |
ls | -0.011 |
ve | -0.010 |
apy | -0.010 |
ashamed | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
istered | +0.033 |
ls | +0.031 |
ve | +0.028 |
apy | +0.026 |
iqu | +0.026 |
Neg logit contributions | |
afternoon | -0.042 |
weekend | -0.041 |
day | -0.040 |
et | -0.040 |
p | -0.040 |
Token | She |
Token ID | 1375 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
weekend | +0.003 |
day | +0.003 |
afternoon | +0.003 |
morning | +0.003 |
Wednesday | +0.003 |
Neg logit contributions | |
istered | -0.005 |
ls | -0.005 |
ve | -0.005 |
vell | -0.005 |
uddle | -0.005 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
p | +0.001 |
afternoon | +0.001 |
weekend | +0.001 |
et | +0.001 |
day | +0.001 |
Neg logit contributions | |
istered | -0.001 |
ls | -0.001 |
ve | -0.001 |
apy | -0.001 |
uddle | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
istered | +0.047 |
iqu | +0.040 |
ls | +0.039 |
uddle | +0.037 |
ashamed | +0.037 |
Neg logit contributions | |
p | -0.036 |
day | -0.035 |
weekend | -0.034 |
afternoon | -0.032 |
ah | -0.032 |
Token | know |
Token ID | 760 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.003 |
ve | +0.002 |
apy | +0.002 |
ashamed | +0.002 |
Neg logit contributions | |
weekend | -0.002 |
afternoon | -0.002 |
et | -0.002 |
p | -0.002 |
day | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
istered | +0.008 |
ls | +0.007 |
ve | +0.007 |
apy | +0.007 |
oled | +0.007 |
Neg logit contributions | |
et | -0.006 |
p | -0.006 |
afternoon | -0.006 |
weekend | -0.006 |
day | -0.006 |
Token | why |
Token ID | 1521 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
weekend | +0.030 |
afternoon | +0.030 |
et | +0.029 |
p | +0.029 |
day | +0.028 |
Neg logit contributions | |
istered | -0.026 |
ls | -0.025 |
ve | -0.022 |
apy | -0.022 |
ashamed | -0.022 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
istered | +0.069 |
ls | +0.062 |
ve | +0.060 |
iqu | +0.056 |
uddle | +0.055 |
Neg logit contributions | |
day | -0.054 |
weekend | -0.053 |
afternoon | -0.052 |
et | -0.051 |
p | -0.051 |
Token | gigg |
Token ID | 30442 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
istered | +0.050 |
ls | +0.050 |
apy | +0.044 |
ve | +0.044 |
ashamed | +0.043 |
Neg logit contributions | |
weekend | -0.078 |
et | -0.077 |
afternoon | -0.076 |
p | -0.075 |
ah | -0.074 |
Token | led |
Token ID | 992 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
istered | +0.128 |
ls | +0.100 |
apy | +0.098 |
iqu | +0.097 |
ve | +0.096 |
Neg logit contributions | |
et | -0.139 |
afternoon | -0.134 |
p | -0.132 |
ah | -0.130 |
day | -0.128 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
istered | +0.022 |
ls | +0.020 |
ve | +0.019 |
apy | +0.018 |
iqu | +0.017 |
Neg logit contributions | |
afternoon | -0.022 |
weekend | -0.021 |
p | -0.021 |
et | -0.021 |
day | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
istered | +0.034 |
ls | +0.033 |
ve | +0.030 |
apy | +0.029 |
uddle | +0.028 |
Neg logit contributions | |
afternoon | -0.033 |
p | -0.033 |
weekend | -0.033 |
et | -0.032 |
day | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
istered | +0.002 |
ls | +0.002 |
ve | +0.002 |
iqu | +0.002 |
apy | +0.002 |
Neg logit contributions | |
weekend | -0.002 |
day | -0.002 |
afternoon | -0.002 |
p | -0.002 |
morning | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
day | +0.003 |
p | +0.003 |
et | +0.002 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
ve | -0.002 |
ashamed | -0.002 |
iqu | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
weekend | +0.026 |
et | +0.026 |
afternoon | +0.026 |
p | +0.025 |
rated | +0.025 |
Neg logit contributions | |
ls | -0.019 |
istered | -0.017 |
apy | -0.016 |
s | -0.016 |
ve | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
istered | +0.005 |
ve | +0.005 |
ls | +0.005 |
uddle | +0.004 |
iqu | +0.004 |
Neg logit contributions | |
day | -0.003 |
afternoon | -0.003 |
morning | -0.003 |
et | -0.003 |
p | -0.003 |
Token | band |
Token ID | 4097 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
istered | +0.032 |
ls | +0.029 |
apy | +0.026 |
ve | +0.025 |
iqu | +0.025 |
Neg logit contributions | |
day | -0.028 |
afternoon | -0.026 |
weekend | -0.026 |
morning | -0.025 |
p | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
weekend | +0.045 |
afternoon | +0.044 |
et | +0.042 |
p | +0.041 |
day | +0.040 |
Neg logit contributions | |
istered | -0.062 |
ls | -0.060 |
ve | -0.057 |
apy | -0.054 |
ashamed | -0.053 |
Token | got |
Token ID | 1392 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
istered | +0.010 |
ls | +0.010 |
ve | +0.009 |
apy | +0.009 |
ashamed | +0.008 |
Neg logit contributions | |
weekend | -0.011 |
afternoon | -0.011 |
et | -0.010 |
p | -0.010 |
day | -0.010 |
Token | aut |
Token ID | 1960 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
istered | +0.038 |
ls | +0.035 |
ve | +0.034 |
oled | +0.032 |
uddle | +0.032 |
Neg logit contributions | |
afternoon | -0.021 |
day | -0.021 |
weekend | -0.021 |
p | -0.021 |
morning | -0.020 |
Token | ographs |
Token ID | 33492 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
istered | +0.118 |
ls | +0.113 |
ashamed | +0.104 |
guilty | +0.104 |
sorry | +0.095 |
Neg logit contributions | |
ah | -0.137 |
afternoon | -0.129 |
p | -0.128 |
weekend | -0.126 |
et | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.009 |
et | +0.009 |
p | +0.009 |
day | +0.009 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.007 |
ve | -0.006 |
apy | -0.006 |
ashamed | -0.006 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
weekend | +0.002 |
afternoon | +0.002 |
day | +0.002 |
morning | +0.002 |
et | +0.002 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
iqu | -0.002 |
apy | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
afternoon | +0.003 |
weekend | +0.003 |
et | +0.003 |
day | +0.003 |
p | +0.003 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
ve | -0.003 |
apy | -0.003 |
iqu | -0.003 |
Token | so |
Token ID | 523 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
weekend | +0.004 |
afternoon | +0.004 |
et | +0.004 |
ah | +0.004 |
p | +0.004 |
Neg logit contributions | |
istered | -0.004 |
ashamed | -0.003 |
shocked | -0.003 |
guilty | -0.003 |
ls | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
istered | +0.052 |
ls | +0.047 |
ve | +0.043 |
iqu | +0.042 |
apy | +0.041 |
Neg logit contributions | |
day | -0.066 |
weekend | -0.064 |
ah | -0.064 |
p | -0.063 |
afternoon | -0.063 |
Token | you |
Token ID | 345 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
istered | +0.032 |
ls | +0.026 |
ve | +0.025 |
oled | +0.025 |
apy | +0.024 |
Neg logit contributions | |
weekend | -0.037 |
day | -0.036 |
afternoon | -0.036 |
p | -0.035 |
morning | -0.034 |
Token | sad |
Token ID | 6507 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
istered | +0.039 |
ls | +0.037 |
ve | +0.035 |
ashamed | +0.034 |
guilty | +0.034 |
Neg logit contributions | |
afternoon | -0.044 |
weekend | -0.044 |
et | -0.042 |
ah | -0.041 |
p | -0.040 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
istered | +0.025 |
ls | +0.024 |
ve | +0.022 |
apy | +0.021 |
ashamed | +0.021 |
Neg logit contributions | |
weekend | -0.024 |
afternoon | -0.024 |
et | -0.023 |
p | -0.023 |
day | -0.023 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
istered | +0.048 |
ls | +0.042 |
ve | +0.041 |
uddle | +0.038 |
iqu | +0.038 |
Neg logit contributions | |
p | -0.041 |
weekend | -0.040 |
afternoon | -0.040 |
day | -0.040 |
morning | -0.038 |
Token | Fl |
Token ID | 1610 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
istered | +0.028 |
ls | +0.026 |
ve | +0.024 |
apy | +0.023 |
ashamed | +0.022 |
Neg logit contributions | |
weekend | -0.028 |
afternoon | -0.028 |
p | -0.027 |
et | -0.027 |
day | -0.027 |
Token | opsy |
Token ID | 44522 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
istered | +0.121 |
ashamed | +0.115 |
guilty | +0.113 |
ls | +0.112 |
shocked | +0.110 |
Neg logit contributions | |
ah | -0.122 |
p | -0.120 |
afternoon | -0.113 |
ifi | -0.112 |
day | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
istered | +0.023 |
ls | +0.021 |
ve | +0.020 |
apy | +0.020 |
iqu | +0.018 |
Neg logit contributions | |
p | -0.023 |
day | -0.023 |
weekend | -0.023 |
afternoon | -0.023 |
et | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
istered | +0.015 |
ls | +0.014 |
ve | +0.013 |
apy | +0.012 |
iqu | +0.012 |
Neg logit contributions | |
weekend | -0.013 |
p | -0.013 |
afternoon | -0.013 |
day | -0.013 |
morning | -0.012 |
Token | I |
Token ID | 40 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
istered | +0.037 |
ls | +0.036 |
ve | +0.032 |
uddle | +0.030 |
oms | +0.030 |
Neg logit contributions | |
weekend | -0.044 |
afternoon | -0.044 |
p | -0.043 |
day | -0.043 |
et | -0.041 |
Token | lost |
Token ID | 2626 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
istered | +0.042 |
ls | +0.040 |
uffed | +0.037 |
apy | +0.037 |
iqu | +0.035 |
Neg logit contributions | |
day | -0.055 |
weekend | -0.051 |
ah | -0.051 |
afternoon | -0.051 |
morning | -0.050 |
Token | find |
Token ID | 1064 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
istered | +0.021 |
ls | +0.021 |
ve | +0.019 |
ashamed | +0.018 |
apy | +0.018 |
Neg logit contributions | |
weekend | -0.021 |
afternoon | -0.021 |
et | -0.020 |
p | -0.020 |
ah | -0.020 |
Token | out |
Token ID | 503 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
weekend | +0.009 |
afternoon | +0.009 |
et | +0.009 |
p | +0.009 |
day | +0.009 |
Neg logit contributions | |
istered | -0.012 |
ls | -0.012 |
ve | -0.011 |
apy | -0.011 |
ashamed | -0.010 |
Token | what |
Token ID | 644 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
weekend | +0.007 |
afternoon | +0.007 |
p | +0.007 |
et | +0.007 |
day | +0.007 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.007 |
ve | -0.006 |
apy | -0.006 |
uddle | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
istered | +0.077 |
ls | +0.075 |
ve | +0.067 |
apy | +0.066 |
ashamed | +0.064 |
Neg logit contributions | |
weekend | -0.077 |
afternoon | -0.076 |
et | -0.074 |
p | -0.074 |
day | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
weekend | +0.028 |
afternoon | +0.027 |
et | +0.027 |
ah | +0.026 |
p | +0.026 |
Neg logit contributions | |
ls | -0.037 |
istered | -0.034 |
ashamed | -0.032 |
guilty | -0.031 |
apy | -0.031 |
Token | comm |
Token ID | 725 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
istered | +0.005 |
ls | +0.005 |
ve | +0.005 |
ashamed | +0.004 |
apy | +0.004 |
Neg logit contributions | |
weekend | -0.006 |
afternoon | -0.006 |
et | -0.006 |
p | -0.006 |
ah | -0.006 |
Token | otion |
Token ID | 9650 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
istered | +0.119 |
uddle | +0.097 |
ls | +0.094 |
ashamed | +0.093 |
iqu | +0.093 |
Neg logit contributions | |
weekend | -0.138 |
p | -0.134 |
et | -0.132 |
day | -0.132 |
afternoon | -0.131 |
Token | was |
Token ID | 373 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
istered | +0.006 |
ls | +0.006 |
ve | +0.006 |
apy | +0.005 |
ashamed | +0.005 |
Neg logit contributions | |
weekend | -0.007 |
afternoon | -0.007 |
p | -0.007 |
et | -0.007 |
day | -0.007 |
Token | about |
Token ID | 546 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
weekend | +0.029 |
afternoon | +0.029 |
ah | +0.028 |
et | +0.028 |
p | +0.027 |
Neg logit contributions | |
istered | -0.029 |
ls | -0.028 |
ve | -0.026 |
ashamed | -0.025 |
guilty | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
weekend | +0.008 |
afternoon | +0.008 |
day | +0.008 |
p | +0.008 |
et | +0.008 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.006 |
ve | -0.006 |
apy | -0.005 |
ashamed | -0.005 |
Token | When |
Token ID | 1649 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
weekend | +0.002 |
afternoon | +0.002 |
et | +0.002 |
p | +0.002 |
ah | +0.002 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
ashamed | -0.002 |
apy | -0.002 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
istered | +0.033 |
ls | +0.031 |
ve | +0.028 |
ashamed | +0.027 |
apy | +0.026 |
Neg logit contributions | |
weekend | -0.038 |
afternoon | -0.038 |
et | -0.036 |
p | -0.036 |
day | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
istered | +0.024 |
ls | +0.023 |
apy | +0.020 |
ve | +0.020 |
ashamed | +0.020 |
Neg logit contributions | |
weekend | -0.038 |
et | -0.038 |
afternoon | -0.038 |
p | -0.037 |
ah | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
istered | +0.022 |
ls | +0.020 |
ve | +0.019 |
iqu | +0.018 |
sters | +0.018 |
Neg logit contributions | |
afternoon | -0.018 |
day | -0.017 |
weekend | -0.017 |
p | -0.017 |
morning | -0.016 |
Token | L |
Token ID | 43 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
istered | +0.027 |
ls | +0.026 |
apy | +0.023 |
ve | +0.022 |
ashamed | +0.021 |
Neg logit contributions | |
weekend | -0.039 |
afternoon | -0.037 |
et | -0.037 |
day | -0.036 |
p | -0.036 |
Token | ily |
Token ID | 813 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
weekend | +0.004 |
afternoon | +0.004 |
day | +0.003 |
p | +0.003 |
et | +0.003 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
ve | -0.003 |
ashamed | -0.003 |
uddle | -0.003 |
Token | gigg |
Token ID | 30442 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
istered | +0.020 |
ls | +0.017 |
ve | +0.017 |
apy | +0.017 |
oled | +0.015 |
Neg logit contributions | |
et | -0.021 |
afternoon | -0.020 |
p | -0.020 |
weekend | -0.020 |
ah | -0.020 |
Token | les |
Token ID | 829 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
istered | +0.146 |
ve | +0.131 |
apy | +0.130 |
iqu | +0.126 |
itt | +0.119 |
Neg logit contributions | |
et | -0.123 |
p | -0.113 |
afternoon | -0.112 |
day | -0.103 |
ah | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
istered | +0.033 |
ls | +0.030 |
ve | +0.029 |
iqu | +0.028 |
apy | +0.028 |
Neg logit contributions | |
p | -0.029 |
afternoon | -0.028 |
et | -0.028 |
day | -0.027 |
weekend | -0.027 |
Token | nods |
Token ID | 34833 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
istered | +0.001 |
ve | +0.001 |
ls | +0.001 |
oled | +0.001 |
itt | +0.001 |
Neg logit contributions | |
afternoon | -0.001 |
et | -0.001 |
p | -0.001 |
day | -0.001 |
weekend | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
istered | +0.001 |
ls | +0.001 |
ve | +0.000 |
apy | +0.000 |
ashamed | +0.000 |
Neg logit contributions | |
weekend | -0.001 |
afternoon | -0.001 |
et | -0.001 |
p | -0.001 |
day | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
weekend | +0.016 |
afternoon | +0.016 |
day | +0.015 |
morning | +0.015 |
p | +0.015 |
Neg logit contributions | |
istered | -0.019 |
ls | -0.017 |
ve | -0.017 |
iqu | -0.015 |
apy | -0.015 |
Token | One |
Token ID | 1881 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
et | +0.003 |
p | +0.003 |
day | +0.003 |
Neg logit contributions | |
istered | -0.004 |
ls | -0.004 |
ve | -0.003 |
apy | -0.003 |
ashamed | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
et | +0.031 |
pole | +0.028 |
arine | +0.027 |
bet | +0.026 |
p | +0.026 |
Neg logit contributions | |
s | -0.080 |
ls | -0.079 |
istered | -0.078 |
apy | -0.077 |
guilty | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
istered | +0.046 |
iqu | +0.041 |
ls | +0.041 |
ve | +0.040 |
ashamed | +0.039 |
Neg logit contributions | |
day | -0.028 |
afternoon | -0.028 |
weekend | -0.027 |
morning | -0.026 |
p | -0.025 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
weekend | +0.007 |
afternoon | +0.007 |
day | +0.007 |
p | +0.007 |
et | +0.007 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.007 |
ve | -0.006 |
iqu | -0.006 |
ashamed | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
weekend | +0.016 |
afternoon | +0.015 |
et | +0.015 |
p | +0.015 |
day | +0.015 |
Neg logit contributions | |
istered | -0.019 |
ls | -0.018 |
ve | -0.017 |
apy | -0.016 |
ashamed | -0.016 |
Token | Fl |
Token ID | 1610 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
weekend | +0.000 |
et | +0.000 |
afternoon | +0.000 |
p | +0.000 |
ah | +0.000 |
Neg logit contributions | |
istered | -0.000 |
ls | -0.000 |
ve | -0.000 |
apy | -0.000 |
ashamed | -0.000 |
Token | uffy |
Token ID | 15352 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ashamed | +0.102 |
guilty | +0.101 |
nam | +0.098 |
ls | +0.098 |
vell | +0.098 |
Neg logit contributions | |
day | -0.125 |
afternoon | -0.125 |
iny | -0.118 |
ah | -0.118 |
p | -0.115 |
Token | went |
Token ID | 1816 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
istered | +0.056 |
ls | +0.053 |
iqu | +0.050 |
apy | +0.050 |
ve | +0.050 |
Neg logit contributions | |
day | -0.026 |
afternoon | -0.025 |
weekend | -0.024 |
morning | -0.023 |
et | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
et | +0.010 |
afternoon | +0.009 |
weekend | +0.009 |
ah | +0.009 |
p | +0.009 |
Neg logit contributions | |
ls | -0.011 |
istered | -0.011 |
ve | -0.010 |
uddle | -0.009 |
ashamed | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
istered | +0.045 |
ls | +0.043 |
ve | +0.040 |
apy | +0.039 |
iqu | +0.038 |
Neg logit contributions | |
weekend | -0.031 |
afternoon | -0.030 |
day | -0.029 |
p | -0.029 |
et | -0.028 |
Token | market |
Token ID | 1910 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
istered | +0.022 |
ls | +0.021 |
uddle | +0.019 |
ve | +0.019 |
iqu | +0.018 |
Neg logit contributions | |
et | -0.019 |
p | -0.019 |
afternoon | -0.019 |
ah | -0.018 |
weekend | -0.018 |
Token | When |
Token ID | 2215 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
istered | +0.000 |
ve | +0.000 |
ls | +0.000 |
apy | +0.000 |
oled | +0.000 |
Neg logit contributions | |
et | -0.000 |
weekend | -0.000 |
afternoon | -0.000 |
day | -0.000 |
p | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ls | +0.010 |
istered | +0.009 |
apy | +0.009 |
ve | +0.008 |
ashamed | +0.008 |
Neg logit contributions | |
et | -0.014 |
p | -0.014 |
weekend | -0.013 |
afternoon | -0.013 |
ah | -0.013 |
Token | arrived |
Token ID | 5284 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
weekend | +0.039 |
afternoon | +0.039 |
p | +0.037 |
et | +0.037 |
age | +0.035 |
Neg logit contributions | |
ls | -0.033 |
istered | -0.030 |
ve | -0.030 |
gasped | -0.029 |
shocked | -0.028 |
Token | he |
Token ID | 339 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
istered | +0.019 |
ls | +0.018 |
ve | +0.017 |
apy | +0.016 |
iqu | +0.016 |
Neg logit contributions | |
weekend | -0.018 |
afternoon | -0.018 |
day | -0.017 |
et | -0.017 |
p | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
istered | +0.027 |
ls | +0.026 |
ve | +0.023 |
apy | +0.023 |
ashamed | +0.022 |
Neg logit contributions | |
weekend | -0.030 |
afternoon | -0.030 |
et | -0.029 |
p | -0.029 |
day | -0.029 |
Token | pleasantly |
Token ID | 42683 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
istered | +0.041 |
ls | +0.038 |
ve | +0.036 |
ashamed | +0.035 |
shocked | +0.034 |
Neg logit contributions | |
weekend | -0.043 |
afternoon | -0.043 |
et | -0.041 |
day | -0.040 |
ah | -0.040 |
Token | surprised |
Token ID | 6655 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
istered | +0.087 |
ls | +0.076 |
� | +0.071 |
oled | +0.069 |
ve | +0.069 |
Neg logit contributions | |
afternoon | -0.157 |
p | -0.156 |
day | -0.153 |
weekend | -0.150 |
et | -0.148 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
istered | +0.017 |
ls | +0.016 |
ve | +0.015 |
apy | +0.014 |
ashamed | +0.014 |
Neg logit contributions | |
weekend | -0.015 |
afternoon | -0.015 |
et | -0.015 |
p | -0.015 |
day | -0.014 |
Token | find |
Token ID | 1064 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
istered | +0.028 |
ls | +0.028 |
ve | +0.026 |
ashamed | +0.025 |
apy | +0.024 |
Neg logit contributions | |
weekend | -0.040 |
afternoon | -0.040 |
et | -0.038 |
ah | -0.038 |
p | -0.038 |
Token | that |
Token ID | 326 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
istered | +0.014 |
ls | +0.013 |
ve | +0.012 |
apy | +0.012 |
uddle | +0.012 |
Neg logit contributions | |
weekend | -0.010 |
afternoon | -0.010 |
et | -0.010 |
p | -0.010 |
day | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
istered | +0.029 |
ls | +0.028 |
apy | +0.025 |
ve | +0.025 |
ashamed | +0.024 |
Neg logit contributions | |
weekend | -0.029 |
afternoon | -0.028 |
et | -0.028 |
p | -0.028 |
ah | -0.027 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
weekend | +0.007 |
afternoon | +0.007 |
et | +0.007 |
p | +0.007 |
day | +0.007 |
Neg logit contributions | |
ls | -0.004 |
istered | -0.004 |
ve | -0.004 |
apy | -0.003 |
ashamed | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ls | +0.033 |
istered | +0.032 |
apy | +0.029 |
ashamed | +0.029 |
ve | +0.028 |
Neg logit contributions | |
weekend | -0.052 |
afternoon | -0.052 |
et | -0.051 |
ah | -0.049 |
p | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
istered | +0.007 |
ls | +0.006 |
ve | +0.006 |
apy | +0.006 |
ashamed | +0.006 |
Neg logit contributions | |
weekend | -0.008 |
afternoon | -0.008 |
p | -0.008 |
day | -0.007 |
et | -0.007 |
Token | M |
Token ID | 44 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ls | +0.018 |
istered | +0.018 |
apy | +0.016 |
s | +0.015 |
ve | +0.015 |
Neg logit contributions | |
weekend | -0.030 |
afternoon | -0.029 |
et | -0.028 |
day | -0.027 |
morning | -0.027 |
Token | ia |
Token ID | 544 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
istered | +0.004 |
ls | +0.004 |
ve | +0.004 |
apy | +0.004 |
uddle | +0.004 |
Neg logit contributions | |
weekend | -0.002 |
afternoon | -0.002 |
et | -0.002 |
p | -0.002 |
day | -0.002 |
Token | gigg |
Token ID | 30442 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
istered | +0.007 |
ls | +0.006 |
ve | +0.006 |
apy | +0.006 |
oled | +0.006 |
Neg logit contributions | |
et | -0.006 |
afternoon | -0.006 |
weekend | -0.006 |
p | -0.006 |
ah | -0.006 |
Token | les |
Token ID | 829 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
istered | +0.146 |
apy | +0.126 |
ve | +0.120 |
iqu | +0.118 |
� | +0.117 |
Neg logit contributions | |
et | -0.127 |
p | -0.114 |
afternoon | -0.112 |
ah | -0.107 |
day | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
istered | +0.036 |
ls | +0.033 |
ve | +0.032 |
iqu | +0.031 |
uddle | +0.031 |
Neg logit contributions | |
p | -0.031 |
afternoon | -0.030 |
et | -0.029 |
day | -0.029 |
weekend | -0.028 |
Token | " |
Token ID | 366 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
istered | +0.008 |
ls | +0.007 |
ve | +0.007 |
apy | +0.006 |
iqu | +0.006 |
Neg logit contributions | |
weekend | -0.007 |
afternoon | -0.007 |
p | -0.007 |
day | -0.007 |
et | -0.007 |
Token | Do |
Token ID | 5211 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
istered | +0.032 |
ls | +0.030 |
ve | +0.028 |
apy | +0.027 |
ashamed | +0.026 |
Neg logit contributions | |
weekend | -0.040 |
afternoon | -0.039 |
et | -0.039 |
day | -0.037 |
p | -0.037 |
Token | you |
Token ID | 345 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
weekend | +0.018 |
afternoon | +0.018 |
et | +0.018 |
p | +0.018 |
day | +0.017 |
Neg logit contributions | |
istered | -0.008 |
ls | -0.008 |
ve | -0.007 |
apy | -0.006 |
ashamed | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
weekend | +0.008 |
afternoon | +0.008 |
day | +0.007 |
p | +0.007 |
morning | +0.007 |
Neg logit contributions | |
istered | -0.008 |
ls | -0.008 |
ve | -0.007 |
iqu | -0.007 |
ashamed | -0.007 |
Token | B |
Token ID | 33 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
istered | +0.005 |
ls | +0.005 |
ve | +0.005 |
apy | +0.004 |
ashamed | +0.004 |
Neg logit contributions | |
weekend | -0.004 |
afternoon | -0.004 |
et | -0.004 |
p | -0.004 |
day | -0.004 |
Token | eth |
Token ID | 2788 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
istered | +0.008 |
ls | +0.008 |
ashamed | +0.007 |
apy | +0.007 |
ve | +0.007 |
Neg logit contributions | |
weekend | -0.008 |
afternoon | -0.008 |
et | -0.008 |
day | -0.008 |
ah | -0.008 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
weekend | +0.064 |
afternoon | +0.060 |
day | +0.057 |
p | +0.057 |
morning | +0.056 |
Neg logit contributions | |
ls | -0.045 |
ve | -0.043 |
istered | -0.042 |
gasped | -0.039 |
ashamed | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
et | +0.003 |
ah | +0.003 |
p | +0.003 |
Neg logit contributions | |
istered | -0.004 |
ls | -0.004 |
apy | -0.004 |
ve | -0.004 |
ashamed | -0.003 |
Token | comm |
Token ID | 725 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
istered | +0.015 |
ls | +0.014 |
ve | +0.013 |
apy | +0.013 |
iqu | +0.012 |
Neg logit contributions | |
weekend | -0.013 |
afternoon | -0.013 |
day | -0.013 |
p | -0.013 |
et | -0.013 |
Token | otion |
Token ID | 9650 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
istered | +0.104 |
ls | +0.092 |
uddle | +0.082 |
iqu | +0.079 |
ashamed | +0.076 |
Neg logit contributions | |
weekend | -0.150 |
afternoon | -0.145 |
day | -0.143 |
p | -0.143 |
et | -0.143 |
Token | and |
Token ID | 290 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
weekend | +0.007 |
afternoon | +0.007 |
p | +0.007 |
et | +0.007 |
ah | +0.007 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.007 |
ashamed | -0.006 |
ve | -0.006 |
apy | -0.006 |
Token | came |
Token ID | 1625 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
istered | +0.018 |
ls | +0.017 |
ve | +0.015 |
apy | +0.015 |
uddle | +0.014 |
Neg logit contributions | |
weekend | -0.017 |
afternoon | -0.017 |
p | -0.016 |
et | -0.016 |
day | -0.016 |
Token | running |
Token ID | 2491 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
istered | +0.046 |
ls | +0.044 |
ve | +0.040 |
apy | +0.040 |
ashamed | +0.039 |
Neg logit contributions | |
weekend | -0.026 |
afternoon | -0.026 |
p | -0.026 |
day | -0.025 |
et | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
istered | +0.006 |
ls | +0.006 |
ve | +0.005 |
apy | +0.005 |
ashamed | +0.005 |
Neg logit contributions | |
weekend | -0.005 |
afternoon | -0.005 |
et | -0.004 |
p | -0.004 |
day | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
weekend | +0.007 |
afternoon | +0.007 |
p | +0.007 |
et | +0.007 |
day | +0.007 |
Neg logit contributions | |
istered | -0.004 |
ls | -0.004 |
ve | -0.003 |
ashamed | -0.003 |
apy | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
weekend | +0.025 |
afternoon | +0.025 |
p | +0.024 |
et | +0.024 |
day | +0.024 |
Neg logit contributions | |
istered | -0.022 |
ls | -0.021 |
ve | -0.020 |
apy | -0.018 |
ashamed | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
weekend | +0.022 |
afternoon | +0.021 |
et | +0.021 |
p | +0.021 |
day | +0.020 |
Neg logit contributions | |
istered | -0.019 |
ls | -0.018 |
ve | -0.017 |
apy | -0.016 |
ashamed | -0.016 |
Token | The |
Token ID | 464 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
et | +0.005 |
weekend | +0.004 |
afternoon | +0.004 |
ah | +0.004 |
day | +0.004 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
ve | -0.003 |
apy | -0.003 |
s | -0.002 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
weekend | +0.009 |
afternoon | +0.009 |
et | +0.009 |
p | +0.009 |
ah | +0.009 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.008 |
ve | -0.008 |
apy | -0.007 |
ashamed | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
et | +0.061 |
zie | +0.056 |
pole | +0.056 |
ah | +0.054 |
afternoon | +0.054 |
Neg logit contributions | |
ls | -0.042 |
istered | -0.037 |
s | -0.035 |
ashamed | -0.035 |
itt | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
wn | +0.221 |
rated | +0.217 |
pole | +0.211 |
ah | +0.208 |
et | +0.206 |
Neg logit contributions | |
ls | -0.061 |
itt | -0.052 |
fighting | -0.050 |
shocked | -0.050 |
s | -0.049 |
Token | story |
Token ID | 1621 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
et | +0.061 |
afternoon | +0.058 |
weekend | +0.058 |
p | +0.057 |
ah | +0.056 |
Neg logit contributions | |
ls | -0.100 |
istered | -0.099 |
ve | -0.093 |
ashamed | -0.088 |
uddle | -0.087 |
Token | is |
Token ID | 318 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
et | +0.084 |
afternoon | +0.084 |
weekend | +0.084 |
p | +0.083 |
ah | +0.080 |
Neg logit contributions | |
ls | -0.068 |
istered | -0.065 |
ve | -0.057 |
apy | -0.055 |
ashamed | -0.054 |
Token | : |
Token ID | 25 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
weekend | +0.037 |
afternoon | +0.037 |
et | +0.037 |
ah | +0.035 |
p | +0.035 |
Neg logit contributions | |
istered | -0.044 |
ls | -0.044 |
ve | -0.040 |
ashamed | -0.039 |
apy | -0.039 |
Token | You |
Token ID | 921 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
weekend | +0.031 |
afternoon | +0.030 |
et | +0.030 |
p | +0.029 |
ah | +0.029 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.026 |
ve | -0.024 |
apy | -0.023 |
ashamed | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
afternoon | +0.020 |
weekend | +0.020 |
day | +0.019 |
et | +0.019 |
p | +0.019 |
Neg logit contributions | |
istered | -0.018 |
ls | -0.017 |
ve | -0.016 |
apy | -0.015 |
iqu | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
weekend | +0.028 |
afternoon | +0.028 |
day | +0.027 |
p | +0.026 |
morning | +0.026 |
Neg logit contributions | |
istered | -0.029 |
ls | -0.028 |
ve | -0.026 |
apy | -0.024 |
uddle | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
weekend | +0.020 |
afternoon | +0.019 |
p | +0.019 |
day | +0.019 |
et | +0.018 |
Neg logit contributions | |
istered | -0.020 |
ls | -0.018 |
ve | -0.017 |
apy | -0.016 |
ashamed | -0.016 |
Token | The |
Token ID | 464 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
weekend | +0.002 |
afternoon | +0.002 |
et | +0.002 |
p | +0.002 |
day | +0.002 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
apy | -0.002 |
ashamed | -0.002 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
weekend | +0.013 |
afternoon | +0.013 |
et | +0.013 |
day | +0.013 |
p | +0.012 |
Neg logit contributions | |
istered | -0.021 |
ls | -0.020 |
ve | -0.019 |
apy | -0.018 |
ashamed | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
et | +0.053 |
afternoon | +0.050 |
weekend | +0.050 |
ah | +0.049 |
zie | +0.049 |
Neg logit contributions | |
ls | -0.043 |
istered | -0.040 |
ve | -0.037 |
apy | -0.036 |
ashamed | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
rated | +0.198 |
pole | +0.197 |
et | +0.195 |
wn | +0.195 |
ah | +0.188 |
Neg logit contributions | |
ls | -0.074 |
itt | -0.070 |
ve | -0.069 |
s | -0.068 |
shocked | -0.067 |
Token | story |
Token ID | 1621 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
et | +0.059 |
afternoon | +0.058 |
weekend | +0.058 |
p | +0.057 |
ah | +0.054 |
Neg logit contributions | |
istered | -0.105 |
ls | -0.104 |
ve | -0.098 |
ashamed | -0.093 |
apy | -0.093 |
Token | is |
Token ID | 318 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
weekend | +0.076 |
afternoon | +0.075 |
et | +0.074 |
p | +0.074 |
ah | +0.071 |
Neg logit contributions | |
ls | -0.066 |
istered | -0.066 |
ve | -0.058 |
apy | -0.056 |
ashamed | -0.055 |
Token | : |
Token ID | 25 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
weekend | +0.036 |
afternoon | +0.036 |
et | +0.036 |
p | +0.034 |
ah | +0.034 |
Neg logit contributions | |
istered | -0.044 |
ls | -0.043 |
ve | -0.039 |
apy | -0.038 |
ashamed | -0.038 |
Token | Mat |
Token ID | 6550 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
weekend | +0.030 |
afternoon | +0.030 |
et | +0.029 |
p | +0.028 |
ah | +0.028 |
Neg logit contributions | |
istered | -0.025 |
ls | -0.024 |
ve | -0.021 |
apy | -0.021 |
ashamed | -0.021 |
Token | ." |
Token ID | 526 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
istered | +0.023 |
ls | +0.022 |
ve | +0.021 |
apy | +0.020 |
ashamed | +0.020 |
Neg logit contributions | |
weekend | -0.018 |
afternoon | -0.018 |
p | -0.017 |
et | -0.017 |
day | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
istered | +0.011 |
ls | +0.011 |
ve | +0.010 |
apy | +0.009 |
ashamed | +0.009 |
Neg logit contributions | |
weekend | -0.013 |
afternoon | -0.013 |
et | -0.012 |
p | -0.012 |
day | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +6.96e-03 |
Pos logit contributions | |
weekend | +0.019 |
afternoon | +0.019 |
p | +0.018 |
day | +0.018 |
et | +0.018 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.016 |
ve | -0.014 |
apy | -0.014 |
ashamed | -0.013 |
Token | The |
Token ID | 464 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
istered | +0.000 |
ls | +0.000 |
ve | +0.000 |
apy | +0.000 |
ashamed | +0.000 |
Neg logit contributions | |
weekend | -0.000 |
afternoon | -0.000 |
et | -0.000 |
p | -0.000 |
day | -0.000 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
weekend | +0.009 |
afternoon | +0.008 |
et | +0.008 |
p | +0.008 |
day | +0.008 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.008 |
ve | -0.008 |
apy | -0.007 |
ashamed | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
et | +0.050 |
afternoon | +0.048 |
weekend | +0.048 |
p | +0.047 |
ah | +0.046 |
Neg logit contributions | |
ls | -0.044 |
istered | -0.043 |
ve | -0.039 |
ashamed | -0.038 |
apy | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
wn | +0.205 |
ah | +0.200 |
rated | +0.199 |
et | +0.197 |
pole | +0.197 |
Neg logit contributions | |
ls | -0.070 |
fighting | -0.062 |
itt | -0.061 |
shocked | -0.060 |
sorry | -0.060 |
Token | story |
Token ID | 1621 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
afternoon | +0.052 |
weekend | +0.052 |
et | +0.052 |
p | +0.050 |
ah | +0.048 |
Neg logit contributions | |
istered | -0.099 |
ls | -0.098 |
ve | -0.091 |
ashamed | -0.088 |
apy | -0.087 |
Token | is |
Token ID | 318 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
weekend | +0.069 |
afternoon | +0.069 |
et | +0.068 |
p | +0.068 |
ah | +0.065 |
Neg logit contributions | |
ls | -0.060 |
istered | -0.059 |
ve | -0.053 |
apy | -0.051 |
ashamed | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
weekend | +0.031 |
afternoon | +0.031 |
et | +0.030 |
p | +0.029 |
ah | +0.029 |
Neg logit contributions | |
istered | -0.041 |
ls | -0.040 |
ve | -0.037 |
apy | -0.036 |
ashamed | -0.035 |
Token | always |
Token ID | 1464 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
weekend | +0.025 |
et | +0.025 |
afternoon | +0.025 |
ah | +0.024 |
p | +0.023 |
Neg logit contributions | |
istered | -0.036 |
ve | -0.034 |
ls | -0.033 |
ashamed | -0.033 |
sorry | -0.033 |
Token | ." |
Token ID | 526 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
istered | +0.023 |
ls | +0.022 |
ve | +0.019 |
apy | +0.018 |
ashamed | +0.018 |
Neg logit contributions | |
weekend | -0.035 |
afternoon | -0.034 |
et | -0.033 |
p | -0.033 |
day | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
istered | +0.023 |
ve | +0.021 |
ls | +0.020 |
iqu | +0.020 |
vell | +0.020 |
Neg logit contributions | |
day | -0.015 |
weekend | -0.014 |
afternoon | -0.014 |
p | -0.014 |
morning | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
p | +0.009 |
afternoon | +0.009 |
day | +0.009 |
weekend | +0.009 |
morning | +0.008 |
Neg logit contributions | |
istered | -0.012 |
ls | -0.011 |
ve | -0.010 |
iqu | -0.010 |
ashamed | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
istered | +0.005 |
ls | +0.005 |
ve | +0.004 |
apy | +0.004 |
ashamed | +0.004 |
Neg logit contributions | |
weekend | -0.005 |
afternoon | -0.005 |
p | -0.005 |
et | -0.004 |
day | -0.004 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
weekend | +0.005 |
afternoon | +0.005 |
day | +0.004 |
p | +0.004 |
et | +0.004 |
Neg logit contributions | |
istered | -0.008 |
ls | -0.007 |
ve | -0.007 |
apy | -0.007 |
iqu | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
et | +0.047 |
weekend | +0.046 |
afternoon | +0.045 |
ah | +0.044 |
p | +0.044 |
Neg logit contributions | |
ls | -0.044 |
istered | -0.044 |
ve | -0.039 |
apy | -0.039 |
ashamed | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
wn | +0.218 |
rated | +0.216 |
pole | +0.212 |
ah | +0.205 |
et | +0.204 |
Neg logit contributions | |
ls | -0.065 |
shocked | -0.052 |
itt | -0.051 |
sorry | -0.050 |
s | -0.050 |
Token | story |
Token ID | 1621 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
weekend | +0.054 |
afternoon | +0.054 |
et | +0.053 |
p | +0.051 |
ah | +0.049 |
Neg logit contributions | |
istered | -0.102 |
ls | -0.101 |
ve | -0.094 |
apy | -0.090 |
ashamed | -0.090 |
Token | is |
Token ID | 318 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
weekend | +0.078 |
afternoon | +0.077 |
et | +0.077 |
p | +0.076 |
ah | +0.073 |
Neg logit contributions | |
ls | -0.068 |
istered | -0.067 |
ve | -0.058 |
apy | -0.057 |
ashamed | -0.056 |
Token | : |
Token ID | 25 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
weekend | +0.031 |
afternoon | +0.030 |
et | +0.029 |
p | +0.029 |
day | +0.028 |
Neg logit contributions | |
istered | -0.044 |
ls | -0.043 |
ve | -0.039 |
apy | -0.038 |
ashamed | -0.038 |
Token | We |
Token ID | 775 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
weekend | +0.027 |
afternoon | +0.026 |
et | +0.026 |
p | +0.025 |
day | +0.025 |
Neg logit contributions | |
istered | -0.025 |
ls | -0.024 |
ve | -0.022 |
apy | -0.021 |
ashamed | -0.021 |
Token | ! |
Token ID | 0 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
istered | +0.032 |
ls | +0.030 |
ve | +0.028 |
apy | +0.026 |
ashamed | +0.026 |
Neg logit contributions | |
weekend | -0.037 |
afternoon | -0.037 |
et | -0.035 |
p | -0.035 |
day | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.011 |
p | +0.011 |
day | +0.011 |
et | +0.011 |
Neg logit contributions | |
istered | -0.011 |
ls | -0.011 |
ve | -0.009 |
apy | -0.009 |
iqu | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
weekend | +0.029 |
afternoon | +0.029 |
p | +0.028 |
day | +0.028 |
et | +0.028 |
Neg logit contributions | |
istered | -0.032 |
ls | -0.030 |
ve | -0.027 |
apy | -0.026 |
ashamed | -0.026 |
Token | M |
Token ID | 44 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
weekend | +0.016 |
afternoon | +0.016 |
et | +0.015 |
day | +0.015 |
p | +0.015 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.012 |
ve | -0.011 |
apy | -0.011 |
ashamed | -0.010 |
Token | oral |
Token ID | 6864 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
weekend | +0.013 |
afternoon | +0.013 |
et | +0.012 |
p | +0.012 |
day | +0.012 |
Neg logit contributions | |
istered | -0.015 |
ls | -0.015 |
ve | -0.014 |
apy | -0.013 |
ashamed | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
et | +0.063 |
weekend | +0.061 |
afternoon | +0.061 |
ah | +0.058 |
p | +0.058 |
Neg logit contributions | |
ls | -0.057 |
istered | -0.053 |
ve | -0.053 |
ashamed | -0.049 |
oms | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
pole | +0.209 |
et | +0.205 |
ah | +0.204 |
rated | +0.202 |
wn | +0.201 |
Neg logit contributions | |
ls | -0.064 |
hugs | -0.056 |
gasped | -0.055 |
itt | -0.054 |
crying | -0.054 |
Token | story |
Token ID | 1621 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
et | +0.049 |
p | +0.048 |
weekend | +0.047 |
afternoon | +0.047 |
ah | +0.045 |
Neg logit contributions | |
ls | -0.079 |
istered | -0.077 |
ve | -0.075 |
ashamed | -0.071 |
guilty | -0.071 |
Token | : |
Token ID | 25 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
afternoon | +0.078 |
weekend | +0.077 |
et | +0.077 |
p | +0.075 |
ah | +0.072 |
Neg logit contributions | |
ls | -0.079 |
istered | -0.075 |
ve | -0.071 |
apy | -0.067 |
ashamed | -0.066 |
Token | If |
Token ID | 1002 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
afternoon | +0.038 |
et | +0.038 |
weekend | +0.038 |
ah | +0.037 |
p | +0.036 |
Neg logit contributions | |
istered | -0.032 |
ls | -0.030 |
ve | -0.028 |
apy | -0.028 |
ashamed | -0.028 |
Token | something |
Token ID | 1223 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
istered | +0.011 |
ls | +0.010 |
ve | +0.009 |
apy | +0.009 |
ashamed | +0.009 |
Neg logit contributions | |
weekend | -0.016 |
afternoon | -0.016 |
day | -0.015 |
p | -0.015 |
et | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
p | +0.012 |
et | +0.012 |
ah | +0.012 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.008 |
ve | -0.007 |
ashamed | -0.007 |
apy | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
weekend | +0.053 |
afternoon | +0.053 |
et | +0.052 |
p | +0.051 |
day | +0.050 |
Neg logit contributions | |
istered | -0.040 |
ls | -0.038 |
ve | -0.034 |
apy | -0.033 |
ashamed | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
et | +0.060 |
weekend | +0.060 |
afternoon | +0.059 |
ah | +0.058 |
p | +0.057 |
Neg logit contributions | |
ls | -0.043 |
istered | -0.042 |
ve | -0.038 |
apy | -0.036 |
ashamed | -0.035 |
Token | The |
Token ID | 464 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
et | +0.039 |
weekend | +0.038 |
est | +0.037 |
zie | +0.037 |
afternoon | +0.036 |
Neg logit contributions | |
ls | -0.024 |
istered | -0.024 |
ve | -0.023 |
apy | -0.021 |
s | -0.021 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
afternoon | +0.012 |
weekend | +0.012 |
day | +0.012 |
morning | +0.010 |
et | +0.010 |
Neg logit contributions | |
istered | -0.022 |
ls | -0.021 |
apy | -0.019 |
ve | -0.019 |
uffed | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
et | +0.060 |
weekend | +0.055 |
zie | +0.055 |
afternoon | +0.055 |
ah | +0.054 |
Neg logit contributions | |
ls | -0.043 |
istered | -0.039 |
ashamed | -0.038 |
ve | -0.037 |
apy | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
rated | +0.216 |
wn | +0.212 |
pole | +0.209 |
ah | +0.208 |
et | +0.202 |
Neg logit contributions | |
ls | -0.061 |
sorry | -0.056 |
shocked | -0.055 |
fighting | -0.055 |
itt | -0.052 |
Token | story |
Token ID | 1621 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
weekend | +0.048 |
afternoon | +0.047 |
day | +0.044 |
p | +0.044 |
et | +0.044 |
Neg logit contributions | |
istered | -0.110 |
ls | -0.105 |
ve | -0.099 |
apy | -0.097 |
ashamed | -0.094 |
Token | is |
Token ID | 318 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
weekend | +0.065 |
afternoon | +0.064 |
et | +0.063 |
p | +0.063 |
day | +0.060 |
Neg logit contributions | |
istered | -0.063 |
ls | -0.062 |
ve | -0.056 |
apy | -0.053 |
ashamed | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
weekend | +0.032 |
afternoon | +0.032 |
et | +0.030 |
p | +0.030 |
day | +0.030 |
Neg logit contributions | |
istered | -0.040 |
ls | -0.039 |
ve | -0.036 |
apy | -0.035 |
ashamed | -0.034 |
Token | sharing |
Token ID | 7373 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
afternoon | +0.027 |
weekend | +0.027 |
day | +0.027 |
p | +0.025 |
morning | +0.025 |
Neg logit contributions | |
istered | -0.036 |
ls | -0.034 |
ve | -0.032 |
iqu | -0.030 |
apy | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
p | +0.041 |
weekend | +0.041 |
et | +0.040 |
ah | +0.040 |
afternoon | +0.040 |
Neg logit contributions | |
ls | -0.037 |
istered | -0.036 |
apy | -0.033 |
ashamed | -0.032 |
shocked | -0.032 |
Token | end |
Token ID | 886 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
istered | +0.004 |
ls | +0.003 |
ve | +0.003 |
ashamed | +0.003 |
uddle | +0.003 |
Neg logit contributions | |
weekend | -0.002 |
p | -0.002 |
et | -0.002 |
afternoon | -0.002 |
ah | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
day | +0.004 |
afternoon | +0.004 |
weekend | +0.004 |
p | +0.004 |
morning | +0.004 |
Neg logit contributions | |
istered | -0.007 |
ve | -0.006 |
ls | -0.006 |
iqu | -0.006 |
oled | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
istered | +0.011 |
ls | +0.010 |
ve | +0.009 |
iqu | +0.009 |
uddle | +0.009 |
Neg logit contributions | |
weekend | -0.012 |
afternoon | -0.012 |
day | -0.011 |
et | -0.011 |
p | -0.011 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
afternoon | +0.007 |
weekend | +0.007 |
day | +0.007 |
p | +0.007 |
morning | +0.007 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.008 |
ve | -0.007 |
apy | -0.007 |
oled | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
et | +0.067 |
afternoon | +0.063 |
weekend | +0.063 |
pole | +0.061 |
ah | +0.060 |
Neg logit contributions | |
ls | -0.049 |
istered | -0.045 |
ashamed | -0.042 |
ve | -0.041 |
itt | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
ah | +0.212 |
et | +0.204 |
pole | +0.203 |
wn | +0.201 |
rated | +0.200 |
Neg logit contributions | |
fighting | -0.068 |
shocked | -0.068 |
ls | -0.067 |
ashamed | -0.066 |
sorry | -0.064 |
Token | story |
Token ID | 1621 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
weekend | +0.053 |
afternoon | +0.053 |
et | +0.052 |
p | +0.050 |
ah | +0.048 |
Neg logit contributions | |
istered | -0.103 |
ls | -0.102 |
ve | -0.095 |
apy | -0.091 |
ashamed | -0.091 |
Token | was |
Token ID | 373 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
weekend | +0.059 |
afternoon | +0.059 |
et | +0.057 |
p | +0.057 |
day | +0.055 |
Neg logit contributions | |
istered | -0.062 |
ls | -0.060 |
ve | -0.054 |
apy | -0.052 |
ashamed | -0.051 |
Token | that |
Token ID | 326 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
et | +0.041 |
afternoon | +0.039 |
ah | +0.038 |
weekend | +0.038 |
p | +0.037 |
Neg logit contributions | |
ls | -0.032 |
ashamed | -0.031 |
istered | -0.031 |
ve | -0.030 |
guilty | -0.029 |
Token | playing |
Token ID | 2712 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
weekend | +0.017 |
afternoon | +0.017 |
day | +0.016 |
p | +0.016 |
et | +0.015 |
Neg logit contributions | |
istered | -0.016 |
ls | -0.015 |
ve | -0.014 |
apy | -0.013 |
uddle | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.003 |
ve | +0.003 |
apy | +0.003 |
ashamed | +0.002 |
Neg logit contributions | |
weekend | -0.006 |
afternoon | -0.006 |
p | -0.006 |
et | -0.006 |
day | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
weekend | +0.021 |
afternoon | +0.021 |
day | +0.020 |
p | +0.020 |
et | +0.019 |
Neg logit contributions | |
istered | -0.021 |
ls | -0.020 |
ve | -0.018 |
apy | -0.017 |
iqu | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
weekend | +0.017 |
afternoon | +0.017 |
p | +0.016 |
day | +0.016 |
et | +0.016 |
Neg logit contributions | |
istered | -0.018 |
ls | -0.017 |
ve | -0.015 |
apy | -0.015 |
ashamed | -0.014 |
Token | The |
Token ID | 464 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
et | +0.004 |
weekend | +0.004 |
afternoon | +0.004 |
ah | +0.004 |
p | +0.004 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
ve | -0.003 |
apy | -0.003 |
uddle | -0.002 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
weekend | +0.005 |
afternoon | +0.005 |
et | +0.005 |
day | +0.005 |
p | +0.005 |
Neg logit contributions | |
istered | -0.010 |
ls | -0.010 |
ve | -0.009 |
apy | -0.009 |
ashamed | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
et | +0.047 |
weekend | +0.045 |
afternoon | +0.045 |
ah | +0.044 |
p | +0.043 |
Neg logit contributions | |
ls | -0.042 |
istered | -0.040 |
apy | -0.037 |
ve | -0.036 |
ashamed | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
rated | +0.197 |
pole | +0.196 |
wn | +0.195 |
et | +0.191 |
ah | +0.190 |
Neg logit contributions | |
ls | -0.072 |
itt | -0.069 |
fighting | -0.065 |
s | -0.064 |
shocked | -0.063 |
Token | story |
Token ID | 1621 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
weekend | +0.053 |
afternoon | +0.053 |
et | +0.052 |
p | +0.050 |
ah | +0.048 |
Neg logit contributions | |
istered | -0.104 |
ls | -0.102 |
ve | -0.095 |
apy | -0.092 |
ashamed | -0.091 |
Token | is |
Token ID | 318 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
weekend | +0.084 |
afternoon | +0.084 |
et | +0.082 |
p | +0.081 |
ah | +0.079 |
Neg logit contributions | |
istered | -0.079 |
ls | -0.078 |
ve | -0.069 |
apy | -0.067 |
ashamed | -0.066 |
Token | : |
Token ID | 25 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
weekend | +0.037 |
afternoon | +0.037 |
et | +0.035 |
p | +0.035 |
day | +0.034 |
Neg logit contributions | |
istered | -0.057 |
ls | -0.055 |
ve | -0.051 |
apy | -0.049 |
ashamed | -0.048 |
Token | Be |
Token ID | 1355 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
weekend | +0.032 |
afternoon | +0.031 |
et | +0.031 |
p | +0.030 |
day | +0.030 |
Neg logit contributions | |
istered | -0.031 |
ls | -0.029 |
ve | -0.027 |
apy | -0.026 |
ashamed | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
weekend | +0.007 |
afternoon | +0.007 |
et | +0.007 |
p | +0.006 |
day | +0.006 |
Neg logit contributions | |
istered | -0.006 |
ls | -0.006 |
ve | -0.005 |
apy | -0.005 |
ashamed | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
weekend | +0.028 |
afternoon | +0.027 |
day | +0.027 |
morning | +0.025 |
p | +0.024 |
Neg logit contributions | |
istered | -0.035 |
ls | -0.033 |
ve | -0.033 |
apy | -0.030 |
iqu | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
weekend | +0.026 |
afternoon | +0.026 |
day | +0.025 |
p | +0.025 |
et | +0.024 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.025 |
ve | -0.023 |
apy | -0.022 |
iqu | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
et | +0.019 |
weekend | +0.018 |
ah | +0.018 |
afternoon | +0.018 |
p | +0.018 |
Neg logit contributions | |
istered | -0.014 |
ls | -0.014 |
ve | -0.013 |
apy | -0.012 |
s | -0.012 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
et | +0.010 |
weekend | +0.010 |
p | +0.010 |
afternoon | +0.009 |
ah | +0.009 |
Neg logit contributions | |
istered | -0.016 |
ls | -0.016 |
ve | -0.015 |
ashamed | -0.014 |
guilty | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
et | +0.052 |
zie | +0.048 |
ah | +0.047 |
afternoon | +0.047 |
pole | +0.047 |
Neg logit contributions | |
ls | -0.040 |
istered | -0.036 |
ashamed | -0.034 |
apy | -0.033 |
ve | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
pole | +0.210 |
wn | +0.207 |
ah | +0.207 |
rated | +0.206 |
et | +0.204 |
Neg logit contributions | |
ls | -0.065 |
shocked | -0.055 |
fighting | -0.053 |
gasped | -0.052 |
ashamed | -0.050 |
Token | story |
Token ID | 1621 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
et | +0.056 |
weekend | +0.056 |
afternoon | +0.056 |
p | +0.053 |
ah | +0.052 |
Neg logit contributions | |
istered | -0.105 |
ls | -0.104 |
ve | -0.097 |
ashamed | -0.093 |
apy | -0.093 |
Token | is |
Token ID | 318 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
weekend | +0.074 |
afternoon | +0.074 |
et | +0.074 |
p | +0.073 |
ah | +0.071 |
Neg logit contributions | |
ls | -0.063 |
istered | -0.061 |
ve | -0.054 |
apy | -0.052 |
ashamed | -0.051 |
Token | : |
Token ID | 25 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
weekend | +0.036 |
afternoon | +0.035 |
et | +0.034 |
p | +0.034 |
day | +0.033 |
Neg logit contributions | |
istered | -0.049 |
ls | -0.047 |
ve | -0.043 |
apy | -0.042 |
ashamed | -0.041 |
Token | It |
Token ID | 632 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
weekend | +0.030 |
afternoon | +0.030 |
et | +0.030 |
p | +0.029 |
ah | +0.028 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.026 |
ve | -0.023 |
apy | -0.023 |
ashamed | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
weekend | +0.075 |
afternoon | +0.074 |
p | +0.072 |
et | +0.072 |
ah | +0.071 |
Neg logit contributions | |
istered | -0.041 |
ls | -0.038 |
ve | -0.034 |
apy | -0.031 |
uddle | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
weekend | +0.018 |
afternoon | +0.018 |
p | +0.017 |
day | +0.017 |
et | +0.017 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.016 |
ve | -0.014 |
apy | -0.014 |
ashamed | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
weekend | +0.043 |
afternoon | +0.042 |
et | +0.041 |
p | +0.041 |
day | +0.040 |
Neg logit contributions | |
istered | -0.039 |
ls | -0.037 |
ve | -0.034 |
apy | -0.033 |
ashamed | -0.032 |
Token | M |
Token ID | 44 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
et | +0.024 |
weekend | +0.023 |
afternoon | +0.023 |
ah | +0.022 |
p | +0.022 |
Neg logit contributions | |
istered | -0.023 |
ve | -0.022 |
apy | -0.021 |
ls | -0.021 |
oled | -0.019 |
Token | oral |
Token ID | 6864 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
weekend | +0.026 |
afternoon | +0.026 |
et | +0.025 |
p | +0.025 |
day | +0.025 |
Neg logit contributions | |
istered | -0.030 |
ls | -0.029 |
ve | -0.027 |
apy | -0.026 |
ashamed | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
et | +0.067 |
weekend | +0.064 |
afternoon | +0.064 |
pole | +0.063 |
ah | +0.062 |
Neg logit contributions | |
ls | -0.051 |
istered | -0.047 |
ve | -0.047 |
ashamed | -0.044 |
itt | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
pole | +0.215 |
et | +0.215 |
ah | +0.214 |
wn | +0.205 |
rated | +0.204 |
Neg logit contributions | |
crying | -0.057 |
ls | -0.054 |
hugs | -0.052 |
gasped | -0.050 |
guilty | -0.050 |
Token | story |
Token ID | 1621 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
et | +0.047 |
weekend | +0.046 |
afternoon | +0.046 |
p | +0.045 |
ah | +0.043 |
Neg logit contributions | |
ls | -0.081 |
istered | -0.081 |
ve | -0.076 |
ashamed | -0.072 |
guilty | -0.071 |
Token | : |
Token ID | 25 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
et | +0.084 |
afternoon | +0.084 |
weekend | +0.083 |
p | +0.080 |
ah | +0.079 |
Neg logit contributions | |
ls | -0.079 |
istered | -0.074 |
ve | -0.069 |
s | -0.067 |
apy | -0.066 |
Token | It |
Token ID | 632 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
et | +0.044 |
afternoon | +0.043 |
weekend | +0.043 |
ah | +0.042 |
p | +0.041 |
Neg logit contributions | |
istered | -0.035 |
ls | -0.033 |
apy | -0.032 |
ashamed | -0.031 |
ve | -0.030 |
Token | 's |
Token ID | 338 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
weekend | +0.029 |
afternoon | +0.029 |
p | +0.028 |
day | +0.028 |
et | +0.028 |
Neg logit contributions | |
istered | -0.037 |
ls | -0.035 |
ve | -0.032 |
apy | -0.032 |
uddle | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
istered | +0.005 |
ls | +0.005 |
ve | +0.004 |
ashamed | +0.004 |
apy | +0.004 |
Neg logit contributions | |
weekend | -0.008 |
afternoon | -0.008 |
et | -0.008 |
p | -0.008 |
ah | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
weekend | +0.038 |
afternoon | +0.037 |
p | +0.036 |
day | +0.036 |
et | +0.035 |
Neg logit contributions | |
istered | -0.040 |
ls | -0.037 |
ve | -0.035 |
iqu | -0.032 |
uddle | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
weekend | +0.027 |
afternoon | +0.027 |
p | +0.026 |
day | +0.026 |
et | +0.026 |
Neg logit contributions | |
istered | -0.024 |
ls | -0.023 |
ve | -0.021 |
apy | -0.020 |
ashamed | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
weekend | +0.011 |
et | +0.010 |
afternoon | +0.010 |
p | +0.010 |
ah | +0.010 |
Neg logit contributions | |
istered | -0.010 |
ls | -0.010 |
ve | -0.009 |
apy | -0.009 |
ashamed | -0.008 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.011 |
day | +0.011 |
p | +0.011 |
et | +0.011 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.012 |
ve | -0.011 |
apy | -0.011 |
iqu | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
et | +0.046 |
weekend | +0.045 |
afternoon | +0.045 |
ah | +0.043 |
p | +0.043 |
Neg logit contributions | |
ls | -0.044 |
istered | -0.043 |
ve | -0.038 |
ashamed | -0.038 |
apy | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
rated | +0.201 |
wn | +0.200 |
ah | +0.200 |
pole | +0.197 |
et | +0.197 |
Neg logit contributions | |
ls | -0.074 |
sorry | -0.063 |
shocked | -0.063 |
itt | -0.062 |
ashamed | -0.061 |
Token | story |
Token ID | 1621 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
weekend | +0.049 |
afternoon | +0.049 |
et | +0.048 |
p | +0.047 |
ah | +0.045 |
Neg logit contributions | |
istered | -0.096 |
ls | -0.095 |
ve | -0.089 |
apy | -0.085 |
ashamed | -0.085 |
Token | is |
Token ID | 318 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
weekend | +0.064 |
afternoon | +0.063 |
et | +0.062 |
p | +0.061 |
ah | +0.059 |
Neg logit contributions | |
istered | -0.062 |
ls | -0.061 |
ve | -0.054 |
apy | -0.052 |
ashamed | -0.051 |
Token | : |
Token ID | 25 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
weekend | +0.027 |
afternoon | +0.027 |
p | +0.026 |
day | +0.025 |
et | +0.025 |
Neg logit contributions | |
istered | -0.043 |
ls | -0.041 |
ve | -0.038 |
apy | -0.037 |
ashamed | -0.036 |
Token | Do |
Token ID | 2141 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
weekend | +0.021 |
afternoon | +0.021 |
et | +0.021 |
p | +0.020 |
day | +0.020 |
Neg logit contributions | |
istered | -0.023 |
ls | -0.021 |
ve | -0.020 |
apy | -0.019 |
ashamed | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
istered | +0.012 |
ls | +0.011 |
ve | +0.010 |
oled | +0.010 |
apy | +0.010 |
Neg logit contributions | |
afternoon | -0.013 |
day | -0.013 |
weekend | -0.012 |
et | -0.012 |
morning | -0.012 |
Token | my |
Token ID | 1820 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
weekend | +0.031 |
afternoon | +0.030 |
p | +0.030 |
et | +0.028 |
ah | +0.028 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.025 |
ve | -0.023 |
ashamed | -0.023 |
s | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
weekend | +0.021 |
afternoon | +0.021 |
p | +0.020 |
et | +0.020 |
ah | +0.020 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.012 |
ve | -0.011 |
ashamed | -0.010 |
guilty | -0.010 |
Token | The |
Token ID | 383 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
weekend | +0.028 |
afternoon | +0.028 |
et | +0.028 |
p | +0.027 |
ah | +0.026 |
Neg logit contributions | |
istered | -0.022 |
ls | -0.021 |
ve | -0.019 |
apy | -0.018 |
ashamed | -0.018 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
weekend | +0.006 |
afternoon | +0.006 |
et | +0.006 |
p | +0.006 |
day | +0.005 |
Neg logit contributions | |
istered | -0.015 |
ls | -0.014 |
ve | -0.013 |
apy | -0.013 |
ashamed | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
et | +0.080 |
pole | +0.073 |
zie | +0.073 |
afternoon | +0.070 |
ah | +0.070 |
Neg logit contributions | |
ls | -0.048 |
ashamed | -0.041 |
istered | -0.041 |
itt | -0.040 |
s | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
ah | +0.191 |
et | +0.191 |
pole | +0.183 |
wn | +0.179 |
age | +0.178 |
Neg logit contributions | |
ls | -0.098 |
ve | -0.081 |
sorry | -0.081 |
shocked | -0.080 |
guilty | -0.080 |
Token | story |
Token ID | 1621 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
et | +0.064 |
p | +0.061 |
afternoon | +0.060 |
weekend | +0.060 |
ah | +0.059 |
Neg logit contributions | |
ls | -0.098 |
istered | -0.096 |
ve | -0.091 |
ashamed | -0.087 |
guilty | -0.086 |
Token | is |
Token ID | 318 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
weekend | +0.057 |
afternoon | +0.056 |
et | +0.055 |
p | +0.055 |
ah | +0.053 |
Neg logit contributions | |
istered | -0.052 |
ls | -0.051 |
ve | -0.045 |
apy | -0.044 |
ashamed | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
weekend | +0.030 |
afternoon | +0.030 |
et | +0.029 |
p | +0.028 |
ah | +0.028 |
Neg logit contributions | |
istered | -0.032 |
ls | -0.031 |
ve | -0.028 |
apy | -0.028 |
ashamed | -0.027 |
Token | it |
Token ID | 340 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
weekend | +0.022 |
afternoon | +0.022 |
day | +0.022 |
p | +0.021 |
et | +0.020 |
Neg logit contributions | |
istered | -0.025 |
ls | -0.023 |
ve | -0.022 |
apy | -0.020 |
uddle | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
istered | +0.005 |
ls | +0.005 |
ve | +0.004 |
ashamed | +0.004 |
guilty | +0.004 |
Neg logit contributions | |
weekend | -0.011 |
afternoon | -0.011 |
p | -0.011 |
et | -0.011 |
ah | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
weekend | +0.023 |
afternoon | +0.023 |
et | +0.022 |
day | +0.022 |
p | +0.022 |
Neg logit contributions | |
istered | -0.023 |
ls | -0.022 |
ve | -0.020 |
apy | -0.019 |
ashamed | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
et | +0.039 |
afternoon | +0.039 |
weekend | +0.039 |
p | +0.038 |
ah | +0.037 |
Neg logit contributions | |
istered | -0.024 |
ls | -0.023 |
ve | -0.021 |
apy | -0.020 |
uddle | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
et | +0.021 |
weekend | +0.021 |
p | +0.020 |
afternoon | +0.020 |
ah | +0.020 |
Neg logit contributions | |
istered | -0.022 |
ve | -0.020 |
ls | -0.020 |
apy | -0.020 |
oled | -0.018 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
et | +0.021 |
p | +0.021 |
weekend | +0.020 |
ah | +0.020 |
afternoon | +0.020 |
Neg logit contributions | |
istered | -0.025 |
ls | -0.024 |
ve | -0.022 |
ashamed | -0.022 |
guilty | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
et | +0.066 |
zie | +0.061 |
weekend | +0.061 |
afternoon | +0.060 |
pole | +0.060 |
Neg logit contributions | |
ls | -0.042 |
ashamed | -0.036 |
istered | -0.036 |
itt | -0.036 |
s | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
ah | +0.187 |
et | +0.185 |
pole | +0.179 |
wn | +0.178 |
age | +0.176 |
Neg logit contributions | |
ls | -0.096 |
guilty | -0.081 |
ve | -0.080 |
ashamed | -0.079 |
shocked | -0.078 |
Token | story |
Token ID | 1621 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
et | +0.069 |
p | +0.065 |
afternoon | +0.063 |
weekend | +0.063 |
ah | +0.063 |
Neg logit contributions | |
ls | -0.095 |
istered | -0.091 |
ve | -0.088 |
ashamed | -0.084 |
guilty | -0.084 |
Token | is |
Token ID | 318 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
weekend | +0.061 |
afternoon | +0.061 |
et | +0.059 |
p | +0.059 |
ah | +0.057 |
Neg logit contributions | |
istered | -0.057 |
ls | -0.056 |
ve | -0.050 |
apy | -0.048 |
ashamed | -0.047 |
Token | that |
Token ID | 326 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
weekend | +0.032 |
afternoon | +0.032 |
et | +0.031 |
p | +0.031 |
day | +0.030 |
Neg logit contributions | |
istered | -0.038 |
ls | -0.037 |
ve | -0.034 |
apy | -0.033 |
ashamed | -0.033 |
Token | it |
Token ID | 340 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
afternoon | +0.025 |
weekend | +0.025 |
day | +0.025 |
p | +0.024 |
et | +0.023 |
Neg logit contributions | |
istered | -0.028 |
ls | -0.026 |
ve | -0.024 |
apy | -0.022 |
iqu | -0.022 |
Token | all |
Token ID | 477 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
afternoon | +0.002 |
weekend | +0.002 |
day | +0.002 |
et | +0.002 |
p | +0.002 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
iqu | -0.002 |
apy | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
oscope | +0.034 |
age | +0.032 |
arine | +0.032 |
nob | +0.029 |
bet | +0.028 |
Neg logit contributions | |
s | -0.079 |
ls | -0.076 |
apy | -0.072 |
dizz | -0.069 |
shocked | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
istered | +0.011 |
iqu | +0.010 |
ls | +0.009 |
apy | +0.009 |
ashamed | +0.009 |
Neg logit contributions | |
day | -0.009 |
afternoon | -0.009 |
weekend | -0.009 |
morning | -0.008 |
p | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
weekend | +0.039 |
afternoon | +0.038 |
et | +0.037 |
p | +0.037 |
ah | +0.036 |
Neg logit contributions | |
istered | -0.031 |
ls | -0.030 |
apy | -0.027 |
ve | -0.026 |
ashamed | -0.026 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
day | +0.011 |
et | +0.011 |
p | +0.011 |
Neg logit contributions | |
istered | -0.016 |
ls | -0.015 |
ve | -0.014 |
apy | -0.013 |
ashamed | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
et | +0.085 |
zie | +0.080 |
pole | +0.078 |
ah | +0.075 |
weekend | +0.073 |
Neg logit contributions | |
ls | -0.051 |
ashamed | -0.042 |
s | -0.042 |
istered | -0.042 |
itt | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
rated | +0.203 |
ah | +0.201 |
pole | +0.201 |
wn | +0.200 |
et | +0.196 |
Neg logit contributions | |
ls | -0.060 |
fighting | -0.059 |
shocked | -0.057 |
sorry | -0.053 |
guilty | -0.052 |
Token | story |
Token ID | 1621 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
et | +0.064 |
weekend | +0.062 |
afternoon | +0.062 |
p | +0.061 |
ah | +0.059 |
Neg logit contributions | |
istered | -0.110 |
ls | -0.110 |
ve | -0.102 |
ashamed | -0.099 |
guilty | -0.097 |
Token | is |
Token ID | 318 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
weekend | +0.098 |
afternoon | +0.096 |
et | +0.095 |
p | +0.095 |
ah | +0.091 |
Neg logit contributions | |
ls | -0.083 |
istered | -0.083 |
ve | -0.073 |
apy | -0.070 |
ashamed | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
weekend | +0.050 |
afternoon | +0.050 |
et | +0.049 |
p | +0.048 |
ah | +0.047 |
Neg logit contributions | |
istered | -0.061 |
ls | -0.060 |
ve | -0.055 |
apy | -0.053 |
ashamed | -0.052 |
Token | be |
Token ID | 307 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
weekend | +0.038 |
et | +0.038 |
afternoon | +0.037 |
p | +0.035 |
ah | +0.035 |
Neg logit contributions | |
istered | -0.059 |
ls | -0.055 |
ve | -0.055 |
ashamed | -0.053 |
apy | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
istered | +0.001 |
ls | +0.001 |
ve | +0.001 |
apy | +0.001 |
ashamed | +0.001 |
Neg logit contributions | |
weekend | -0.001 |
afternoon | -0.001 |
et | -0.001 |
p | -0.001 |
day | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
et | +0.025 |
weekend | +0.025 |
afternoon | +0.025 |
p | +0.025 |
ah | +0.024 |
Neg logit contributions | |
istered | -0.016 |
ls | -0.015 |
ve | -0.013 |
apy | -0.013 |
ashamed | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
et | +0.053 |
weekend | +0.052 |
afternoon | +0.052 |
p | +0.050 |
ah | +0.049 |
Neg logit contributions | |
istered | -0.038 |
ls | -0.038 |
ve | -0.036 |
apy | -0.033 |
ashamed | -0.032 |
Token | The |
Token ID | 464 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
et | +0.031 |
afternoon | +0.030 |
weekend | +0.029 |
morning | +0.027 |
rated | +0.027 |
Neg logit contributions | |
ve | -0.026 |
istered | -0.024 |
ls | -0.024 |
apy | -0.022 |
itt | -0.021 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
et | +0.015 |
p | +0.015 |
weekend | +0.014 |
afternoon | +0.014 |
ah | +0.014 |
Neg logit contributions | |
istered | -0.024 |
ls | -0.023 |
ve | -0.022 |
ashamed | -0.022 |
guilty | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
et | +0.064 |
pole | +0.057 |
afternoon | +0.057 |
zie | +0.057 |
weekend | +0.057 |
Neg logit contributions | |
ls | -0.038 |
ve | -0.034 |
ashamed | -0.032 |
oms | -0.032 |
itt | -0.032 |
Token | this |
Token ID | 428 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
rated | +0.192 |
pole | +0.192 |
ah | +0.189 |
et | +0.186 |
ny | +0.185 |
Neg logit contributions | |
itt | -0.072 |
ls | -0.070 |
ve | -0.067 |
hugs | -0.064 |
sorry | -0.064 |
Token | story |
Token ID | 1621 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
et | +0.110 |
p | +0.099 |
weekend | +0.096 |
afternoon | +0.096 |
pole | +0.095 |
Neg logit contributions | |
ls | -0.119 |
ve | -0.111 |
istered | -0.105 |
ashamed | -0.100 |
guilty | -0.099 |
Token | is |
Token ID | 318 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
weekend | +0.076 |
afternoon | +0.076 |
et | +0.075 |
p | +0.074 |
ah | +0.072 |
Neg logit contributions | |
ls | -0.064 |
istered | -0.063 |
ve | -0.057 |
apy | -0.054 |
ashamed | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
weekend | +0.035 |
afternoon | +0.035 |
et | +0.034 |
p | +0.034 |
ah | +0.033 |
Neg logit contributions | |
istered | -0.039 |
ls | -0.038 |
ve | -0.035 |
apy | -0.033 |
ashamed | -0.033 |
Token | ignorance |
Token ID | 17010 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
weekend | +0.030 |
afternoon | +0.030 |
et | +0.030 |
p | +0.029 |
ah | +0.029 |
Neg logit contributions | |
istered | -0.029 |
ls | -0.028 |
ve | -0.026 |
apy | -0.025 |
ashamed | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
weekend | +0.012 |
p | +0.012 |
afternoon | +0.012 |
ah | +0.012 |
et | +0.012 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.008 |
ve | -0.007 |
ashamed | -0.007 |
uddle | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
et | +0.023 |
weekend | +0.023 |
afternoon | +0.022 |
p | +0.022 |
ah | +0.022 |
Neg logit contributions | |
istered | -0.016 |
ls | -0.015 |
ashamed | -0.013 |
apy | -0.013 |
ve | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
weekend | +0.020 |
afternoon | +0.020 |
et | +0.020 |
p | +0.019 |
ah | +0.019 |
Neg logit contributions | |
istered | -0.018 |
ls | -0.017 |
ve | -0.016 |
apy | -0.015 |
ashamed | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
et | +0.008 |
weekend | +0.008 |
afternoon | +0.008 |
p | +0.008 |
est | +0.008 |
Neg logit contributions | |
istered | -0.006 |
ls | -0.006 |
ve | -0.006 |
apy | -0.006 |
oled | -0.005 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
weekend | +0.006 |
afternoon | +0.006 |
day | +0.006 |
et | +0.006 |
p | +0.006 |
Neg logit contributions | |
istered | -0.012 |
ls | -0.012 |
ve | -0.011 |
apy | -0.011 |
iqu | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
et | +0.053 |
afternoon | +0.050 |
weekend | +0.050 |
ah | +0.048 |
zie | +0.048 |
Neg logit contributions | |
ls | -0.044 |
istered | -0.041 |
ashamed | -0.038 |
ve | -0.038 |
apy | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
pole | +0.196 |
rated | +0.195 |
ah | +0.194 |
wn | +0.193 |
et | +0.192 |
Neg logit contributions | |
ls | -0.073 |
fighting | -0.067 |
shocked | -0.064 |
itt | -0.064 |
ashamed | -0.062 |
Token | story |
Token ID | 1621 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
weekend | +0.046 |
afternoon | +0.046 |
et | +0.044 |
p | +0.043 |
day | +0.042 |
Neg logit contributions | |
istered | -0.098 |
ls | -0.095 |
ve | -0.089 |
apy | -0.087 |
ashamed | -0.086 |
Token | is |
Token ID | 318 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
weekend | +0.063 |
afternoon | +0.062 |
et | +0.059 |
day | +0.059 |
p | +0.059 |
Neg logit contributions | |
istered | -0.069 |
ls | -0.066 |
ve | -0.061 |
apy | -0.058 |
ashamed | -0.057 |
Token | : |
Token ID | 25 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
weekend | +0.028 |
afternoon | +0.027 |
et | +0.026 |
p | +0.026 |
day | +0.026 |
Neg logit contributions | |
istered | -0.039 |
ls | -0.038 |
ve | -0.035 |
apy | -0.034 |
ashamed | -0.033 |
Token | Don |
Token ID | 2094 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
weekend | +0.029 |
afternoon | +0.029 |
et | +0.028 |
p | +0.027 |
ah | +0.027 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.026 |
ve | -0.023 |
apy | -0.023 |
ashamed | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
istered | +0.020 |
ls | +0.018 |
ve | +0.016 |
apy | +0.016 |
uddle | +0.016 |
Neg logit contributions | |
afternoon | -0.024 |
weekend | -0.024 |
day | -0.023 |
et | -0.023 |
p | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
et | +0.012 |
p | +0.012 |
day | +0.012 |
Neg logit contributions | |
istered | -0.010 |
ls | -0.010 |
ve | -0.009 |
apy | -0.009 |
ashamed | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
weekend | +0.018 |
afternoon | +0.017 |
et | +0.017 |
p | +0.017 |
day | +0.016 |
Neg logit contributions | |
istered | -0.016 |
ls | -0.015 |
ve | -0.014 |
apy | -0.013 |
ashamed | -0.013 |
Token | M |
Token ID | 44 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
weekend | +0.007 |
et | +0.007 |
afternoon | +0.007 |
p | +0.006 |
day | +0.006 |
Neg logit contributions | |
istered | -0.006 |
ve | -0.006 |
ls | -0.006 |
apy | -0.006 |
oled | -0.005 |
Token | oral |
Token ID | 6864 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
weekend | +0.019 |
afternoon | +0.019 |
et | +0.019 |
p | +0.019 |
day | +0.018 |
Neg logit contributions | |
istered | -0.018 |
ls | -0.017 |
ve | -0.016 |
apy | -0.015 |
iqu | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
et | +0.065 |
afternoon | +0.060 |
weekend | +0.060 |
ah | +0.059 |
pole | +0.059 |
Neg logit contributions | |
ls | -0.052 |
istered | -0.048 |
ve | -0.046 |
ashamed | -0.045 |
oms | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
et | +0.216 |
pole | +0.214 |
rated | +0.212 |
ah | +0.211 |
wn | +0.206 |
Neg logit contributions | |
crying | -0.052 |
hugs | -0.050 |
sorry | -0.049 |
parents | -0.046 |
ls | -0.045 |
Token | story |
Token ID | 1621 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
et | +0.051 |
p | +0.048 |
afternoon | +0.047 |
weekend | +0.046 |
ah | +0.046 |
Neg logit contributions | |
ls | -0.061 |
istered | -0.060 |
ve | -0.059 |
ashamed | -0.057 |
guilty | -0.057 |
Token | : |
Token ID | 25 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
afternoon | +0.070 |
et | +0.070 |
weekend | +0.069 |
p | +0.068 |
ah | +0.065 |
Neg logit contributions | |
ls | -0.070 |
istered | -0.067 |
ve | -0.063 |
ashamed | -0.060 |
s | -0.059 |
Token | it |
Token ID | 340 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
et | +0.034 |
afternoon | +0.034 |
weekend | +0.033 |
ah | +0.032 |
p | +0.032 |
Neg logit contributions | |
istered | -0.026 |
ls | -0.025 |
apy | -0.023 |
ve | -0.023 |
ashamed | -0.023 |
Token | is |
Token ID | 318 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
weekend | +0.016 |
afternoon | +0.016 |
p | +0.016 |
day | +0.016 |
et | +0.015 |
Neg logit contributions | |
istered | -0.022 |
ls | -0.020 |
ve | -0.019 |
apy | -0.018 |
uddle | -0.018 |
Token | be |
Token ID | 307 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
istered | +0.027 |
ls | +0.025 |
ve | +0.023 |
apy | +0.023 |
uffed | +0.023 |
Neg logit contributions | |
weekend | -0.019 |
day | -0.019 |
p | -0.019 |
afternoon | -0.019 |
et | -0.019 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
weekend | +0.029 |
afternoon | +0.028 |
ah | +0.028 |
p | +0.027 |
et | +0.027 |
Neg logit contributions | |
istered | -0.021 |
ls | -0.020 |
ashamed | -0.017 |
ve | -0.017 |
apy | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
istered | +0.021 |
ls | +0.020 |
ve | +0.018 |
apy | +0.017 |
iqu | +0.017 |
Neg logit contributions | |
weekend | -0.027 |
afternoon | -0.027 |
et | -0.026 |
day | -0.026 |
p | -0.026 |
Token | The |
Token ID | 383 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
weekend | +0.026 |
afternoon | +0.026 |
day | +0.025 |
p | +0.025 |
et | +0.025 |
Neg logit contributions | |
istered | -0.023 |
ls | -0.022 |
ve | -0.020 |
apy | -0.019 |
ashamed | -0.018 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
day | +0.003 |
et | +0.003 |
p | +0.003 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.006 |
ve | -0.006 |
apy | -0.006 |
iqu | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
et | +0.073 |
weekend | +0.068 |
pole | +0.067 |
afternoon | +0.067 |
zie | +0.067 |
Neg logit contributions | |
ls | -0.052 |
istered | -0.048 |
ashamed | -0.045 |
itt | -0.044 |
apy | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
ah | +0.187 |
et | +0.184 |
pole | +0.178 |
weekend | +0.173 |
wn | +0.171 |
Neg logit contributions | |
ls | -0.097 |
ashamed | -0.087 |
guilty | -0.085 |
sorry | -0.085 |
shocked | -0.083 |
Token | story |
Token ID | 1621 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
weekend | +0.049 |
afternoon | +0.049 |
et | +0.047 |
p | +0.046 |
day | +0.045 |
Neg logit contributions | |
istered | -0.103 |
ls | -0.100 |
ve | -0.093 |
apy | -0.090 |
ashamed | -0.089 |
Token | is |
Token ID | 318 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
weekend | +0.066 |
afternoon | +0.065 |
et | +0.064 |
p | +0.063 |
day | +0.062 |
Neg logit contributions | |
istered | -0.065 |
ls | -0.064 |
ve | -0.057 |
apy | -0.055 |
ashamed | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
weekend | +0.034 |
afternoon | +0.034 |
et | +0.033 |
p | +0.033 |
day | +0.032 |
Neg logit contributions | |
istered | -0.041 |
ls | -0.039 |
ve | -0.036 |
apy | -0.035 |
ashamed | -0.034 |
Token | always |
Token ID | 1464 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
weekend | +0.033 |
et | +0.032 |
afternoon | +0.032 |
ah | +0.031 |
p | +0.030 |
Neg logit contributions | |
istered | -0.042 |
ashamed | -0.039 |
sorry | -0.039 |
ls | -0.039 |
sincere | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
istered | +0.043 |
ls | +0.041 |
ve | +0.037 |
apy | +0.035 |
ashamed | +0.034 |
Neg logit contributions | |
weekend | -0.052 |
afternoon | -0.052 |
et | -0.050 |
p | -0.050 |
day | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
afternoon | +0.003 |
weekend | +0.003 |
et | +0.003 |
day | +0.003 |
p | +0.003 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
apy | -0.002 |
ashamed | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
et | +0.023 |
weekend | +0.023 |
afternoon | +0.023 |
p | +0.022 |
day | +0.022 |
Neg logit contributions | |
istered | -0.018 |
ls | -0.018 |
ve | -0.016 |
apy | -0.015 |
uddle | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
et | +0.006 |
weekend | +0.006 |
afternoon | +0.005 |
day | +0.005 |
p | +0.005 |
Neg logit contributions | |
istered | -0.005 |
ls | -0.005 |
ve | -0.005 |
apy | -0.004 |
s | -0.004 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
weekend | +0.005 |
et | +0.005 |
afternoon | +0.005 |
p | +0.005 |
ah | +0.004 |
Neg logit contributions | |
istered | -0.005 |
ls | -0.005 |
ve | -0.004 |
ashamed | -0.004 |
guilty | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
et | +0.062 |
pole | +0.057 |
zie | +0.057 |
afternoon | +0.056 |
weekend | +0.055 |
Neg logit contributions | |
ls | -0.039 |
oms | -0.033 |
ve | -0.033 |
itt | -0.032 |
s | -0.032 |
Token | Luna |
Token ID | 23694 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
rated | +0.190 |
ah | +0.190 |
wn | +0.188 |
et | +0.187 |
pole | +0.185 |
Neg logit contributions | |
ls | -0.080 |
itt | -0.069 |
sorry | -0.064 |
shocked | -0.063 |
crying | -0.062 |
Token | 's |
Token ID | 338 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
weekend | +0.084 |
afternoon | +0.082 |
et | +0.078 |
p | +0.077 |
hour | +0.074 |
Neg logit contributions | |
ls | -0.076 |
ve | -0.067 |
istered | -0.067 |
ashamed | -0.063 |
guilty | -0.060 |
Token | story |
Token ID | 1621 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
et | +0.063 |
p | +0.058 |
ah | +0.057 |
afternoon | +0.057 |
weekend | +0.057 |
Neg logit contributions | |
istered | -0.081 |
ls | -0.080 |
ve | -0.076 |
ashamed | -0.076 |
guilty | -0.074 |
Token | is |
Token ID | 318 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
afternoon | +0.043 |
weekend | +0.042 |
et | +0.041 |
p | +0.040 |
ah | +0.040 |
Neg logit contributions | |
ls | -0.046 |
istered | -0.046 |
ve | -0.043 |
apy | -0.039 |
ashamed | -0.039 |
Token | that |
Token ID | 326 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
et | +0.020 |
afternoon | +0.020 |
weekend | +0.020 |
ah | +0.019 |
p | +0.019 |
Neg logit contributions | |
ls | -0.023 |
istered | -0.022 |
ve | -0.022 |
ashamed | -0.021 |
guilty | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
istered | +0.017 |
ls | +0.015 |
ve | +0.014 |
apy | +0.014 |
iqu | +0.014 |
Neg logit contributions | |
afternoon | -0.021 |
weekend | -0.021 |
day | -0.020 |
et | -0.020 |
p | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
weekend | +0.035 |
afternoon | +0.035 |
day | +0.033 |
p | +0.033 |
et | +0.033 |
Neg logit contributions | |
istered | -0.031 |
ls | -0.030 |
ve | -0.027 |
apy | -0.025 |
ashamed | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
et | +0.032 |
weekend | +0.032 |
afternoon | +0.031 |
p | +0.030 |
ah | +0.030 |
Neg logit contributions | |
istered | -0.026 |
ls | -0.026 |
ve | -0.023 |
apy | -0.022 |
ashamed | -0.021 |
Token | The |
Token ID | 464 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
et | +0.016 |
est | +0.015 |
weekend | +0.015 |
p | +0.015 |
afternoon | +0.014 |
Neg logit contributions | |
istered | -0.014 |
ls | -0.014 |
ve | -0.013 |
apy | -0.013 |
itt | -0.012 |
Token | moral |
Token ID | 6573 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
weekend | +0.011 |
afternoon | +0.011 |
day | +0.011 |
et | +0.010 |
p | +0.010 |
Neg logit contributions | |
istered | -0.023 |
ls | -0.022 |
ve | -0.021 |
apy | -0.020 |
iqu | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
et | +0.054 |
weekend | +0.051 |
afternoon | +0.051 |
ah | +0.050 |
p | +0.049 |
Neg logit contributions | |
ls | -0.046 |
istered | -0.044 |
ashamed | -0.040 |
ve | -0.039 |
apy | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
rated | +0.202 |
wn | +0.198 |
ah | +0.197 |
pole | +0.196 |
et | +0.195 |
Neg logit contributions | |
ls | -0.075 |
sorry | -0.066 |
ashamed | -0.063 |
fighting | -0.063 |
shocked | -0.062 |
Token | story |
Token ID | 1621 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
weekend | +0.049 |
afternoon | +0.049 |
et | +0.048 |
p | +0.047 |
ah | +0.045 |
Neg logit contributions | |
istered | -0.095 |
ls | -0.094 |
ve | -0.088 |
apy | -0.084 |
ashamed | -0.084 |
Token | is |
Token ID | 318 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
weekend | +0.057 |
afternoon | +0.056 |
et | +0.055 |
p | +0.054 |
day | +0.053 |
Neg logit contributions | |
istered | -0.059 |
ls | -0.057 |
ve | -0.052 |
apy | -0.050 |
ashamed | -0.049 |
Token | that |
Token ID | 326 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
weekend | +0.026 |
afternoon | +0.026 |
et | +0.025 |
p | +0.025 |
day | +0.025 |
Neg logit contributions | |
istered | -0.036 |
ls | -0.035 |
ve | -0.032 |
apy | -0.031 |
ashamed | -0.030 |
Token | friendship |
Token ID | 14738 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
weekend | +0.022 |
afternoon | +0.022 |
day | +0.022 |
p | +0.020 |
morning | +0.020 |
Neg logit contributions | |
istered | -0.024 |
ls | -0.022 |
ve | -0.021 |
iqu | -0.019 |
apy | -0.019 |
Token | knew |
Token ID | 2993 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
istered | +0.016 |
ls | +0.015 |
ve | +0.013 |
apy | +0.013 |
ashamed | +0.012 |
Neg logit contributions | |
afternoon | -0.017 |
weekend | -0.017 |
et | -0.017 |
day | -0.017 |
p | -0.017 |
Token | she |
Token ID | 673 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
istered | +0.022 |
ls | +0.020 |
ve | +0.019 |
apy | +0.017 |
oled | +0.017 |
Neg logit contributions | |
weekend | -0.021 |
afternoon | -0.021 |
day | -0.021 |
et | -0.021 |
p | -0.021 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
day | +0.015 |
weekend | +0.015 |
afternoon | +0.015 |
et | +0.015 |
ah | +0.014 |
Neg logit contributions | |
istered | -0.021 |
ls | -0.019 |
apy | -0.019 |
oms | -0.018 |
ve | -0.018 |
Token | 't |
Token ID | 470 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
istered | +0.025 |
ls | +0.023 |
ve | +0.020 |
apy | +0.019 |
ashamed | +0.019 |
Neg logit contributions | |
weekend | -0.038 |
afternoon | -0.037 |
p | -0.037 |
day | -0.036 |
et | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
p | +0.032 |
afternoon | +0.032 |
weekend | +0.032 |
day | +0.032 |
et | +0.032 |
Neg logit contributions | |
istered | -0.033 |
ls | -0.031 |
ve | -0.028 |
apy | -0.028 |
iqu | -0.027 |
Token | |
Token ID | 220 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.003 |
ve | +0.002 |
apy | +0.002 |
ashamed | +0.002 |
Neg logit contributions | |
weekend | -0.003 |
afternoon | -0.003 |
et | -0.003 |
day | -0.003 |
p | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
istered | +0.091 |
ls | +0.083 |
ve | +0.076 |
apy | +0.075 |
iqu | +0.075 |
Neg logit contributions | |
weekend | -0.072 |
day | -0.070 |
afternoon | -0.069 |
p | -0.067 |
morning | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
weekend | +0.014 |
afternoon | +0.014 |
day | +0.014 |
p | +0.014 |
et | +0.013 |
Neg logit contributions | |
istered | -0.014 |
ls | -0.013 |
ve | -0.012 |
apy | -0.012 |
iqu | -0.011 |
Token | L |
Token ID | 43 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
istered | +0.002 |
ls | +0.002 |
ve | +0.002 |
apy | +0.002 |
uddle | +0.002 |
Neg logit contributions | |
weekend | -0.002 |
et | -0.002 |
afternoon | -0.002 |
p | -0.002 |
ah | -0.002 |
Token | ily |
Token ID | 813 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
weekend | +0.011 |
afternoon | +0.011 |
et | +0.010 |
p | +0.010 |
ah | +0.010 |
Neg logit contributions | |
istered | -0.010 |
ls | -0.010 |
ve | -0.009 |
uddle | -0.008 |
ashamed | -0.008 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
weekend | +0.013 |
afternoon | +0.012 |
p | +0.012 |
day | +0.011 |
et | +0.011 |
Neg logit contributions | |
ls | -0.009 |
istered | -0.008 |
ve | -0.008 |
ashamed | -0.008 |
gasped | -0.007 |
Token | switch |
Token ID | 5078 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
weekend | +0.019 |
afternoon | +0.019 |
p | +0.019 |
et | +0.019 |
ah | +0.018 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.017 |
ve | -0.016 |
apy | -0.015 |
uddle | -0.015 |
Token | ! |
Token ID | 0 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
weekend | +0.017 |
afternoon | +0.017 |
p | +0.016 |
et | +0.016 |
day | +0.016 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.012 |
ve | -0.011 |
apy | -0.010 |
ashamed | -0.010 |
Token | Let |
Token ID | 3914 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
istered | +0.006 |
ls | +0.005 |
ve | +0.005 |
apy | +0.005 |
ashamed | +0.005 |
Neg logit contributions | |
afternoon | -0.007 |
weekend | -0.007 |
et | -0.007 |
p | -0.007 |
day | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
istered | +0.015 |
ls | +0.015 |
ve | +0.013 |
apy | +0.013 |
ashamed | +0.013 |
Neg logit contributions | |
weekend | -0.012 |
afternoon | -0.012 |
et | -0.011 |
p | -0.011 |
day | -0.011 |
Token | see |
Token ID | 766 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
weekend | +0.030 |
afternoon | +0.030 |
et | +0.028 |
p | +0.028 |
day | +0.028 |
Neg logit contributions | |
istered | -0.040 |
ls | -0.038 |
ve | -0.035 |
apy | -0.034 |
ashamed | -0.034 |
Token | what |
Token ID | 644 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
weekend | +0.007 |
p | +0.007 |
et | +0.007 |
afternoon | +0.007 |
day | +0.007 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.008 |
ve | -0.007 |
apy | -0.007 |
ashamed | -0.007 |
Token | happens |
Token ID | 4325 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
istered | +0.087 |
ls | +0.078 |
ve | +0.074 |
iqu | +0.069 |
oled | +0.068 |
Neg logit contributions | |
weekend | -0.101 |
afternoon | -0.099 |
day | -0.097 |
p | -0.094 |
et | -0.094 |
Token | when |
Token ID | 618 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
istered | +0.009 |
ls | +0.008 |
ve | +0.008 |
apy | +0.007 |
ashamed | +0.007 |
Neg logit contributions | |
afternoon | -0.010 |
weekend | -0.010 |
et | -0.009 |
p | -0.009 |
day | -0.009 |
Token | we |
Token ID | 356 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
istered | +0.035 |
ls | +0.031 |
ve | +0.029 |
oled | +0.027 |
iqu | +0.027 |
Neg logit contributions | |
weekend | -0.046 |
afternoon | -0.045 |
day | -0.045 |
morning | -0.043 |
p | -0.043 |
Token | press |
Token ID | 1803 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
istered | +0.056 |
ls | +0.054 |
apy | +0.049 |
uddled | +0.049 |
uffed | +0.047 |
Neg logit contributions | |
day | -0.043 |
et | -0.042 |
weekend | -0.041 |
p | -0.041 |
afternoon | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
et | +0.003 |
day | +0.003 |
p | +0.003 |
Neg logit contributions | |
istered | -0.004 |
ls | -0.004 |
ve | -0.004 |
iqu | -0.004 |
uddle | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
istered | +0.026 |
ls | +0.024 |
ve | +0.022 |
apy | +0.021 |
uddle | +0.021 |
Neg logit contributions | |
weekend | -0.031 |
afternoon | -0.031 |
et | -0.031 |
p | -0.030 |
day | -0.029 |
Token | yellow |
Token ID | 7872 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
weekend | +0.018 |
p | +0.018 |
afternoon | +0.017 |
et | +0.017 |
ah | +0.016 |
Neg logit contributions | |
ls | -0.013 |
istered | -0.012 |
uddle | -0.011 |
ve | -0.011 |
apy | -0.011 |
Token | slide |
Token ID | 10649 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
weekend | +0.021 |
afternoon | +0.020 |
p | +0.020 |
et | +0.020 |
zie | +0.019 |
Neg logit contributions | |
ls | -0.014 |
istered | -0.014 |
uddle | -0.013 |
apy | -0.013 |
ve | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
weekend | +0.025 |
afternoon | +0.024 |
p | +0.024 |
ont | +0.024 |
ifi | +0.024 |
Neg logit contributions | |
ls | -0.010 |
s | -0.008 |
istered | -0.007 |
ve | -0.006 |
uddle | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
weekend | +0.019 |
afternoon | +0.019 |
p | +0.018 |
et | +0.018 |
day | +0.018 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.016 |
ve | -0.015 |
apy | -0.014 |
ashamed | -0.014 |
Token | thinks |
Token ID | 6834 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
weekend | +0.011 |
afternoon | +0.011 |
et | +0.011 |
day | +0.010 |
p | +0.010 |
Neg logit contributions | |
istered | -0.011 |
ls | -0.010 |
ve | -0.010 |
apy | -0.009 |
ashamed | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
istered | +0.071 |
ls | +0.067 |
ve | +0.061 |
apy | +0.058 |
ashamed | +0.057 |
Neg logit contributions | |
weekend | -0.078 |
afternoon | -0.077 |
et | -0.074 |
p | -0.074 |
day | -0.074 |
Token | is |
Token ID | 318 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
weekend | +0.014 |
afternoon | +0.014 |
p | +0.014 |
et | +0.013 |
day | +0.013 |
Neg logit contributions | |
ls | -0.012 |
istered | -0.012 |
ve | -0.011 |
uddle | -0.010 |
apy | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
weekend | +0.025 |
age | +0.025 |
ah | +0.025 |
afternoon | +0.024 |
et | +0.024 |
Neg logit contributions | |
istered | -0.018 |
ls | -0.017 |
ashamed | -0.016 |
dizz | -0.015 |
guilty | -0.015 |
Token | good |
Token ID | 922 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
istered | +0.013 |
ls | +0.012 |
uddle | +0.012 |
ve | +0.011 |
ashamed | +0.011 |
Neg logit contributions | |
p | -0.016 |
et | -0.016 |
weekend | -0.015 |
afternoon | -0.015 |
zie | -0.015 |
Token | place |
Token ID | 1295 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
p | +0.028 |
et | +0.026 |
zie | +0.025 |
weekend | +0.024 |
lyn | +0.024 |
Neg logit contributions | |
uddle | -0.031 |
dizz | -0.030 |
ls | -0.029 |
istered | -0.027 |
guilty | -0.026 |
Token | ask |
Token ID | 1265 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ls | +0.038 |
istered | +0.038 |
ve | +0.033 |
apy | +0.033 |
iqu | +0.033 |
Neg logit contributions | |
day | -0.033 |
weekend | -0.033 |
afternoon | -0.032 |
p | -0.032 |
morning | -0.031 |
Token | me |
Token ID | 502 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ah | +0.005 |
weekend | +0.005 |
afternoon | +0.005 |
et | +0.005 |
p | +0.005 |
Neg logit contributions | |
istered | -0.006 |
ls | -0.006 |
ve | -0.005 |
ashamed | -0.005 |
apy | -0.005 |
Token | before |
Token ID | 878 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
istered | +0.006 |
ls | +0.006 |
ve | +0.006 |
ashamed | +0.006 |
apy | +0.006 |
Neg logit contributions | |
afternoon | -0.004 |
weekend | -0.004 |
et | -0.004 |
ah | -0.004 |
p | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
istered | +0.021 |
ls | +0.019 |
ve | +0.018 |
iqu | +0.016 |
apy | +0.016 |
Neg logit contributions | |
weekend | -0.030 |
afternoon | -0.030 |
day | -0.029 |
p | -0.028 |
morning | -0.028 |
Token | touch |
Token ID | 3638 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
istered | +0.053 |
ls | +0.052 |
ve | +0.049 |
uffed | +0.046 |
apy | +0.046 |
Neg logit contributions | |
day | -0.036 |
p | -0.035 |
weekend | -0.035 |
afternoon | -0.035 |
morning | -0.034 |
Token | anything |
Token ID | 1997 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
istered | +0.028 |
ls | +0.026 |
ve | +0.025 |
apy | +0.024 |
ashamed | +0.023 |
Neg logit contributions | |
afternoon | -0.020 |
weekend | -0.020 |
et | -0.020 |
p | -0.020 |
day | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
istered | +0.070 |
ve | +0.062 |
oled | +0.059 |
iqu | +0.058 |
uffed | +0.058 |
Neg logit contributions | |
day | -0.077 |
afternoon | -0.076 |
weekend | -0.075 |
morning | -0.072 |
p | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
istered | +0.013 |
ls | +0.012 |
ve | +0.011 |
apy | +0.011 |
ashamed | +0.011 |
Neg logit contributions | |
weekend | -0.009 |
afternoon | -0.009 |
et | -0.009 |
day | -0.009 |
p | -0.009 |
Token | table |
Token ID | 3084 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
weekend | +0.021 |
afternoon | +0.021 |
day | +0.020 |
et | +0.020 |
p | +0.020 |
Neg logit contributions | |
istered | -0.031 |
ls | -0.029 |
ve | -0.028 |
apy | -0.027 |
iqu | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.003 |
ve | +0.003 |
ashamed | +0.002 |
apy | +0.002 |
Neg logit contributions | |
weekend | -0.005 |
afternoon | -0.005 |
p | -0.005 |
ah | -0.005 |
et | -0.005 |
Token | And |
Token ID | 843 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
et | +0.012 |
p | +0.011 |
day | +0.011 |
Neg logit contributions | |
istered | -0.011 |
ls | -0.010 |
apy | -0.009 |
ve | -0.009 |
ashamed | -0.009 |
Token | open |
Token ID | 1280 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
weekend | +0.013 |
afternoon | +0.013 |
p | +0.013 |
day | +0.013 |
et | +0.013 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.016 |
ve | -0.015 |
iqu | -0.014 |
apy | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
weekend | +0.002 |
afternoon | +0.002 |
et | +0.002 |
p | +0.002 |
day | +0.002 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
apy | -0.002 |
ashamed | -0.002 |
Token | engine |
Token ID | 3113 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
istered | +0.037 |
ls | +0.035 |
apy | +0.034 |
ve | +0.033 |
oled | +0.032 |
Neg logit contributions | |
weekend | -0.021 |
afternoon | -0.020 |
et | -0.020 |
day | -0.020 |
p | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
weekend | +0.018 |
afternoon | +0.018 |
p | +0.018 |
ah | +0.017 |
et | +0.017 |
Neg logit contributions | |
ls | -0.013 |
istered | -0.013 |
s | -0.011 |
ve | -0.011 |
ashamed | -0.011 |
Token | see |
Token ID | 766 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
istered | +0.031 |
ls | +0.030 |
ve | +0.027 |
apy | +0.027 |
ashamed | +0.026 |
Neg logit contributions | |
weekend | -0.030 |
afternoon | -0.030 |
et | -0.029 |
p | -0.028 |
ah | -0.028 |
Token | what |
Token ID | 644 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
weekend | +0.001 |
et | +0.001 |
afternoon | +0.001 |
p | +0.001 |
day | +0.001 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.001 |
ve | -0.001 |
apy | -0.001 |
uddle | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
istered | +0.086 |
ls | +0.086 |
apy | +0.076 |
ve | +0.075 |
ashamed | +0.073 |
Neg logit contributions | |
weekend | -0.091 |
afternoon | -0.090 |
et | -0.089 |
p | -0.088 |
ah | -0.085 |
Token | wrong |
Token ID | 2642 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
weekend | +0.011 |
afternoon | +0.011 |
ah | +0.010 |
p | +0.010 |
et | +0.010 |
Neg logit contributions | |
ls | -0.009 |
istered | -0.009 |
ve | -0.008 |
ashamed | -0.008 |
shocked | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
istered | +0.011 |
ls | +0.010 |
ve | +0.009 |
apy | +0.009 |
ashamed | +0.008 |
Neg logit contributions | |
weekend | -0.017 |
afternoon | -0.017 |
et | -0.017 |
p | -0.017 |
day | -0.017 |
Token | But |
Token ID | 887 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.003 |
ve | +0.003 |
apy | +0.003 |
ashamed | +0.003 |
Neg logit contributions | |
weekend | -0.003 |
afternoon | -0.003 |
et | -0.003 |
p | -0.003 |
day | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ls | +0.007 |
istered | +0.007 |
apy | +0.007 |
ashamed | +0.007 |
shocked | +0.006 |
Neg logit contributions | |
weekend | -0.008 |
afternoon | -0.008 |
p | -0.008 |
et | -0.008 |
ah | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
weekend | +0.006 |
afternoon | +0.006 |
p | +0.006 |
ah | +0.005 |
et | +0.005 |
Neg logit contributions | |
ls | -0.004 |
istered | -0.004 |
ve | -0.004 |
s | -0.004 |
apy | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
istered | +0.001 |
ls | +0.001 |
ve | +0.001 |
apy | +0.001 |
ashamed | +0.001 |
Neg logit contributions | |
weekend | -0.001 |
afternoon | -0.001 |
et | -0.001 |
p | -0.001 |
day | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
istered | +0.004 |
ls | +0.004 |
ve | +0.004 |
apy | +0.004 |
ashamed | +0.003 |
Neg logit contributions | |
weekend | -0.004 |
afternoon | -0.004 |
p | -0.004 |
et | -0.004 |
day | -0.004 |
Token | blue |
Token ID | 4171 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
weekend | +0.027 |
ah | +0.027 |
afternoon | +0.026 |
et | +0.025 |
p | +0.025 |
Neg logit contributions | |
istered | -0.024 |
ls | -0.022 |
apy | -0.021 |
ashamed | -0.021 |
shocked | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.010 |
p | +0.009 |
day | +0.009 |
et | +0.009 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.009 |
ve | -0.008 |
uddle | -0.007 |
apy | -0.007 |
Token | spark |
Token ID | 9009 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
weekend | +0.016 |
ah | +0.015 |
p | +0.015 |
et | +0.015 |
afternoon | +0.015 |
Neg logit contributions | |
istered | -0.012 |
ls | -0.012 |
apy | -0.011 |
shocked | -0.010 |
ve | -0.010 |
Token | ly |
Token ID | 306 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
istered | +0.006 |
ls | +0.006 |
ve | +0.005 |
apy | +0.005 |
ashamed | +0.005 |
Neg logit contributions | |
afternoon | -0.006 |
et | -0.006 |
weekend | -0.006 |
p | -0.006 |
day | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
istered | +0.012 |
ls | +0.012 |
ve | +0.011 |
apy | +0.010 |
ashamed | +0.010 |
Neg logit contributions | |
weekend | -0.016 |
afternoon | -0.015 |
et | -0.015 |
p | -0.015 |
ah | -0.014 |
Token | Tom |
Token ID | 4186 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
istered | +0.005 |
ls | +0.005 |
ve | +0.004 |
apy | +0.004 |
ashamed | +0.004 |
Neg logit contributions | |
weekend | -0.005 |
afternoon | -0.005 |
et | -0.005 |
p | -0.005 |
day | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
istered | +0.014 |
ls | +0.013 |
ve | +0.012 |
apy | +0.011 |
ashamed | +0.011 |
Neg logit contributions | |
weekend | -0.013 |
afternoon | -0.013 |
et | -0.013 |
p | -0.013 |
day | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
ls | +0.001 |
istered | +0.001 |
apy | +0.001 |
ashamed | +0.001 |
guilty | +0.001 |
Neg logit contributions | |
afternoon | -0.001 |
weekend | -0.001 |
et | -0.001 |
ah | -0.001 |
p | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
istered | +0.032 |
ls | +0.031 |
ve | +0.027 |
ashamed | +0.026 |
guilty | +0.025 |
Neg logit contributions | |
weekend | -0.043 |
afternoon | -0.042 |
p | -0.041 |
et | -0.041 |
ah | -0.040 |
Token | that |
Token ID | 326 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
istered | +0.038 |
ls | +0.036 |
ve | +0.033 |
apy | +0.032 |
ashamed | +0.031 |
Neg logit contributions | |
weekend | -0.035 |
afternoon | -0.035 |
et | -0.034 |
p | -0.033 |
day | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
istered | +0.018 |
ls | +0.017 |
ve | +0.016 |
apy | +0.015 |
ashamed | +0.015 |
Neg logit contributions | |
weekend | -0.018 |
afternoon | -0.017 |
et | -0.017 |
p | -0.017 |
day | -0.017 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
istered | +0.006 |
ls | +0.006 |
ve | +0.005 |
ashamed | +0.005 |
apy | +0.005 |
Neg logit contributions | |
weekend | -0.005 |
afternoon | -0.005 |
et | -0.005 |
p | -0.005 |
ah | -0.005 |
Token | would |
Token ID | 561 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
istered | +0.050 |
ls | +0.048 |
ve | +0.044 |
apy | +0.043 |
iqu | +0.041 |
Neg logit contributions | |
weekend | -0.043 |
afternoon | -0.043 |
et | -0.041 |
day | -0.041 |
p | -0.041 |
Token | help |
Token ID | 1037 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
afternoon | +0.005 |
weekend | +0.005 |
et | +0.005 |
p | +0.005 |
ah | +0.005 |
Neg logit contributions | |
istered | -0.006 |
ls | -0.006 |
ve | -0.005 |
ashamed | -0.005 |
guilty | -0.005 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
istered | +0.017 |
ls | +0.016 |
ve | +0.015 |
apy | +0.014 |
ashamed | +0.014 |
Neg logit contributions | |
weekend | -0.020 |
afternoon | -0.020 |
et | -0.019 |
p | -0.019 |
day | -0.019 |
Token | them |
Token ID | 606 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
weekend | +0.026 |
afternoon | +0.026 |
et | +0.025 |
p | +0.025 |
day | +0.025 |
Neg logit contributions | |
istered | -0.026 |
ls | -0.025 |
ve | -0.022 |
apy | -0.022 |
ashamed | -0.021 |
Token | safe |
Token ID | 3338 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
istered | +0.085 |
ls | +0.081 |
ve | +0.075 |
apy | +0.074 |
iqu | +0.072 |
Neg logit contributions | |
afternoon | -0.067 |
weekend | -0.066 |
day | -0.065 |
et | -0.063 |
p | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
et | +0.012 |
p | +0.012 |
ah | +0.012 |
Neg logit contributions | |
istered | -0.008 |
ls | -0.008 |
ve | -0.007 |
apy | -0.006 |
ashamed | -0.006 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
weekend | +0.013 |
afternoon | +0.013 |
et | +0.012 |
p | +0.012 |
day | +0.012 |
Neg logit contributions | |
istered | -0.012 |
ls | -0.011 |
ve | -0.010 |
apy | -0.010 |
ashamed | -0.009 |
Token | excited |
Token ID | 6568 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
weekend | +0.029 |
afternoon | +0.029 |
et | +0.028 |
p | +0.028 |
ah | +0.028 |
Neg logit contributions | |
istered | -0.023 |
ls | -0.022 |
ve | -0.020 |
apy | -0.020 |
ashamed | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.010 |
et | +0.010 |
ah | +0.010 |
p | +0.010 |
Neg logit contributions | |
ls | -0.006 |
istered | -0.006 |
ve | -0.006 |
ashamed | -0.005 |
guilty | -0.005 |
Token | High |
Token ID | 3334 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
p | +0.011 |
weekend | +0.011 |
et | +0.011 |
afternoon | +0.011 |
ah | +0.011 |
Neg logit contributions | |
istered | -0.010 |
ls | -0.010 |
ashamed | -0.010 |
apy | -0.009 |
guilty | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
day | +0.011 |
p | +0.011 |
et | +0.011 |
Neg logit contributions | |
ls | -0.013 |
istered | -0.012 |
ve | -0.011 |
uddle | -0.011 |
apy | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
age | +0.024 |
p | +0.024 |
pole | +0.024 |
rated | +0.023 |
ah | +0.023 |
Neg logit contributions | |
ls | -0.009 |
apy | -0.008 |
gasped | -0.008 |
dizz | -0.008 |
shocked | -0.007 |
Token | sky |
Token ID | 6766 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
istered | +0.007 |
ls | +0.007 |
uddle | +0.007 |
dizz | +0.007 |
guilty | +0.007 |
Neg logit contributions | |
p | -0.007 |
ah | -0.006 |
et | -0.006 |
ifi | -0.006 |
weekend | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
weekend | +0.009 |
p | +0.008 |
afternoon | +0.008 |
ifi | +0.008 |
et | +0.008 |
Neg logit contributions | |
ls | -0.006 |
istered | -0.005 |
apy | -0.005 |
s | -0.005 |
gasped | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
istered | +0.028 |
ls | +0.027 |
ve | +0.025 |
apy | +0.024 |
ashamed | +0.024 |
Neg logit contributions | |
weekend | -0.027 |
afternoon | -0.027 |
et | -0.026 |
p | -0.026 |
day | -0.025 |
Token | sky |
Token ID | 6766 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
istered | +0.016 |
ls | +0.016 |
ve | +0.015 |
apy | +0.014 |
ashamed | +0.014 |
Neg logit contributions | |
afternoon | -0.009 |
weekend | -0.009 |
day | -0.009 |
et | -0.009 |
p | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
p | +0.003 |
et | +0.003 |
ah | +0.003 |
Neg logit contributions | |
ls | -0.002 |
istered | -0.002 |
apy | -0.002 |
s | -0.002 |
shocked | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
age | +0.040 |
oscope | +0.040 |
ah | +0.039 |
ifi | +0.039 |
ont | +0.038 |
Neg logit contributions | |
dizz | -0.024 |
shocked | -0.023 |
istered | -0.021 |
ashamed | -0.020 |
apy | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.002 |
et | +0.002 |
p | +0.002 |
day | +0.002 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
apy | -0.002 |
ashamed | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
istered | +0.023 |
ls | +0.022 |
ve | +0.020 |
apy | +0.019 |
ashamed | +0.018 |
Neg logit contributions | |
weekend | -0.026 |
afternoon | -0.025 |
et | -0.025 |
p | -0.024 |
day | -0.024 |
Token | started |
Token ID | 2067 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
istered | +0.000 |
ls | +0.000 |
ve | +0.000 |
ashamed | +0.000 |
apy | +0.000 |
Neg logit contributions | |
weekend | -0.000 |
afternoon | -0.000 |
p | -0.000 |
et | -0.000 |
day | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
weekend | +0.034 |
et | +0.033 |
afternoon | +0.033 |
p | +0.032 |
ah | +0.032 |
Neg logit contributions | |
istered | -0.033 |
ls | -0.033 |
ve | -0.030 |
ashamed | -0.029 |
apy | -0.029 |
Token | buy |
Token ID | 2822 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
istered | +0.016 |
ls | +0.015 |
ve | +0.014 |
ashamed | +0.014 |
apy | +0.014 |
Neg logit contributions | |
weekend | -0.016 |
afternoon | -0.016 |
et | -0.016 |
p | -0.016 |
day | -0.015 |
Token | them |
Token ID | 606 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
istered | +0.011 |
ls | +0.010 |
ve | +0.009 |
apy | +0.009 |
ashamed | +0.009 |
Neg logit contributions | |
weekend | -0.010 |
afternoon | -0.010 |
et | -0.009 |
p | -0.009 |
day | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
istered | +0.046 |
ls | +0.044 |
ve | +0.040 |
apy | +0.039 |
ashamed | +0.038 |
Neg logit contributions | |
weekend | -0.043 |
afternoon | -0.043 |
et | -0.041 |
p | -0.041 |
day | -0.041 |
Token | Even |
Token ID | 3412 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
istered | +0.009 |
ls | +0.008 |
ve | +0.008 |
apy | +0.007 |
ashamed | +0.007 |
Neg logit contributions | |
weekend | -0.008 |
afternoon | -0.008 |
p | -0.008 |
et | -0.008 |
day | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
age | +0.022 |
et | +0.022 |
weekend | +0.022 |
p | +0.022 |
afternoon | +0.021 |
Neg logit contributions | |
ls | -0.028 |
istered | -0.026 |
ashamed | -0.025 |
guilty | -0.024 |
dizz | -0.024 |
Token | other |
Token ID | 584 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
istered | +0.016 |
ls | +0.015 |
ve | +0.014 |
ashamed | +0.013 |
guilty | +0.013 |
Neg logit contributions | |
weekend | -0.016 |
afternoon | -0.016 |
et | -0.016 |
p | -0.016 |
ah | -0.015 |
Token | bunny |
Token ID | 44915 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
weekend | +0.000 |
afternoon | +0.000 |
et | +0.000 |
p | +0.000 |
day | +0.000 |
Neg logit contributions | |
istered | -0.000 |
ls | -0.000 |
ve | -0.000 |
apy | -0.000 |
ashamed | -0.000 |
Token | eyes |
Token ID | 2951 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
afternoon | +0.019 |
day | +0.019 |
weekend | +0.019 |
morning | +0.018 |
p | +0.018 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.012 |
ve | -0.011 |
oled | -0.011 |
apy | -0.010 |
Token | grew |
Token ID | 6348 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
istered | +0.055 |
ls | +0.054 |
ve | +0.049 |
iqu | +0.048 |
uddle | +0.047 |
Neg logit contributions | |
afternoon | -0.043 |
et | -0.043 |
p | -0.042 |
day | -0.041 |
weekend | -0.040 |
Token | wide |
Token ID | 3094 |
Feature activation | -7.58e-03 |
Pos logit contributions | |
istered | +0.001 |
ls | +0.001 |
ve | +0.001 |
apy | +0.001 |
oled | +0.001 |
Neg logit contributions | |
afternoon | -0.001 |
et | -0.001 |
weekend | -0.001 |
p | -0.001 |
day | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
weekend | +0.000 |
afternoon | +0.000 |
p | +0.000 |
ah | +0.000 |
et | +0.000 |
Neg logit contributions | |
istered | -0.000 |
ls | -0.000 |
ve | -0.000 |
ashamed | -0.000 |
apy | -0.000 |
Token | wonder |
Token ID | 4240 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
istered | +0.009 |
ls | +0.009 |
ve | +0.009 |
uddle | +0.008 |
apy | +0.008 |
Neg logit contributions | |
afternoon | -0.009 |
weekend | -0.009 |
day | -0.009 |
et | -0.009 |
p | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
weekend | +0.033 |
afternoon | +0.032 |
et | +0.032 |
p | +0.032 |
day | +0.031 |
Neg logit contributions | |
istered | -0.024 |
ls | -0.023 |
ve | -0.021 |
apy | -0.020 |
uddle | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
weekend | +0.000 |
afternoon | +0.000 |
day | +0.000 |
morning | +0.000 |
p | +0.000 |
Neg logit contributions | |
istered | -0.000 |
ls | -0.000 |
ve | -0.000 |
apy | -0.000 |
iqu | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
weekend | +0.014 |
afternoon | +0.014 |
day | +0.014 |
p | +0.013 |
morning | +0.013 |
Neg logit contributions | |
istered | -0.016 |
ls | -0.015 |
ve | -0.013 |
iqu | -0.013 |
ashamed | -0.013 |
Token | " |
Token ID | 1 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
istered | +0.001 |
ls | +0.001 |
ve | +0.001 |
apy | +0.001 |
ashamed | +0.001 |
Neg logit contributions | |
weekend | -0.001 |
afternoon | -0.001 |
p | -0.001 |
et | -0.001 |
day | -0.001 |
Token | It |
Token ID | 1026 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
istered | +0.004 |
ls | +0.003 |
ve | +0.003 |
apy | +0.003 |
oled | +0.003 |
Neg logit contributions | |
et | -0.005 |
weekend | -0.005 |
afternoon | -0.005 |
p | -0.005 |
day | -0.005 |
Token | taste |
Token ID | 6938 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
weekend | +0.014 |
afternoon | +0.014 |
et | +0.013 |
p | +0.013 |
day | +0.013 |
Neg logit contributions | |
istered | -0.015 |
ls | -0.014 |
ve | -0.013 |
apy | -0.012 |
ashamed | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
weekend | +0.022 |
afternoon | +0.022 |
p | +0.022 |
et | +0.022 |
ah | +0.021 |
Neg logit contributions | |
istered | -0.022 |
ls | -0.021 |
apy | -0.019 |
ve | -0.019 |
ashamed | -0.018 |
Token | monster |
Token ID | 9234 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
istered | +0.001 |
ls | +0.001 |
ve | +0.000 |
apy | +0.000 |
uffed | +0.000 |
Neg logit contributions | |
day | -0.000 |
afternoon | -0.000 |
weekend | -0.000 |
morning | -0.000 |
p | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
weekend | +0.005 |
afternoon | +0.005 |
p | +0.005 |
et | +0.005 |
day | +0.005 |
Neg logit contributions | |
istered | -0.005 |
ls | -0.005 |
ve | -0.005 |
ashamed | -0.004 |
apy | -0.004 |
Token | only |
Token ID | 691 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
weekend | +0.027 |
afternoon | +0.026 |
ah | +0.026 |
et | +0.025 |
p | +0.025 |
Neg logit contributions | |
istered | -0.026 |
ls | -0.024 |
ashamed | -0.023 |
ve | -0.023 |
shocked | -0.022 |
Token | nice |
Token ID | 3621 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
weekend | +0.026 |
ah | +0.025 |
et | +0.025 |
afternoon | +0.025 |
p | +0.025 |
Neg logit contributions | |
istered | -0.024 |
ashamed | -0.022 |
guilty | -0.022 |
ls | -0.021 |
sorry | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
weekend | +0.012 |
afternoon | +0.012 |
et | +0.012 |
p | +0.012 |
ah | +0.011 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.012 |
ve | -0.011 |
ashamed | -0.011 |
apy | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
weekend | +0.019 |
afternoon | +0.018 |
et | +0.018 |
ah | +0.018 |
p | +0.018 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.016 |
ashamed | -0.015 |
ve | -0.015 |
apy | -0.014 |
Token | not |
Token ID | 407 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
weekend | +0.018 |
afternoon | +0.018 |
et | +0.017 |
ah | +0.017 |
p | +0.017 |
Neg logit contributions | |
istered | -0.020 |
ls | -0.018 |
ashamed | -0.018 |
ve | -0.017 |
shocked | -0.017 |
Token | going |
Token ID | 1016 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
weekend | +0.025 |
afternoon | +0.025 |
et | +0.024 |
p | +0.023 |
ah | +0.023 |
Neg logit contributions | |
istered | -0.020 |
ls | -0.019 |
ashamed | -0.018 |
ve | -0.018 |
guilty | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
afternoon | +0.005 |
weekend | +0.005 |
et | +0.005 |
ah | +0.005 |
p | +0.005 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.007 |
ve | -0.006 |
ashamed | -0.006 |
guilty | -0.006 |
Token | scare |
Token ID | 19437 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
istered | +0.033 |
ls | +0.031 |
ve | +0.028 |
apy | +0.027 |
ashamed | +0.027 |
Neg logit contributions | |
weekend | -0.033 |
afternoon | -0.033 |
et | -0.032 |
p | -0.031 |
day | -0.031 |
Token | Mom |
Token ID | 11254 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.003 |
ve | +0.002 |
iqu | +0.002 |
ashamed | +0.002 |
Neg logit contributions | |
weekend | -0.002 |
afternoon | -0.002 |
day | -0.002 |
p | -0.002 |
morning | -0.002 |
Token | is |
Token ID | 318 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
weekend | +0.002 |
afternoon | +0.002 |
p | +0.002 |
day | +0.002 |
et | +0.002 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
ashamed | -0.001 |
apy | -0.001 |
Token | waiting |
Token ID | 4953 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
istered | +0.016 |
ls | +0.014 |
ashamed | +0.014 |
ve | +0.014 |
shocked | +0.014 |
Neg logit contributions | |
ah | -0.017 |
weekend | -0.017 |
et | -0.017 |
afternoon | -0.017 |
p | -0.017 |
Token | for |
Token ID | 329 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
istered | +0.020 |
ls | +0.020 |
ve | +0.018 |
apy | +0.018 |
ashamed | +0.018 |
Neg logit contributions | |
weekend | -0.010 |
afternoon | -0.010 |
p | -0.010 |
et | -0.010 |
ah | -0.010 |
Token | them |
Token ID | 606 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
istered | +0.015 |
ls | +0.014 |
ve | +0.013 |
apy | +0.012 |
ashamed | +0.012 |
Neg logit contributions | |
weekend | -0.016 |
afternoon | -0.016 |
et | -0.015 |
p | -0.015 |
day | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
istered | +0.020 |
ls | +0.019 |
ve | +0.018 |
apy | +0.017 |
ashamed | +0.016 |
Neg logit contributions | |
weekend | -0.026 |
afternoon | -0.026 |
et | -0.025 |
p | -0.025 |
day | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
afternoon | +0.006 |
weekend | +0.006 |
day | +0.006 |
morning | +0.006 |
et | +0.006 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.009 |
ve | -0.008 |
uddle | -0.008 |
iqu | -0.008 |
Token | big |
Token ID | 1263 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
istered | +0.011 |
ls | +0.010 |
ve | +0.009 |
uffed | +0.009 |
iqu | +0.009 |
Neg logit contributions | |
weekend | -0.010 |
day | -0.010 |
afternoon | -0.010 |
morning | -0.010 |
ah | -0.009 |
Token | smile |
Token ID | 8212 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
weekend | +0.031 |
afternoon | +0.031 |
day | +0.030 |
et | +0.030 |
p | +0.029 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.025 |
ve | -0.023 |
apy | -0.022 |
iqu | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
weekend | +0.034 |
afternoon | +0.034 |
p | +0.033 |
et | +0.033 |
zie | +0.032 |
Neg logit contributions | |
istered | -0.016 |
ls | -0.016 |
ve | -0.013 |
apy | -0.012 |
oled | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
weekend | +0.013 |
afternoon | +0.012 |
morning | +0.012 |
day | +0.012 |
Tuesday | +0.011 |
Neg logit contributions | |
istered | -0.019 |
ve | -0.018 |
ls | -0.018 |
vell | -0.017 |
iqu | -0.017 |
Token | milk |
Token ID | 7545 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
weekend | +0.001 |
afternoon | +0.001 |
et | +0.001 |
p | +0.001 |
day | +0.001 |
Neg logit contributions | |
istered | -0.001 |
ls | -0.001 |
ve | -0.001 |
apy | -0.001 |
ashamed | -0.001 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
afternoon | +0.005 |
p | +0.005 |
weekend | +0.005 |
et | +0.005 |
ah | +0.005 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
uddle | -0.003 |
ve | -0.003 |
s | -0.003 |
Token | His |
Token ID | 2399 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
istered | +0.023 |
ls | +0.023 |
apy | +0.022 |
ashamed | +0.021 |
ve | +0.020 |
Neg logit contributions | |
et | -0.037 |
weekend | -0.037 |
p | -0.036 |
afternoon | -0.036 |
ah | -0.035 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
day | +0.009 |
weekend | +0.008 |
afternoon | +0.008 |
morning | +0.008 |
man | +0.008 |
Neg logit contributions | |
istered | -0.007 |
ls | -0.007 |
ve | -0.006 |
oled | -0.006 |
oms | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
istered | +0.010 |
ls | +0.010 |
ve | +0.009 |
apy | +0.008 |
ashamed | +0.008 |
Neg logit contributions | |
weekend | -0.016 |
afternoon | -0.016 |
p | -0.015 |
et | -0.015 |
day | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
weekend | +0.013 |
day | +0.012 |
afternoon | +0.012 |
et | +0.012 |
p | +0.012 |
Neg logit contributions | |
istered | -0.019 |
ls | -0.018 |
iqu | -0.017 |
ve | -0.016 |
uddle | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
weekend | +0.046 |
afternoon | +0.045 |
p | +0.044 |
day | +0.044 |
et | +0.043 |
Neg logit contributions | |
istered | -0.048 |
ls | -0.046 |
ve | -0.041 |
iqu | -0.039 |
apy | -0.039 |
Token | Sure |
Token ID | 19457 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
et | +0.002 |
afternoon | +0.002 |
weekend | +0.002 |
p | +0.002 |
zie | +0.002 |
Neg logit contributions | |
istered | -0.001 |
ls | -0.001 |
ve | -0.001 |
apy | -0.001 |
s | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
weekend | +0.034 |
afternoon | +0.034 |
p | +0.033 |
et | +0.032 |
day | +0.031 |
Neg logit contributions | |
istered | -0.026 |
ls | -0.026 |
ve | -0.024 |
ashamed | -0.022 |
apy | -0.022 |
Token | let |
Token ID | 1309 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
afternoon | +0.052 |
weekend | +0.052 |
et | +0.051 |
p | +0.050 |
ah | +0.050 |
Neg logit contributions | |
istered | -0.035 |
ls | -0.034 |
ve | -0.030 |
apy | -0.029 |
ashamed | -0.028 |
Token | me |
Token ID | 502 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
afternoon | +0.003 |
weekend | +0.003 |
day | +0.003 |
et | +0.003 |
p | +0.003 |
Neg logit contributions | |
istered | -0.005 |
ls | -0.005 |
apy | -0.004 |
ve | -0.004 |
iqu | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
weekend | +0.027 |
afternoon | +0.027 |
et | +0.026 |
p | +0.026 |
day | +0.025 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.027 |
ve | -0.024 |
apy | -0.023 |
ashamed | -0.023 |
Token | sharing |
Token ID | 7373 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
et | +0.036 |
ah | +0.035 |
p | +0.035 |
weekend | +0.035 |
afternoon | +0.034 |
Neg logit contributions | |
ls | -0.031 |
istered | -0.030 |
ashamed | -0.029 |
guilty | -0.028 |
apy | -0.028 |
Token | is |
Token ID | 318 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
weekend | +0.019 |
ah | +0.018 |
p | +0.018 |
afternoon | +0.018 |
et | +0.018 |
Neg logit contributions | |
ls | -0.015 |
istered | -0.014 |
ashamed | -0.014 |
guilty | -0.013 |
apy | -0.013 |
Token | better |
Token ID | 1365 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
et | +0.036 |
weekend | +0.035 |
afternoon | +0.034 |
ah | +0.034 |
p | +0.033 |
Neg logit contributions | |
istered | -0.034 |
ashamed | -0.033 |
ls | -0.033 |
guilty | -0.032 |
sorry | -0.031 |
Token | than |
Token ID | 621 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
weekend | +0.027 |
et | +0.026 |
afternoon | +0.025 |
p | +0.025 |
ah | +0.025 |
Neg logit contributions | |
istered | -0.041 |
ls | -0.041 |
ve | -0.038 |
ashamed | -0.036 |
guilty | -0.035 |
Token | keeping |
Token ID | 5291 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
afternoon | +0.043 |
weekend | +0.043 |
et | +0.043 |
ah | +0.042 |
p | +0.041 |
Neg logit contributions | |
istered | -0.046 |
ls | -0.045 |
ve | -0.042 |
ashamed | -0.041 |
guilty | -0.040 |
Token | everything |
Token ID | 2279 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
afternoon | +0.023 |
weekend | +0.023 |
et | +0.023 |
p | +0.022 |
day | +0.022 |
Neg logit contributions | |
istered | -0.025 |
ls | -0.024 |
ve | -0.022 |
apy | -0.021 |
ashamed | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
istered | +0.060 |
ls | +0.055 |
ve | +0.053 |
apy | +0.050 |
oled | +0.050 |
Neg logit contributions | |
afternoon | -0.054 |
weekend | -0.054 |
day | -0.053 |
et | -0.052 |
p | -0.051 |
Token | himself |
Token ID | 2241 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.002 |
ve | +0.002 |
apy | +0.002 |
ashamed | +0.002 |
Neg logit contributions | |
weekend | -0.002 |
afternoon | -0.002 |
et | -0.002 |
p | -0.002 |
day | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
istered | +0.031 |
ls | +0.030 |
ve | +0.026 |
apy | +0.025 |
ashamed | +0.024 |
Neg logit contributions | |
weekend | -0.046 |
afternoon | -0.046 |
et | -0.045 |
p | -0.045 |
day | -0.044 |
Token | He |
Token ID | 679 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
weekend | +0.011 |
afternoon | +0.011 |
et | +0.011 |
p | +0.011 |
ah | +0.011 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.012 |
ashamed | -0.011 |
ve | -0.011 |
apy | -0.011 |
Token | full |
Token ID | 1336 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
istered | +0.052 |
ls | +0.045 |
ve | +0.044 |
oled | +0.043 |
apy | +0.042 |
Neg logit contributions | |
weekend | -0.047 |
afternoon | -0.046 |
day | -0.046 |
p | -0.044 |
morning | -0.043 |
Token | of |
Token ID | 286 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
istered | +0.003 |
ls | +0.003 |
ve | +0.002 |
apy | +0.002 |
ashamed | +0.002 |
Neg logit contributions | |
weekend | -0.003 |
afternoon | -0.003 |
et | -0.003 |
p | -0.003 |
ah | -0.003 |
Token | water |
Token ID | 1660 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
weekend | +0.005 |
afternoon | +0.004 |
p | +0.004 |
et | +0.004 |
day | +0.004 |
Neg logit contributions | |
istered | -0.005 |
ls | -0.005 |
ve | -0.004 |
apy | -0.004 |
uddle | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.009 |
et | +0.009 |
p | +0.009 |
day | +0.009 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.008 |
ve | -0.007 |
apy | -0.007 |
ashamed | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
weekend | +0.001 |
afternoon | +0.001 |
et | +0.001 |
p | +0.001 |
day | +0.001 |
Neg logit contributions | |
istered | -0.001 |
ls | -0.001 |
ve | -0.001 |
apy | -0.001 |
ashamed | -0.000 |
Token | need |
Token ID | 761 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
istered | +0.043 |
ls | +0.040 |
ve | +0.037 |
apy | +0.036 |
oled | +0.035 |
Neg logit contributions | |
weekend | -0.051 |
afternoon | -0.051 |
day | -0.051 |
et | -0.050 |
p | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
weekend | +0.009 |
afternoon | +0.008 |
p | +0.008 |
day | +0.008 |
et | +0.008 |
Neg logit contributions | |
istered | -0.013 |
ls | -0.013 |
ve | -0.012 |
apy | -0.011 |
ashamed | -0.011 |
Token | let |
Token ID | 1309 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
weekend | +0.002 |
afternoon | +0.002 |
et | +0.002 |
p | +0.002 |
day | +0.002 |
Neg logit contributions | |
istered | -0.002 |
ls | -0.002 |
ve | -0.002 |
apy | -0.002 |
ashamed | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
istered | +0.007 |
ls | +0.006 |
ve | +0.006 |
apy | +0.006 |
ashamed | +0.006 |
Neg logit contributions | |
weekend | -0.006 |
afternoon | -0.006 |
et | -0.006 |
p | -0.006 |
day | -0.006 |
Token | out |
Token ID | 503 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
istered | +0.015 |
ls | +0.014 |
ve | +0.013 |
apy | +0.013 |
ashamed | +0.012 |
Neg logit contributions | |
weekend | -0.011 |
afternoon | -0.011 |
et | -0.011 |
p | -0.011 |
day | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
istered | +0.018 |
ls | +0.017 |
ve | +0.015 |
apy | +0.014 |
ashamed | +0.014 |
Neg logit contributions | |
weekend | -0.023 |
afternoon | -0.023 |
et | -0.022 |
p | -0.022 |
day | -0.021 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
afternoon | +0.001 |
weekend | +0.001 |
et | +0.001 |
day | +0.001 |
p | +0.001 |
Neg logit contributions | |
istered | -0.001 |
ls | -0.001 |
ve | -0.001 |
apy | -0.001 |
iqu | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
et | +0.002 |
p | +0.002 |
ah | +0.002 |
Neg logit contributions | |
istered | -0.003 |
ls | -0.003 |
ve | -0.002 |
apy | -0.002 |
ashamed | -0.002 |
Token | earth |
Token ID | 4534 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
istered | +0.034 |
ls | +0.032 |
ve | +0.030 |
apy | +0.029 |
oled | +0.028 |
Neg logit contributions | |
afternoon | -0.026 |
weekend | -0.026 |
day | -0.025 |
et | -0.024 |
morning | -0.023 |
Token | too |
Token ID | 1165 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
istered | +0.002 |
ls | +0.002 |
ve | +0.002 |
apy | +0.002 |
ashamed | +0.002 |
Neg logit contributions | |
weekend | -0.003 |
afternoon | -0.003 |
p | -0.003 |
et | -0.003 |
ah | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
istered | +0.017 |
ls | +0.016 |
uffed | +0.016 |
iqu | +0.015 |
uddle | +0.015 |
Neg logit contributions | |
day | -0.015 |
afternoon | -0.015 |
weekend | -0.014 |
morning | -0.014 |
et | -0.013 |
Token | From |
Token ID | 3574 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
weekend | +0.014 |
afternoon | +0.014 |
day | +0.013 |
et | +0.013 |
p | +0.013 |
Neg logit contributions | |
istered | -0.014 |
ls | -0.013 |
ve | -0.012 |
apy | -0.011 |
iqu | -0.011 |
Token | that |
Token ID | 326 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
weekend | +0.090 |
afternoon | +0.088 |
et | +0.087 |
ah | +0.087 |
p | +0.087 |
Neg logit contributions | |
ls | -0.079 |
istered | -0.073 |
ve | -0.067 |
ashamed | -0.064 |
apy | -0.064 |
Token | day |
Token ID | 1110 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
p | +0.061 |
et | +0.059 |
pole | +0.051 |
bet | +0.049 |
cker | +0.047 |
Neg logit contributions | |
ls | -0.129 |
ve | -0.128 |
guilty | -0.126 |
s | -0.126 |
dizz | -0.121 |
Token | on |
Token ID | 319 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
weekend | +0.037 |
afternoon | +0.036 |
et | +0.036 |
p | +0.036 |
ah | +0.034 |
Neg logit contributions | |
istered | -0.040 |
ls | -0.039 |
ve | -0.036 |
apy | -0.035 |
ashamed | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
weekend | +0.053 |
afternoon | +0.052 |
p | +0.051 |
et | +0.051 |
ah | +0.049 |
Neg logit contributions | |
istered | -0.051 |
ls | -0.050 |
ve | -0.045 |
apy | -0.043 |
ashamed | -0.042 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
weekend | +0.037 |
afternoon | +0.036 |
et | +0.036 |
p | +0.036 |
ah | +0.035 |
Neg logit contributions | |
istered | -0.033 |
ls | -0.031 |
ve | -0.028 |
apy | -0.027 |
ashamed | -0.027 |
Token | they |
Token ID | 484 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
weekend | +0.003 |
afternoon | +0.003 |
et | +0.003 |
p | +0.003 |
ah | +0.003 |
Neg logit contributions | |
ls | -0.003 |
istered | -0.003 |
apy | -0.002 |
ashamed | -0.002 |
ve | -0.002 |
Token | became |
Token ID | 2627 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
istered | +0.017 |
ls | +0.016 |
ve | +0.015 |
apy | +0.015 |
iqu | +0.015 |
Neg logit contributions | |
afternoon | -0.015 |
weekend | -0.015 |
et | -0.014 |
day | -0.014 |
p | -0.014 |
Token | good |
Token ID | 922 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
weekend | +0.036 |
afternoon | +0.035 |
et | +0.034 |
p | +0.034 |
day | +0.034 |
Neg logit contributions | |
istered | -0.028 |
ls | -0.026 |
ve | -0.024 |
apy | -0.022 |
ashamed | -0.022 |
Token | friends |
Token ID | 2460 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
afternoon | +0.013 |
day | +0.013 |
weekend | +0.013 |
p | +0.012 |
morning | +0.012 |
Neg logit contributions | |
istered | -0.011 |
ls | -0.010 |
apy | -0.009 |
ve | -0.009 |
iqu | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
afternoon | +0.018 |
day | +0.017 |
weekend | +0.017 |
et | +0.017 |
p | +0.017 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.015 |
apy | -0.014 |
iqu | -0.014 |
ve | -0.014 |
Token | From |
Token ID | 3574 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
weekend | +0.036 |
afternoon | +0.035 |
et | +0.034 |
p | +0.034 |
day | +0.034 |
Neg logit contributions | |
istered | -0.031 |
ls | -0.030 |
ve | -0.027 |
apy | -0.026 |
ashamed | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
weekend | +0.119 |
ah | +0.114 |
afternoon | +0.112 |
et | +0.111 |
p | +0.109 |
Neg logit contributions | |
ls | -0.077 |
istered | -0.059 |
ashamed | -0.058 |
shocked | -0.056 |
ve | -0.056 |
Token | day |
Token ID | 1110 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
p | +0.067 |
et | +0.066 |
wn | +0.063 |
icle | +0.062 |
round | +0.061 |
Neg logit contributions | |
ls | -0.128 |
s | -0.126 |
sorry | -0.126 |
guilty | -0.126 |
ve | -0.123 |
Token | on |
Token ID | 319 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
weekend | +0.025 |
afternoon | +0.024 |
et | +0.024 |
p | +0.023 |
day | +0.023 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.026 |
ve | -0.024 |
apy | -0.024 |
ashamed | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
p | +0.067 |
weekend | +0.067 |
et | +0.066 |
ah | +0.064 |
afternoon | +0.064 |
Neg logit contributions | |
ls | -0.050 |
istered | -0.046 |
apy | -0.043 |
ve | -0.041 |
ashamed | -0.038 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
weekend | +0.041 |
et | +0.040 |
p | +0.039 |
afternoon | +0.039 |
ah | +0.038 |
Neg logit contributions | |
ls | -0.034 |
istered | -0.033 |
apy | -0.030 |
ve | -0.029 |
ashamed | -0.028 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
ls | +0.038 |
istered | +0.038 |
ve | +0.033 |
iqu | +0.032 |
uddle | +0.032 |
Neg logit contributions | |
afternoon | -0.040 |
day | -0.040 |
weekend | -0.040 |
p | -0.038 |
morning | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
weekend | +0.010 |
afternoon | +0.010 |
et | +0.010 |
p | +0.010 |
day | +0.009 |
Neg logit contributions | |
istered | -0.009 |
ls | -0.009 |
ve | -0.008 |
apy | -0.008 |
ashamed | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
weekend | +0.023 |
afternoon | +0.023 |
et | +0.021 |
p | +0.021 |
day | +0.021 |
Neg logit contributions | |
istered | -0.031 |
ls | -0.030 |
ve | -0.027 |
apy | -0.026 |
ashamed | -0.026 |
Token | learned |
Token ID | 4499 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
weekend | +0.026 |
afternoon | +0.026 |
et | +0.025 |
p | +0.025 |
day | +0.025 |
Neg logit contributions | |
istered | -0.023 |
ls | -0.022 |
ve | -0.020 |
apy | -0.019 |
ashamed | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
et | +0.102 |
afternoon | +0.102 |
weekend | +0.102 |
ah | +0.099 |
p | +0.094 |
Neg logit contributions | |
ls | -0.082 |
istered | -0.079 |
ashamed | -0.075 |
ve | -0.070 |
apy | -0.070 |
Token | valuable |
Token ID | 8119 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
weekend | +0.072 |
afternoon | +0.072 |
et | +0.071 |
p | +0.069 |
day | +0.066 |
Neg logit contributions | |
istered | -0.097 |
ls | -0.093 |
ve | -0.087 |
apy | -0.084 |
ashamed | -0.083 |
Token | lesson |
Token ID | 11483 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
et | +0.116 |
afternoon | +0.105 |
zie | +0.102 |
p | +0.101 |
weekend | +0.100 |
Neg logit contributions | |
ls | -0.132 |
ve | -0.128 |
istered | -0.122 |
ashamed | -0.113 |
uddle | -0.113 |
Token | about |
Token ID | 546 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
afternoon | +0.110 |
weekend | +0.109 |
et | +0.106 |
ah | +0.104 |
p | +0.103 |
Neg logit contributions | |
ls | -0.075 |
ve | -0.068 |
istered | -0.067 |
ashamed | -0.060 |
s | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
weekend | +0.059 |
afternoon | +0.058 |
ah | +0.057 |
et | +0.056 |
p | +0.055 |
Neg logit contributions | |
istered | -0.059 |
ls | -0.058 |
ve | -0.054 |
ashamed | -0.053 |
apy | -0.053 |
Token | power |
Token ID | 1176 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
weekend | +0.007 |
afternoon | +0.007 |
p | +0.007 |
et | +0.007 |
ah | +0.007 |
Neg logit contributions | |
istered | -0.011 |
ls | -0.010 |
ve | -0.010 |
ashamed | -0.009 |
apy | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
weekend | +0.049 |
afternoon | +0.048 |
p | +0.048 |
et | +0.047 |
ah | +0.047 |
Neg logit contributions | |
ls | -0.047 |
istered | -0.045 |
ve | -0.041 |
apy | -0.041 |
ashamed | -0.040 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
istered | +0.008 |
ls | +0.008 |
apy | +0.007 |
ve | +0.007 |
ashamed | +0.007 |
Neg logit contributions | |
weekend | -0.008 |
afternoon | -0.008 |
et | -0.008 |
p | -0.008 |
ah | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
weekend | +0.018 |
afternoon | +0.018 |
et | +0.017 |
p | +0.017 |
ah | +0.017 |
Neg logit contributions | |
istered | -0.017 |
ls | -0.017 |
ve | -0.016 |
apy | -0.016 |
ashamed | -0.015 |
Token | view |
Token ID | 1570 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
weekend | +0.017 |
et | +0.016 |
p | +0.016 |
ah | +0.016 |
afternoon | +0.016 |
Neg logit contributions | |
istered | -0.020 |
ls | -0.020 |
ve | -0.019 |
uddle | -0.018 |
guilty | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
weekend | +0.033 |
afternoon | +0.032 |
p | +0.032 |
ah | +0.032 |
et | +0.032 |
Neg logit contributions | |
ls | -0.022 |
istered | -0.020 |
ve | -0.018 |
apy | -0.017 |
s | -0.017 |
Token | From |
Token ID | 3574 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
istered | +0.001 |
ls | +0.001 |
ve | +0.001 |
apy | +0.001 |
iqu | +0.001 |
Neg logit contributions | |
weekend | -0.001 |
afternoon | -0.001 |
day | -0.001 |
et | -0.001 |
morning | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
weekend | +0.071 |
afternoon | +0.068 |
p | +0.068 |
ah | +0.068 |
et | +0.067 |
Neg logit contributions | |
ls | -0.092 |
istered | -0.084 |
ve | -0.080 |
apy | -0.078 |
ashamed | -0.077 |
Token | day |
Token ID | 1110 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
p | +0.044 |
et | +0.037 |
age | +0.034 |
bet | +0.033 |
wn | +0.033 |
Neg logit contributions | |
ls | -0.116 |
ve | -0.115 |
guilty | -0.112 |
s | -0.112 |
apy | -0.109 |
Token | forward |
Token ID | 2651 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
afternoon | +0.011 |
weekend | +0.011 |
day | +0.011 |
et | +0.011 |
p | +0.010 |
Neg logit contributions | |
istered | -0.014 |
ls | -0.013 |
ve | -0.012 |
apy | -0.012 |
iqu | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
weekend | +0.064 |
afternoon | +0.063 |
p | +0.063 |
et | +0.062 |
ah | +0.060 |
Neg logit contributions | |
ls | -0.054 |
istered | -0.052 |
ve | -0.047 |
apy | -0.045 |
ashamed | -0.045 |
Token | they |
Token ID | 484 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
weekend | +0.021 |
afternoon | +0.021 |
day | +0.020 |
et | +0.019 |
p | +0.019 |
Neg logit contributions | |
istered | -0.025 |
ls | -0.023 |
ve | -0.022 |
apy | -0.021 |
iqu | -0.020 |
Token | became |
Token ID | 2627 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
istered | +0.009 |
ls | +0.009 |
ve | +0.008 |
apy | +0.008 |
ashamed | +0.008 |
Neg logit contributions | |
weekend | -0.007 |
afternoon | -0.007 |
p | -0.007 |
et | -0.007 |
day | -0.007 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
istered | +0.010 |
ls | +0.010 |
ve | +0.009 |
apy | +0.008 |
oled | +0.008 |
Neg logit contributions | |
day | -0.013 |
afternoon | -0.013 |
weekend | -0.013 |
morning | -0.012 |
et | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
weekend | +0.035 |
afternoon | +0.034 |
et | +0.034 |
p | +0.034 |
ah | +0.033 |
Neg logit contributions | |
istered | -0.030 |
ls | -0.030 |
ve | -0.027 |
s | -0.026 |
ashamed | -0.025 |
Token | adding |
Token ID | 4375 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ah | +0.042 |
weekend | +0.042 |
afternoon | +0.041 |
et | +0.041 |
p | +0.040 |
Neg logit contributions | |
istered | -0.039 |
ls | -0.036 |
ve | -0.035 |
ashamed | -0.034 |
apy | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
weekend | +0.044 |
afternoon | +0.043 |
p | +0.042 |
et | +0.042 |
ah | +0.041 |
Neg logit contributions | |
istered | -0.050 |
ls | -0.049 |
ve | -0.044 |
apy | -0.043 |
ashamed | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
weekend | +0.028 |
afternoon | +0.027 |
ah | +0.027 |
et | +0.026 |
p | +0.026 |
Neg logit contributions | |
ls | -0.027 |
istered | -0.026 |
ve | -0.024 |
ashamed | -0.022 |
s | -0.022 |
Token | From |
Token ID | 3574 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
afternoon | +0.016 |
weekend | +0.016 |
day | +0.016 |
morning | +0.015 |
et | +0.014 |
Neg logit contributions | |
istered | -0.020 |
ls | -0.019 |
ve | -0.017 |
iqu | -0.016 |
apy | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
weekend | +0.085 |
afternoon | +0.083 |
et | +0.082 |
p | +0.082 |
ah | +0.081 |
Neg logit contributions | |
ls | -0.082 |
istered | -0.079 |
ve | -0.071 |
apy | -0.068 |
ashamed | -0.068 |
Token | day |
Token ID | 1110 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
et | +0.055 |
p | +0.054 |
pole | +0.049 |
bet | +0.044 |
ifi | +0.043 |
Neg logit contributions | |
ve | -0.123 |
s | -0.121 |
guilty | -0.120 |
ls | -0.120 |
dizz | -0.115 |
Token | on |
Token ID | 319 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
afternoon | +0.029 |
weekend | +0.029 |
day | +0.027 |
et | +0.027 |
p | +0.027 |
Neg logit contributions | |
istered | -0.040 |
ls | -0.038 |
ve | -0.035 |
iqu | -0.034 |
apy | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
afternoon | +0.043 |
weekend | +0.043 |
day | +0.042 |
et | +0.041 |
p | +0.040 |
Neg logit contributions | |
istered | -0.052 |
ls | -0.048 |
ve | -0.045 |
apy | -0.043 |
ashamed | -0.043 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
weekend | +0.032 |
afternoon | +0.032 |
day | +0.031 |
et | +0.030 |
p | +0.030 |
Neg logit contributions | |
istered | -0.027 |
ls | -0.025 |
ve | -0.023 |
apy | -0.022 |
ashamed | -0.021 |