Token | had |
Token ID | 550 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
packs | +0.091 |
uth | +0.087 |
eth | +0.086 |
aj | +0.083 |
majesty | +0.081 |
Neg logit contributions | |
ting | -0.070 |
course | -0.056 |
neath | -0.052 |
pped | -0.051 |
That | -0.050 |
Token | an |
Token ID | 281 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
ting | +0.113 |
course | +0.087 |
neath | +0.082 |
pped | +0.079 |
That | +0.076 |
Neg logit contributions | |
packs | -0.155 |
uth | -0.149 |
eth | -0.146 |
aj | -0.140 |
patients | -0.135 |
Token | idea |
Token ID | 2126 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
ting | +0.003 |
course | +0.003 |
neath | +0.003 |
pped | +0.003 |
That | +0.003 |
Neg logit contributions | |
packs | -0.001 |
uth | -0.001 |
eth | -0.001 |
aj | -0.001 |
majesty | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
packs | +0.043 |
uth | +0.040 |
eth | +0.039 |
ies | +0.035 |
aj | +0.035 |
Neg logit contributions | |
ting | -0.072 |
neath | -0.061 |
course | -0.060 |
pped | -0.059 |
That | -0.057 |
Token | " |
Token ID | 366 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
ting | +0.031 |
That | +0.021 |
You | +0.021 |
Good | +0.020 |
course | +0.020 |
Neg logit contributions | |
packs | -0.055 |
uth | -0.053 |
ies | -0.050 |
aj | -0.050 |
eth | -0.050 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ting | +0.091 |
course | +0.065 |
neath | +0.057 |
pped | +0.056 |
wheel | +0.048 |
Neg logit contributions | |
packs | -0.219 |
uth | -0.213 |
eth | -0.210 |
patients | -0.193 |
aj | -0.190 |
Token | 's |
Token ID | 338 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ting | +0.168 |
course | +0.129 |
neath | +0.121 |
pped | +0.118 |
That | +0.111 |
Neg logit contributions | |
packs | -0.260 |
uth | -0.256 |
eth | -0.251 |
aj | -0.236 |
ies | -0.232 |
Token | go |
Token ID | 467 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
packs | +0.023 |
uth | +0.022 |
eth | +0.022 |
aj | +0.021 |
majesty | +0.020 |
Neg logit contributions | |
ting | -0.022 |
course | -0.018 |
neath | -0.017 |
pped | -0.017 |
You | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
ting | +0.060 |
course | +0.053 |
That | +0.051 |
pped | +0.050 |
neath | +0.049 |
Neg logit contributions | |
packs | -0.045 |
eth | -0.043 |
uth | -0.039 |
aj | -0.038 |
ies | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
packs | +0.004 |
uth | +0.004 |
eth | +0.004 |
aj | +0.004 |
patients | +0.003 |
Neg logit contributions | |
ting | -0.003 |
course | -0.002 |
pped | -0.002 |
neath | -0.002 |
That | -0.002 |
Token | special |
Token ID | 2041 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
ting | +0.049 |
course | +0.043 |
neath | +0.041 |
pped | +0.040 |
That | +0.040 |
Neg logit contributions | |
packs | -0.031 |
uth | -0.030 |
eth | -0.029 |
aj | -0.027 |
majesty | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ting | +0.096 |
neath | +0.081 |
Looks | +0.080 |
That | +0.079 |
course | +0.078 |
Neg logit contributions | |
packs | -0.065 |
eth | -0.059 |
uth | -0.055 |
ies | -0.054 |
aj | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
packs | +0.069 |
uth | +0.067 |
eth | +0.066 |
aj | +0.062 |
majesty | +0.060 |
Neg logit contributions | |
ting | -0.049 |
course | -0.037 |
neath | -0.036 |
pped | -0.035 |
That | -0.034 |
Token | floor |
Token ID | 4314 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
ting | +0.089 |
course | +0.073 |
neath | +0.073 |
pped | +0.073 |
You | +0.070 |
Neg logit contributions | |
packs | -0.069 |
uth | -0.064 |
eth | -0.064 |
aj | -0.059 |
majesty | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
packs | +0.010 |
uth | +0.010 |
eth | +0.010 |
aj | +0.009 |
majesty | +0.008 |
Neg logit contributions | |
ting | -0.015 |
course | -0.013 |
neath | -0.012 |
pped | -0.012 |
That | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
ting | +0.033 |
course | +0.027 |
pped | +0.026 |
neath | +0.025 |
That | +0.024 |
Neg logit contributions | |
packs | -0.035 |
uth | -0.034 |
eth | -0.033 |
aj | -0.031 |
majesty | -0.030 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ting | +0.112 |
course | +0.076 |
neath | +0.072 |
causing | +0.071 |
wheel | +0.069 |
Neg logit contributions | |
packs | -0.172 |
uth | -0.172 |
eth | -0.166 |
ighed | -0.164 |
heads | -0.153 |
Token | 's |
Token ID | 338 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ting | +0.211 |
neath | +0.156 |
Any | +0.155 |
Looks | +0.154 |
pped | +0.153 |
Neg logit contributions | |
eth | -0.201 |
packs | -0.201 |
uth | -0.197 |
ies | -0.190 |
by | -0.178 |
Token | land |
Token ID | 1956 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
packs | +0.023 |
uth | +0.022 |
eth | +0.022 |
aj | +0.020 |
majesty | +0.020 |
Neg logit contributions | |
ting | -0.026 |
course | -0.021 |
neath | -0.020 |
pped | -0.020 |
That | -0.020 |
Token | there |
Token ID | 612 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ting | +0.027 |
course | +0.022 |
neath | +0.020 |
pped | +0.020 |
That | +0.020 |
Neg logit contributions | |
packs | -0.027 |
eth | -0.026 |
uth | -0.025 |
aj | -0.024 |
ies | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
ting | +0.021 |
course | +0.018 |
neath | +0.017 |
pped | +0.017 |
You | +0.016 |
Neg logit contributions | |
packs | -0.019 |
uth | -0.019 |
eth | -0.018 |
aj | -0.017 |
majesty | -0.017 |
Token | explore |
Token ID | 7301 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
ting | +0.065 |
course | +0.055 |
pped | +0.052 |
neath | +0.051 |
That | +0.050 |
Neg logit contributions | |
packs | -0.059 |
uth | -0.055 |
eth | -0.054 |
patients | -0.051 |
majesty | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
packs | +0.067 |
uth | +0.065 |
eth | +0.063 |
aj | +0.060 |
majesty | +0.059 |
Neg logit contributions | |
ting | -0.075 |
course | -0.063 |
neath | -0.060 |
pped | -0.059 |
That | -0.059 |
Token | â |
Token ID | 22940 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
eth | +0.047 |
packs | +0.046 |
uth | +0.045 |
ifi | +0.038 |
ies | +0.038 |
Neg logit contributions | |
ting | -0.058 |
course | -0.046 |
neath | -0.045 |
pped | -0.044 |
Good | -0.041 |
Token | € |
Token ID | 26391 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
ting | +0.067 |
neath | +0.052 |
pped | +0.051 |
course | +0.050 |
ted | +0.047 |
Neg logit contributions | |
eth | -0.060 |
uth | -0.060 |
packs | -0.057 |
spine | -0.053 |
ighed | -0.053 |
Token | � |
Token ID | 129 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
packs | +0.055 |
uth | +0.054 |
eth | +0.052 |
aj | +0.050 |
patients | +0.049 |
Neg logit contributions | |
ting | -0.057 |
course | -0.048 |
neath | -0.045 |
pped | -0.044 |
That | -0.044 |
Token | � |
Token ID | 241 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ting | +0.073 |
course | +0.061 |
neath | +0.058 |
pped | +0.057 |
You | +0.054 |
Neg logit contributions | |
uth | -0.069 |
packs | -0.069 |
eth | -0.068 |
aj | -0.062 |
majesty | -0.060 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ting | +0.060 |
course | +0.044 |
neath | +0.043 |
pped | +0.040 |
wheel | +0.036 |
Neg logit contributions | |
packs | -0.085 |
uth | -0.085 |
eth | -0.083 |
ifi | -0.075 |
aj | -0.075 |
Token | â |
Token ID | 22940 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
ting | +0.205 |
course | +0.163 |
neath | +0.157 |
Any | +0.152 |
pped | +0.152 |
Neg logit contributions | |
packs | -0.204 |
uth | -0.204 |
eth | -0.203 |
ies | -0.190 |
patients | -0.180 |
Token | € |
Token ID | 26391 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ting | +0.101 |
neath | +0.080 |
ted | +0.077 |
pped | +0.076 |
Good | +0.076 |
Neg logit contributions | |
eth | -0.058 |
packs | -0.056 |
uth | -0.056 |
ighed | -0.051 |
ifi | -0.050 |
Token | ™ |
Token ID | 8151 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
packs | +0.049 |
uth | +0.048 |
eth | +0.047 |
aj | +0.044 |
majesty | +0.043 |
Neg logit contributions | |
ting | -0.051 |
course | -0.042 |
neath | -0.040 |
pped | -0.040 |
You | -0.039 |
Token | s |
Token ID | 82 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
ting | +0.071 |
course | +0.060 |
neath | +0.058 |
pped | +0.057 |
That | +0.055 |
Neg logit contributions | |
packs | -0.055 |
uth | -0.053 |
eth | -0.052 |
aj | -0.048 |
majesty | -0.046 |
Token | play |
Token ID | 711 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
packs | +0.048 |
uth | +0.047 |
eth | +0.046 |
aj | +0.043 |
majesty | +0.041 |
Neg logit contributions | |
ting | -0.053 |
course | -0.044 |
neath | -0.042 |
pped | -0.041 |
That | -0.040 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
packs | +0.005 |
uth | +0.005 |
eth | +0.005 |
aj | +0.004 |
majesty | +0.004 |
Neg logit contributions | |
ting | -0.007 |
course | -0.006 |
neath | -0.006 |
pped | -0.006 |
That | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
packs | +0.056 |
uth | +0.054 |
eth | +0.053 |
aj | +0.049 |
majesty | +0.047 |
Neg logit contributions | |
ting | -0.084 |
course | -0.071 |
neath | -0.069 |
pped | -0.068 |
That | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
ting | +0.021 |
course | +0.017 |
neath | +0.016 |
That | +0.016 |
You | +0.016 |
Neg logit contributions | |
packs | -0.025 |
uth | -0.025 |
eth | -0.024 |
aj | -0.023 |
majesty | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
packs | +0.078 |
uth | +0.077 |
majesty | +0.073 |
aj | +0.072 |
eth | +0.072 |
Neg logit contributions | |
ting | -0.065 |
course | -0.055 |
That | -0.055 |
You | -0.054 |
neath | -0.052 |
Token | " |
Token ID | 1 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
packs | +0.043 |
eth | +0.042 |
uth | +0.041 |
aj | +0.038 |
ies | +0.035 |
Neg logit contributions | |
ting | -0.059 |
course | -0.049 |
neath | -0.048 |
pped | -0.047 |
You | -0.044 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ting | +0.088 |
course | +0.066 |
neath | +0.059 |
pped | +0.059 |
wheel | +0.051 |
Neg logit contributions | |
packs | -0.183 |
eth | -0.175 |
uth | -0.175 |
ifi | -0.160 |
ighed | -0.157 |
Token | 's |
Token ID | 338 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ting | +0.188 |
course | +0.146 |
neath | +0.141 |
pped | +0.137 |
Any | +0.133 |
Neg logit contributions | |
packs | -0.231 |
uth | -0.225 |
eth | -0.223 |
ies | -0.208 |
aj | -0.205 |
Token | roll |
Token ID | 4836 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
packs | +0.028 |
uth | +0.027 |
eth | +0.027 |
aj | +0.025 |
majesty | +0.024 |
Neg logit contributions | |
ting | -0.028 |
course | -0.023 |
neath | -0.021 |
pped | -0.021 |
That | -0.021 |
Token | down |
Token ID | 866 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
ting | +0.127 |
course | +0.099 |
pped | +0.098 |
neath | +0.095 |
Looks | +0.094 |
Neg logit contributions | |
packs | -0.145 |
eth | -0.132 |
uth | -0.130 |
ies | -0.125 |
aj | -0.120 |
Token | the |
Token ID | 262 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
packs | +0.004 |
uth | +0.004 |
eth | +0.004 |
ies | +0.003 |
apartment | +0.003 |
Neg logit contributions | |
ting | -0.005 |
pped | -0.004 |
wheel | -0.003 |
Looks | -0.003 |
Any | -0.003 |
Token | hill |
Token ID | 12788 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
ting | +0.127 |
pped | +0.109 |
Looks | +0.101 |
course | +0.101 |
neath | +0.100 |
Neg logit contributions | |
packs | -0.068 |
eth | -0.064 |
uth | -0.062 |
ies | -0.056 |
ilot | -0.053 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
ting | +0.003 |
course | +0.002 |
neath | +0.002 |
pped | +0.002 |
That | +0.002 |
Neg logit contributions | |
packs | -0.002 |
uth | -0.002 |
eth | -0.002 |
aj | -0.001 |
majesty | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
packs | +0.057 |
uth | +0.056 |
eth | +0.054 |
aj | +0.051 |
majesty | +0.049 |
Neg logit contributions | |
ting | -0.082 |
course | -0.069 |
neath | -0.066 |
pped | -0.066 |
You | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
ting | +0.029 |
neath | +0.021 |
That | +0.021 |
course | +0.021 |
You | +0.021 |
Neg logit contributions | |
packs | -0.041 |
uth | -0.041 |
eth | -0.040 |
aj | -0.038 |
majesty | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
packs | +0.067 |
uth | +0.066 |
majesty | +0.064 |
aj | +0.063 |
ies | +0.062 |
Neg logit contributions | |
ting | -0.053 |
That | -0.046 |
course | -0.045 |
You | -0.044 |
neath | -0.043 |
Token | " |
Token ID | 1 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
packs | +0.039 |
uth | +0.037 |
eth | +0.037 |
aj | +0.034 |
majesty | +0.033 |
Neg logit contributions | |
ting | -0.046 |
course | -0.038 |
neath | -0.037 |
pped | -0.036 |
You | -0.035 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ting | +0.084 |
course | +0.065 |
pped | +0.055 |
neath | +0.055 |
wheel | +0.050 |
Neg logit contributions | |
packs | -0.186 |
uth | -0.178 |
eth | -0.175 |
ifi | -0.160 |
ighed | -0.159 |
Token | 's |
Token ID | 338 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ting | +0.168 |
course | +0.128 |
neath | +0.121 |
pped | +0.118 |
You | +0.111 |
Neg logit contributions | |
packs | -0.254 |
uth | -0.248 |
eth | -0.245 |
aj | -0.230 |
ies | -0.226 |
Token | record |
Token ID | 1700 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
packs | +0.023 |
uth | +0.022 |
eth | +0.021 |
aj | +0.020 |
majesty | +0.019 |
Neg logit contributions | |
ting | -0.026 |
course | -0.021 |
neath | -0.020 |
pped | -0.020 |
You | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
ting | +0.051 |
course | +0.039 |
neath | +0.038 |
pped | +0.037 |
That | +0.035 |
Neg logit contributions | |
packs | -0.073 |
uth | -0.070 |
eth | -0.069 |
aj | -0.066 |
majesty | -0.064 |
Token | show |
Token ID | 905 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
ting | +0.020 |
course | +0.016 |
neath | +0.015 |
That | +0.015 |
You | +0.015 |
Neg logit contributions | |
packs | -0.018 |
uth | -0.017 |
eth | -0.017 |
aj | -0.016 |
majesty | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
uth | +0.011 |
packs | +0.011 |
eth | +0.010 |
aj | +0.010 |
majesty | +0.010 |
Neg logit contributions | |
ting | -0.011 |
course | -0.009 |
pped | -0.008 |
You | -0.008 |
neath | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
packs | +0.022 |
uth | +0.022 |
eth | +0.021 |
aj | +0.020 |
majesty | +0.020 |
Neg logit contributions | |
ting | -0.016 |
course | -0.012 |
pped | -0.012 |
neath | -0.012 |
That | -0.011 |
Token | an |
Token ID | 281 |
Feature activation | -1.58e-04 |
Pos logit contributions | |
ting | +0.090 |
course | +0.067 |
neath | +0.062 |
pped | +0.060 |
That | +0.058 |
Neg logit contributions | |
packs | -0.150 |
uth | -0.146 |
eth | -0.144 |
aj | -0.138 |
majesty | -0.132 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
packs | +0.000 |
uth | +0.000 |
eth | +0.000 |
aj | +0.000 |
majesty | +0.000 |
Neg logit contributions | |
ting | -0.000 |
course | -0.000 |
neath | -0.000 |
pped | -0.000 |
That | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
packs | +0.047 |
eth | +0.043 |
uth | +0.042 |
ies | +0.037 |
aj | +0.037 |
Neg logit contributions | |
ting | -0.084 |
course | -0.071 |
neath | -0.071 |
pped | -0.069 |
That | -0.068 |
Token | " |
Token ID | 366 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
ting | +0.029 |
course | +0.023 |
neath | +0.022 |
pped | +0.021 |
That | +0.021 |
Neg logit contributions | |
packs | -0.034 |
uth | -0.033 |
eth | -0.033 |
aj | -0.031 |
majesty | -0.030 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ting | +0.095 |
course | +0.068 |
neath | +0.057 |
pped | +0.057 |
wheel | +0.057 |
Neg logit contributions | |
packs | -0.220 |
uth | -0.215 |
eth | -0.210 |
ifi | -0.193 |
patients | -0.191 |
Token | 's |
Token ID | 338 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ting | +0.174 |
course | +0.135 |
neath | +0.127 |
pped | +0.125 |
You | +0.117 |
Neg logit contributions | |
packs | -0.244 |
uth | -0.242 |
eth | -0.237 |
aj | -0.221 |
ies | -0.219 |
Token | go |
Token ID | 467 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
packs | +0.028 |
uth | +0.027 |
eth | +0.027 |
aj | +0.025 |
majesty | +0.024 |
Neg logit contributions | |
ting | -0.027 |
course | -0.022 |
neath | -0.021 |
pped | -0.021 |
That | -0.020 |
Token | on |
Token ID | 319 |
Feature activation | -3.07e-03 |
Pos logit contributions | |
ting | +0.057 |
course | +0.050 |
That | +0.048 |
pped | +0.048 |
neath | +0.047 |
Neg logit contributions | |
packs | -0.042 |
eth | -0.040 |
uth | -0.037 |
aj | -0.035 |
ies | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
packs | +0.007 |
uth | +0.007 |
eth | +0.007 |
aj | +0.007 |
patients | +0.006 |
Neg logit contributions | |
ting | -0.005 |
course | -0.004 |
pped | -0.003 |
neath | -0.003 |
That | -0.003 |
Token | holiday |
Token ID | 9912 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
ting | +0.047 |
course | +0.040 |
neath | +0.039 |
pped | +0.038 |
That | +0.037 |
Neg logit contributions | |
packs | -0.029 |
uth | -0.028 |
eth | -0.027 |
aj | -0.025 |
majesty | -0.024 |
Token | idea |
Token ID | 2126 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
ting | +0.008 |
course | +0.008 |
neath | +0.007 |
pped | +0.007 |
That | +0.007 |
Neg logit contributions | |
packs | -0.004 |
uth | -0.004 |
eth | -0.004 |
aj | -0.003 |
majesty | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
packs | +0.048 |
uth | +0.046 |
eth | +0.045 |
aj | +0.042 |
majesty | +0.040 |
Neg logit contributions | |
ting | -0.068 |
course | -0.058 |
neath | -0.056 |
pped | -0.055 |
That | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
ting | +0.016 |
course | +0.013 |
neath | +0.013 |
pped | +0.012 |
That | +0.012 |
Neg logit contributions | |
packs | -0.013 |
uth | -0.013 |
eth | -0.013 |
aj | -0.012 |
majesty | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
packs | +0.071 |
uth | +0.068 |
eth | +0.067 |
aj | +0.062 |
majesty | +0.059 |
Neg logit contributions | |
ting | -0.090 |
course | -0.075 |
neath | -0.072 |
pped | -0.071 |
That | -0.069 |
Token | " |
Token ID | 1 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
eth | +0.047 |
packs | +0.046 |
uth | +0.044 |
ifi | +0.039 |
common | +0.038 |
Neg logit contributions | |
ting | -0.072 |
neath | -0.056 |
pped | -0.055 |
course | -0.055 |
ted | -0.053 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.094 |
course | +0.069 |
pped | +0.064 |
neath | +0.062 |
wheel | +0.056 |
Neg logit contributions | |
packs | -0.174 |
eth | -0.167 |
uth | -0.167 |
patients | -0.152 |
ifi | -0.149 |
Token | 's |
Token ID | 338 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ting | +0.182 |
course | +0.141 |
neath | +0.134 |
pped | +0.132 |
Any | +0.125 |
Neg logit contributions | |
packs | -0.238 |
uth | -0.232 |
eth | -0.231 |
ies | -0.215 |
aj | -0.214 |
Token | sell |
Token ID | 3677 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
packs | +0.024 |
uth | +0.023 |
eth | +0.023 |
aj | +0.021 |
majesty | +0.020 |
Neg logit contributions | |
ting | -0.029 |
course | -0.024 |
neath | -0.023 |
pped | -0.023 |
That | -0.022 |
Token | these |
Token ID | 777 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ting | +0.053 |
course | +0.041 |
neath | +0.040 |
pped | +0.039 |
That | +0.038 |
Neg logit contributions | |
packs | -0.073 |
uth | -0.070 |
eth | -0.069 |
aj | -0.065 |
ies | -0.063 |
Token | screws |
Token ID | 23742 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
packs | +0.024 |
uth | +0.023 |
eth | +0.023 |
aj | +0.021 |
majesty | +0.021 |
Neg logit contributions | |
ting | -0.028 |
course | -0.024 |
neath | -0.023 |
pped | -0.022 |
That | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
ting | +0.022 |
course | +0.019 |
neath | +0.018 |
pped | +0.018 |
You | +0.017 |
Neg logit contributions | |
packs | -0.018 |
uth | -0.018 |
eth | -0.018 |
aj | -0.017 |
majesty | -0.016 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
packs | +0.003 |
uth | +0.002 |
eth | +0.002 |
aj | +0.002 |
majesty | +0.002 |
Neg logit contributions | |
ting | -0.008 |
course | -0.007 |
neath | -0.007 |
pped | -0.007 |
That | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +9.54e-03 |
Pos logit contributions | |
packs | +0.059 |
uth | +0.057 |
eth | +0.055 |
aj | +0.051 |
majesty | +0.048 |
Neg logit contributions | |
ting | -0.089 |
course | -0.075 |
neath | -0.073 |
pped | -0.071 |
That | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
ting | +0.016 |
That | +0.013 |
course | +0.013 |
You | +0.013 |
neath | +0.013 |
Neg logit contributions | |
packs | -0.020 |
uth | -0.020 |
eth | -0.019 |
aj | -0.019 |
patients | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
packs | +0.079 |
uth | +0.077 |
majesty | +0.074 |
aj | +0.074 |
eth | +0.073 |
Neg logit contributions | |
ting | -0.065 |
That | -0.056 |
course | -0.055 |
You | -0.054 |
neath | -0.053 |
Token | " |
Token ID | 1 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
packs | +0.046 |
uth | +0.045 |
eth | +0.044 |
aj | +0.040 |
ies | +0.038 |
Neg logit contributions | |
ting | -0.059 |
course | -0.049 |
neath | -0.047 |
pped | -0.046 |
You | -0.044 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.084 |
course | +0.065 |
pped | +0.057 |
neath | +0.054 |
wheel | +0.052 |
Neg logit contributions | |
packs | -0.180 |
uth | -0.172 |
eth | -0.170 |
ifi | -0.158 |
patients | -0.153 |
Token | 's |
Token ID | 338 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ting | +0.182 |
course | +0.141 |
neath | +0.134 |
pped | +0.132 |
Any | +0.126 |
Neg logit contributions | |
packs | -0.236 |
uth | -0.231 |
eth | -0.229 |
ies | -0.213 |
aj | -0.211 |
Token | get |
Token ID | 651 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
packs | +0.026 |
uth | +0.025 |
eth | +0.025 |
aj | +0.023 |
majesty | +0.022 |
Neg logit contributions | |
ting | -0.032 |
course | -0.027 |
neath | -0.025 |
pped | -0.025 |
That | -0.025 |
Token | some |
Token ID | 617 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
ting | +0.095 |
course | +0.081 |
That | +0.072 |
pped | +0.070 |
neath | +0.070 |
Neg logit contributions | |
packs | -0.110 |
eth | -0.098 |
uth | -0.097 |
ies | -0.095 |
patients | -0.093 |
Token | wood |
Token ID | 4898 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
ting | +0.007 |
course | +0.006 |
neath | +0.006 |
pped | +0.006 |
You | +0.005 |
Neg logit contributions | |
packs | -0.008 |
uth | -0.008 |
eth | -0.008 |
aj | -0.007 |
majesty | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
uth | +0.005 |
packs | +0.005 |
eth | +0.005 |
aj | +0.004 |
majesty | +0.004 |
Neg logit contributions | |
ting | -0.007 |
course | -0.006 |
neath | -0.005 |
You | -0.005 |
pped | -0.005 |
Token | cave |
Token ID | 11527 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
ting | +0.028 |
course | +0.024 |
neath | +0.023 |
pped | +0.022 |
That | +0.022 |
Neg logit contributions | |
packs | -0.022 |
uth | -0.022 |
eth | -0.021 |
aj | -0.020 |
majesty | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
packs | +0.049 |
eth | +0.044 |
uth | +0.043 |
ies | +0.042 |
aj | +0.040 |
Neg logit contributions | |
ting | -0.088 |
course | -0.074 |
neath | -0.073 |
pped | -0.073 |
Any | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
ting | +0.041 |
course | +0.034 |
neath | +0.033 |
That | +0.033 |
You | +0.033 |
Neg logit contributions | |
packs | -0.044 |
eth | -0.044 |
uth | -0.043 |
aj | -0.042 |
majesty | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
packs | +0.074 |
uth | +0.072 |
majesty | +0.070 |
eth | +0.070 |
aj | +0.070 |
Neg logit contributions | |
ting | -0.062 |
course | -0.054 |
That | -0.054 |
You | -0.052 |
neath | -0.052 |
Token | " |
Token ID | 1 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
packs | +0.043 |
uth | +0.042 |
eth | +0.041 |
aj | +0.036 |
ies | +0.035 |
Neg logit contributions | |
ting | -0.060 |
course | -0.049 |
neath | -0.048 |
pped | -0.047 |
You | -0.044 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.092 |
course | +0.071 |
pped | +0.061 |
neath | +0.059 |
wheel | +0.057 |
Neg logit contributions | |
packs | -0.178 |
uth | -0.175 |
eth | -0.167 |
ifi | -0.157 |
patients | -0.151 |
Token | 's |
Token ID | 338 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ting | +0.188 |
course | +0.142 |
neath | +0.139 |
pped | +0.138 |
Any | +0.133 |
Neg logit contributions | |
uth | -0.224 |
packs | -0.223 |
eth | -0.218 |
ies | -0.203 |
patients | -0.199 |
Token | go |
Token ID | 467 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
packs | +0.025 |
uth | +0.025 |
eth | +0.024 |
aj | +0.024 |
majesty | +0.022 |
Neg logit contributions | |
ting | -0.021 |
course | -0.018 |
neath | -0.017 |
pped | -0.017 |
That | -0.016 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ting | +0.057 |
course | +0.048 |
neath | +0.045 |
pped | +0.044 |
That | +0.044 |
Neg logit contributions | |
packs | -0.055 |
eth | -0.052 |
uth | -0.051 |
aj | -0.048 |
ies | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
packs | +0.062 |
uth | +0.061 |
eth | +0.060 |
aj | +0.056 |
majesty | +0.056 |
Neg logit contributions | |
ting | -0.061 |
course | -0.049 |
neath | -0.047 |
pped | -0.046 |
That | -0.045 |
Token | cave |
Token ID | 11527 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
ting | +0.116 |
course | +0.100 |
neath | +0.096 |
pped | +0.094 |
That | +0.093 |
Neg logit contributions | |
packs | -0.070 |
uth | -0.069 |
eth | -0.066 |
aj | -0.061 |
majesty | -0.058 |
Token | old |
Token ID | 1468 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ting | +0.077 |
pped | +0.065 |
course | +0.063 |
neath | +0.060 |
wheel | +0.057 |
Neg logit contributions | |
packs | -0.050 |
uth | -0.045 |
eth | -0.042 |
ies | -0.041 |
aj | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
eth | +0.023 |
uth | +0.022 |
packs | +0.021 |
aj | +0.021 |
majesty | +0.020 |
Neg logit contributions | |
ting | -0.025 |
course | -0.021 |
You | -0.019 |
That | -0.019 |
neath | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
ting | +0.049 |
course | +0.039 |
pped | +0.038 |
neath | +0.037 |
That | +0.035 |
Neg logit contributions | |
packs | -0.053 |
uth | -0.051 |
eth | -0.050 |
aj | -0.047 |
patients | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
packs | +0.054 |
eth | +0.052 |
uth | +0.052 |
aj | +0.046 |
ilot | +0.042 |
Neg logit contributions | |
ting | -0.086 |
course | -0.070 |
pped | -0.067 |
neath | -0.067 |
wheel | -0.063 |
Token | " |
Token ID | 1 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
packs | +0.034 |
eth | +0.034 |
uth | +0.034 |
ifi | +0.029 |
ies | +0.028 |
Neg logit contributions | |
ting | -0.067 |
course | -0.052 |
neath | -0.051 |
wheel | -0.051 |
pped | -0.050 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.095 |
course | +0.072 |
pped | +0.068 |
neath | +0.066 |
wheel | +0.061 |
Neg logit contributions | |
packs | -0.169 |
uth | -0.168 |
eth | -0.157 |
ifi | -0.150 |
ighed | -0.145 |
Token | 's |
Token ID | 338 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ting | +0.192 |
course | +0.146 |
neath | +0.143 |
pped | +0.142 |
Any | +0.137 |
Neg logit contributions | |
packs | -0.222 |
uth | -0.221 |
eth | -0.215 |
ies | -0.201 |
aj | -0.196 |
Token | climb |
Token ID | 12080 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
packs | +0.027 |
uth | +0.026 |
eth | +0.026 |
aj | +0.026 |
majesty | +0.024 |
Neg logit contributions | |
ting | -0.022 |
course | -0.019 |
neath | -0.018 |
pped | -0.017 |
That | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
ting | +0.123 |
Looks | +0.102 |
course | +0.102 |
pped | +0.101 |
Any | +0.099 |
Neg logit contributions | |
packs | -0.136 |
uth | -0.121 |
eth | -0.118 |
ies | -0.112 |
aj | -0.106 |
Token | tree |
Token ID | 5509 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
ting | +0.123 |
course | +0.102 |
neath | +0.098 |
pped | +0.097 |
That | +0.094 |
Neg logit contributions | |
packs | -0.109 |
uth | -0.106 |
eth | -0.104 |
aj | -0.097 |
majesty | -0.093 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
uth | +0.008 |
eth | +0.008 |
packs | +0.008 |
aj | +0.008 |
majesty | +0.008 |
Neg logit contributions | |
ting | -0.010 |
course | -0.008 |
neath | -0.008 |
That | -0.007 |
You | -0.007 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
ting | +0.004 |
course | +0.003 |
neath | +0.003 |
pped | +0.003 |
That | +0.003 |
Neg logit contributions | |
packs | -0.001 |
uth | -0.001 |
eth | -0.001 |
aj | -0.001 |
majesty | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
packs | +0.050 |
uth | +0.048 |
eth | +0.047 |
aj | +0.043 |
majesty | +0.041 |
Neg logit contributions | |
ting | -0.074 |
course | -0.062 |
neath | -0.060 |
pped | -0.059 |
That | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ting | +0.023 |
course | +0.018 |
That | +0.018 |
You | +0.018 |
neath | +0.018 |
Neg logit contributions | |
packs | -0.024 |
uth | -0.023 |
eth | -0.023 |
aj | -0.022 |
majesty | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
packs | +0.077 |
uth | +0.075 |
eth | +0.071 |
aj | +0.070 |
majesty | +0.069 |
Neg logit contributions | |
ting | -0.075 |
course | -0.064 |
That | -0.062 |
neath | -0.061 |
You | -0.061 |
Token | " |
Token ID | 1 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
packs | +0.049 |
uth | +0.048 |
eth | +0.048 |
ifi | +0.041 |
ies | +0.041 |
Neg logit contributions | |
ting | -0.066 |
course | -0.052 |
neath | -0.051 |
pped | -0.051 |
Good | -0.048 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.090 |
course | +0.065 |
pped | +0.062 |
neath | +0.058 |
wheel | +0.054 |
Neg logit contributions | |
packs | -0.178 |
uth | -0.172 |
eth | -0.168 |
ifi | -0.157 |
patients | -0.153 |
Token | 's |
Token ID | 338 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
ting | +0.183 |
course | +0.142 |
neath | +0.135 |
pped | +0.134 |
wheel | +0.128 |
Neg logit contributions | |
packs | -0.234 |
uth | -0.230 |
eth | -0.225 |
ies | -0.211 |
aj | -0.207 |
Token | build |
Token ID | 1382 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
packs | +0.026 |
uth | +0.025 |
eth | +0.025 |
aj | +0.023 |
majesty | +0.022 |
Neg logit contributions | |
ting | -0.030 |
course | -0.025 |
neath | -0.024 |
pped | -0.023 |
That | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
ting | +0.138 |
That | +0.103 |
pped | +0.102 |
neath | +0.100 |
course | +0.099 |
Neg logit contributions | |
packs | -0.154 |
uth | -0.140 |
eth | -0.131 |
ies | -0.129 |
aj | -0.129 |
Token | home |
Token ID | 1363 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
ting | +0.044 |
course | +0.037 |
neath | +0.035 |
pped | +0.035 |
That | +0.034 |
Neg logit contributions | |
packs | -0.038 |
uth | -0.036 |
eth | -0.036 |
aj | -0.033 |
majesty | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
uth | +0.131 |
packs | +0.129 |
eth | +0.128 |
aj | +0.121 |
majesty | +0.117 |
Neg logit contributions | |
ting | -0.127 |
course | -0.104 |
neath | -0.096 |
You | -0.096 |
That | -0.094 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
ting | +0.002 |
course | +0.002 |
neath | +0.002 |
pped | +0.002 |
That | +0.002 |
Neg logit contributions | |
packs | -0.001 |
uth | -0.001 |
eth | -0.001 |
aj | -0.001 |
majesty | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
packs | +0.053 |
uth | +0.050 |
eth | +0.049 |
aj | +0.045 |
ies | +0.043 |
Neg logit contributions | |
ting | -0.084 |
course | -0.071 |
neath | -0.070 |
pped | -0.068 |
That | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ting | +0.014 |
course | +0.011 |
neath | +0.011 |
That | +0.011 |
You | +0.010 |
Neg logit contributions | |
packs | -0.017 |
uth | -0.017 |
eth | -0.016 |
aj | -0.016 |
majesty | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
packs | +0.083 |
uth | +0.080 |
majesty | +0.079 |
aj | +0.077 |
patients | +0.076 |
Neg logit contributions | |
ting | -0.068 |
That | -0.058 |
course | -0.057 |
You | -0.056 |
neath | -0.054 |
Token | " |
Token ID | 1 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
packs | +0.052 |
uth | +0.051 |
eth | +0.050 |
aj | +0.047 |
majesty | +0.045 |
Neg logit contributions | |
ting | -0.060 |
course | -0.050 |
neath | -0.048 |
pped | -0.047 |
That | -0.046 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.085 |
course | +0.064 |
neath | +0.055 |
pped | +0.055 |
wheel | +0.050 |
Neg logit contributions | |
packs | -0.177 |
uth | -0.174 |
eth | -0.169 |
ifi | -0.157 |
patients | -0.153 |
Token | 's |
Token ID | 338 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ting | +0.179 |
course | +0.139 |
neath | +0.133 |
pped | +0.130 |
Any | +0.124 |
Neg logit contributions | |
packs | -0.235 |
uth | -0.232 |
eth | -0.228 |
ies | -0.212 |
aj | -0.212 |
Token | play |
Token ID | 711 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
packs | +0.026 |
uth | +0.025 |
eth | +0.025 |
aj | +0.023 |
majesty | +0.022 |
Neg logit contributions | |
ting | -0.030 |
course | -0.024 |
neath | -0.023 |
pped | -0.023 |
That | -0.022 |
Token | with |
Token ID | 351 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
ting | +0.070 |
neath | +0.055 |
Looks | +0.055 |
pped | +0.054 |
course | +0.053 |
Neg logit contributions | |
packs | -0.062 |
uth | -0.058 |
eth | -0.057 |
aj | -0.054 |
ies | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
ting | +0.040 |
course | +0.031 |
Looks | +0.031 |
Any | +0.030 |
That | +0.030 |
Neg logit contributions | |
packs | -0.043 |
uth | -0.041 |
eth | -0.040 |
patients | -0.038 |
ies | -0.038 |
Token | hose |
Token ID | 31489 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
ting | +0.110 |
course | +0.093 |
pped | +0.091 |
neath | +0.088 |
That | +0.086 |
Neg logit contributions | |
packs | -0.079 |
eth | -0.076 |
uth | -0.076 |
ies | -0.070 |
aj | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ting | +0.109 |
pped | +0.085 |
wheel | +0.084 |
course | +0.084 |
aling | +0.083 |
Neg logit contributions | |
packs | -0.107 |
uth | -0.102 |
eth | -0.094 |
teeth | -0.091 |
patients | -0.091 |
Token | big |
Token ID | 1263 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ting | +0.030 |
course | +0.026 |
neath | +0.024 |
That | +0.024 |
pped | +0.023 |
Neg logit contributions | |
packs | -0.028 |
uth | -0.027 |
eth | -0.026 |
aj | -0.025 |
majesty | -0.024 |
Token | stick |
Token ID | 4859 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
ting | +0.043 |
course | +0.036 |
neath | +0.034 |
pped | +0.034 |
That | +0.033 |
Neg logit contributions | |
packs | -0.034 |
uth | -0.033 |
eth | -0.033 |
aj | -0.030 |
majesty | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ting | +0.133 |
Good | +0.120 |
Looks | +0.118 |
neath | +0.117 |
Great | +0.117 |
Neg logit contributions | |
packs | -0.068 |
eth | -0.054 |
ies | -0.054 |
uth | -0.047 |
ilot | -0.046 |
Token | " |
Token ID | 366 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
ting | +0.049 |
neath | +0.038 |
course | +0.038 |
That | +0.036 |
You | +0.035 |
Neg logit contributions | |
packs | -0.070 |
uth | -0.069 |
eth | -0.066 |
aj | -0.066 |
ies | -0.063 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.113 |
course | +0.085 |
wheel | +0.076 |
pped | +0.067 |
Any | +0.067 |
Neg logit contributions | |
packs | -0.204 |
uth | -0.199 |
eth | -0.194 |
ifi | -0.181 |
ighed | -0.176 |
Token | 's |
Token ID | 338 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ting | +0.191 |
course | +0.145 |
pped | +0.141 |
neath | +0.141 |
Looks | +0.136 |
Neg logit contributions | |
uth | -0.217 |
packs | -0.215 |
eth | -0.214 |
ies | -0.200 |
patients | -0.196 |
Token | measure |
Token ID | 3953 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
packs | +0.024 |
uth | +0.023 |
eth | +0.023 |
aj | +0.021 |
majesty | +0.021 |
Neg logit contributions | |
ting | -0.027 |
course | -0.022 |
neath | -0.021 |
pped | -0.021 |
That | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
ting | +0.032 |
course | +0.025 |
neath | +0.023 |
pped | +0.023 |
That | +0.022 |
Neg logit contributions | |
packs | -0.048 |
uth | -0.046 |
eth | -0.045 |
aj | -0.043 |
majesty | -0.042 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ting | +0.062 |
course | +0.051 |
neath | +0.048 |
pped | +0.047 |
That | +0.046 |
Neg logit contributions | |
packs | -0.064 |
uth | -0.063 |
eth | -0.061 |
aj | -0.058 |
majesty | -0.056 |
Token | said |
Token ID | 531 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
ting | +0.019 |
You | +0.015 |
course | +0.015 |
That | +0.015 |
neath | +0.014 |
Neg logit contributions | |
packs | -0.031 |
uth | -0.031 |
eth | -0.030 |
aj | -0.029 |
majesty | -0.029 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
ting | +0.001 |
course | +0.001 |
neath | +0.001 |
pped | +0.001 |
You | +0.001 |
Neg logit contributions | |
packs | -0.000 |
uth | -0.000 |
eth | -0.000 |
aj | -0.000 |
majesty | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
packs | +0.054 |
uth | +0.052 |
eth | +0.050 |
aj | +0.046 |
majesty | +0.044 |
Neg logit contributions | |
ting | -0.084 |
course | -0.071 |
neath | -0.069 |
pped | -0.068 |
That | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
ting | +0.047 |
course | +0.037 |
You | +0.037 |
That | +0.036 |
neath | +0.035 |
Neg logit contributions | |
packs | -0.061 |
uth | -0.060 |
eth | -0.057 |
aj | -0.056 |
ies | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
packs | +0.072 |
uth | +0.070 |
eth | +0.066 |
aj | +0.064 |
majesty | +0.064 |
Neg logit contributions | |
ting | -0.064 |
course | -0.055 |
That | -0.052 |
neath | -0.052 |
You | -0.052 |
Token | " |
Token ID | 1 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
packs | +0.042 |
eth | +0.041 |
uth | +0.040 |
aj | +0.037 |
ies | +0.034 |
Neg logit contributions | |
ting | -0.065 |
course | -0.054 |
neath | -0.054 |
pped | -0.051 |
Any | -0.049 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.110 |
pped | +0.077 |
neath | +0.075 |
course | +0.073 |
pping | +0.067 |
Neg logit contributions | |
packs | -0.167 |
eth | -0.162 |
uth | -0.158 |
patients | -0.145 |
common | -0.144 |
Token | 's |
Token ID | 338 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ting | +0.185 |
neath | +0.135 |
course | +0.135 |
pped | +0.132 |
Any | +0.127 |
Neg logit contributions | |
packs | -0.232 |
uth | -0.227 |
eth | -0.225 |
ies | -0.211 |
aj | -0.209 |
Token | cut |
Token ID | 2005 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
packs | +0.021 |
uth | +0.020 |
eth | +0.020 |
aj | +0.018 |
majesty | +0.018 |
Neg logit contributions | |
ting | -0.025 |
course | -0.020 |
neath | -0.019 |
pped | -0.019 |
That | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
ting | +0.086 |
course | +0.068 |
pped | +0.066 |
neath | +0.065 |
That | +0.065 |
Neg logit contributions | |
packs | -0.102 |
uth | -0.096 |
eth | -0.096 |
ies | -0.090 |
aj | -0.090 |
Token | paper |
Token ID | 3348 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ting | +0.109 |
course | +0.091 |
neath | +0.087 |
pped | +0.085 |
You | +0.084 |
Neg logit contributions | |
packs | -0.093 |
uth | -0.090 |
eth | -0.088 |
aj | -0.082 |
majesty | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
ting | +0.040 |
course | +0.033 |
neath | +0.032 |
pped | +0.030 |
That | +0.030 |
Neg logit contributions | |
uth | -0.040 |
packs | -0.039 |
eth | -0.038 |
aj | -0.036 |
majesty | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -1.54e-03 |
Pos logit contributions | |
ting | +0.099 |
course | +0.076 |
neath | +0.072 |
pped | +0.069 |
That | +0.067 |
Neg logit contributions | |
packs | -0.138 |
uth | -0.132 |
eth | -0.129 |
aj | -0.123 |
patients | -0.119 |
Token | clever |
Token ID | 14169 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
packs | +0.003 |
uth | +0.002 |
eth | +0.002 |
aj | +0.002 |
ies | +0.002 |
Neg logit contributions | |
ting | -0.003 |
course | -0.003 |
neath | -0.003 |
That | -0.003 |
You | -0.003 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
packs | +0.014 |
uth | +0.013 |
eth | +0.012 |
aj | +0.012 |
patients | +0.010 |
Neg logit contributions | |
ting | -0.031 |
course | -0.029 |
neath | -0.026 |
You | -0.026 |
That | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
packs | +0.046 |
uth | +0.041 |
eth | +0.041 |
ies | +0.037 |
aj | +0.036 |
Neg logit contributions | |
ting | -0.086 |
neath | -0.074 |
course | -0.073 |
pped | -0.071 |
That | -0.070 |
Token | " |
Token ID | 366 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
ting | +0.043 |
pped | +0.038 |
course | +0.038 |
neath | +0.035 |
You | +0.032 |
Neg logit contributions | |
packs | -0.032 |
eth | -0.031 |
uth | -0.030 |
ies | -0.027 |
majesty | -0.027 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ting | +0.113 |
course | +0.084 |
wheel | +0.079 |
pped | +0.078 |
neath | +0.072 |
Neg logit contributions | |
packs | -0.199 |
uth | -0.191 |
eth | -0.187 |
by | -0.173 |
ifi | -0.172 |
Token | 's |
Token ID | 338 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
ting | +0.192 |
course | +0.150 |
neath | +0.146 |
pped | +0.144 |
wheel | +0.136 |
Neg logit contributions | |
packs | -0.216 |
uth | -0.214 |
eth | -0.211 |
ies | -0.199 |
patients | -0.194 |
Token | print |
Token ID | 3601 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
packs | +0.026 |
uth | +0.025 |
eth | +0.024 |
aj | +0.022 |
majesty | +0.022 |
Neg logit contributions | |
ting | -0.030 |
course | -0.024 |
neath | -0.023 |
pped | -0.023 |
That | -0.023 |
Token | our |
Token ID | 674 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
ting | +0.192 |
pped | +0.155 |
Looks | +0.149 |
That | +0.148 |
neath | +0.148 |
Neg logit contributions | |
packs | -0.186 |
ies | -0.162 |
uth | -0.158 |
eth | -0.157 |
patients | -0.154 |
Token | own |
Token ID | 898 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
packs | +0.047 |
uth | +0.045 |
eth | +0.044 |
aj | +0.042 |
ies | +0.040 |
Neg logit contributions | |
ting | -0.054 |
course | -0.044 |
pped | -0.043 |
neath | -0.043 |
That | -0.042 |
Token | song |
Token ID | 3496 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
packs | +0.063 |
uth | +0.057 |
eth | +0.057 |
aj | +0.055 |
ies | +0.054 |
Neg logit contributions | |
ting | -0.070 |
course | -0.056 |
pped | -0.055 |
That | -0.055 |
neath | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
ting | +0.088 |
course | +0.068 |
pped | +0.067 |
neath | +0.065 |
That | +0.063 |
Neg logit contributions | |
packs | -0.114 |
uth | -0.110 |
eth | -0.107 |
patients | -0.102 |
aj | -0.100 |
Token | big |
Token ID | 1263 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
ting | +0.040 |
course | +0.033 |
neath | +0.032 |
pped | +0.031 |
That | +0.031 |
Neg logit contributions | |
packs | -0.033 |
uth | -0.032 |
eth | -0.031 |
aj | -0.029 |
majesty | -0.028 |
Token | bush |
Token ID | 24484 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
ting | +0.057 |
course | +0.046 |
pped | +0.046 |
neath | +0.045 |
You | +0.045 |
Neg logit contributions | |
packs | -0.043 |
uth | -0.041 |
eth | -0.040 |
aj | -0.037 |
ies | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ting | +0.006 |
course | +0.005 |
neath | +0.005 |
pped | +0.005 |
Good | +0.005 |
Neg logit contributions | |
packs | -0.003 |
eth | -0.003 |
ies | -0.003 |
uth | -0.003 |
aj | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
ting | +0.053 |
course | +0.046 |
pped | +0.045 |
neath | +0.040 |
You | +0.040 |
Neg logit contributions | |
eth | -0.053 |
uth | -0.052 |
packs | -0.052 |
aj | -0.047 |
majesty | -0.046 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ting | +0.105 |
course | +0.083 |
wheel | +0.074 |
pped | +0.067 |
neath | +0.065 |
Neg logit contributions | |
packs | -0.201 |
uth | -0.200 |
eth | -0.192 |
ifi | -0.178 |
ighed | -0.174 |
Token | 's |
Token ID | 338 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ting | +0.194 |
course | +0.144 |
neath | +0.143 |
pped | +0.142 |
Looks | +0.138 |
Neg logit contributions | |
uth | -0.213 |
packs | -0.208 |
eth | -0.206 |
ies | -0.193 |
patients | -0.188 |
Token | go |
Token ID | 467 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
packs | +0.027 |
uth | +0.026 |
eth | +0.026 |
aj | +0.024 |
majesty | +0.023 |
Neg logit contributions | |
ting | -0.026 |
course | -0.022 |
neath | -0.021 |
pped | -0.020 |
That | -0.020 |
Token | explore |
Token ID | 7301 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
ting | +0.051 |
course | +0.044 |
That | +0.042 |
pped | +0.042 |
neath | +0.042 |
Neg logit contributions | |
packs | -0.043 |
eth | -0.041 |
uth | -0.039 |
ies | -0.037 |
aj | -0.036 |
Token | that |
Token ID | 326 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ting | +0.050 |
pped | +0.041 |
Looks | +0.040 |
wheel | +0.040 |
That | +0.040 |
Neg logit contributions | |
packs | -0.037 |
uth | -0.036 |
eth | -0.033 |
aj | -0.032 |
ies | -0.031 |
Token | bush |
Token ID | 24484 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
ting | +0.024 |
pped | +0.021 |
course | +0.020 |
neath | +0.019 |
wheel | +0.019 |
Neg logit contributions | |
packs | -0.019 |
uth | -0.018 |
eth | -0.017 |
ies | -0.016 |
aj | -0.015 |
Token | ground |
Token ID | 2323 |
Feature activation | -2.15e-04 |
Pos logit contributions | |
ting | +0.077 |
pped | +0.063 |
course | +0.063 |
neath | +0.061 |
Any | +0.058 |
Neg logit contributions | |
packs | -0.070 |
uth | -0.067 |
eth | -0.066 |
aj | -0.061 |
majesty | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
packs | +0.000 |
uth | +0.000 |
eth | +0.000 |
aj | +0.000 |
majesty | +0.000 |
Neg logit contributions | |
ting | -0.000 |
course | -0.000 |
neath | -0.000 |
pped | -0.000 |
You | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
ting | +0.050 |
course | +0.040 |
neath | +0.038 |
pped | +0.037 |
That | +0.037 |
Neg logit contributions | |
packs | -0.055 |
uth | -0.053 |
eth | -0.052 |
aj | -0.049 |
majesty | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
packs | +0.062 |
majesty | +0.059 |
uth | +0.059 |
aj | +0.058 |
ies | +0.057 |
Neg logit contributions | |
ting | -0.044 |
That | -0.039 |
course | -0.037 |
neath | -0.037 |
You | -0.037 |
Token | " |
Token ID | 1 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
eth | +0.036 |
uth | +0.036 |
packs | +0.035 |
aj | +0.031 |
ilot | +0.030 |
Neg logit contributions | |
ting | -0.047 |
course | -0.038 |
neath | -0.036 |
pped | -0.036 |
wheel | -0.034 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ting | +0.090 |
course | +0.067 |
pped | +0.061 |
wheel | +0.060 |
aling | +0.054 |
Neg logit contributions | |
packs | -0.162 |
uth | -0.160 |
eth | -0.155 |
ifi | -0.144 |
patients | -0.142 |
Token | 's |
Token ID | 338 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ting | +0.190 |
course | +0.146 |
neath | +0.143 |
pped | +0.141 |
wheel | +0.136 |
Neg logit contributions | |
uth | -0.218 |
packs | -0.217 |
eth | -0.212 |
ies | -0.201 |
patients | -0.195 |
Token | go |
Token ID | 467 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
packs | +0.030 |
uth | +0.029 |
eth | +0.029 |
aj | +0.028 |
majesty | +0.026 |
Neg logit contributions | |
ting | -0.028 |
course | -0.023 |
neath | -0.022 |
pped | -0.021 |
You | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | +1.86e-03 |
Pos logit contributions | |
ting | +0.050 |
course | +0.043 |
That | +0.041 |
neath | +0.040 |
pped | +0.040 |
Neg logit contributions | |
packs | -0.042 |
eth | -0.040 |
uth | -0.039 |
ies | -0.036 |
aj | -0.036 |
Token | ," |
Token ID | 553 |
Feature activation | -5.56e-03 |
Pos logit contributions | |
ting | +0.004 |
course | +0.003 |
neath | +0.003 |
pped | +0.003 |
That | +0.003 |
Neg logit contributions | |
packs | -0.004 |
uth | -0.004 |
eth | -0.004 |
aj | -0.003 |
majesty | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
packs | +0.011 |
uth | +0.011 |
eth | +0.011 |
aj | +0.010 |
majesty | +0.010 |
Neg logit contributions | |
ting | -0.011 |
course | -0.009 |
You | -0.009 |
neath | -0.008 |
That | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
packs | +0.069 |
uth | +0.067 |
eth | +0.063 |
aj | +0.063 |
majesty | +0.063 |
Neg logit contributions | |
ting | -0.067 |
course | -0.057 |
neath | -0.055 |
That | -0.054 |
You | -0.053 |
Token | â |
Token ID | 22940 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
eth | +0.048 |
packs | +0.047 |
uth | +0.047 |
aj | +0.039 |
ies | +0.039 |
Neg logit contributions | |
ting | -0.057 |
course | -0.044 |
neath | -0.043 |
pped | -0.043 |
Good | -0.041 |
Token | € |
Token ID | 26391 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
ting | +0.064 |
neath | +0.050 |
pped | +0.049 |
course | +0.049 |
ted | +0.045 |
Neg logit contributions | |
eth | -0.058 |
uth | -0.056 |
packs | -0.056 |
aj | -0.052 |
spine | -0.050 |
Token | � |
Token ID | 129 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
packs | +0.059 |
uth | +0.058 |
eth | +0.056 |
aj | +0.053 |
patients | +0.051 |
Neg logit contributions | |
ting | -0.065 |
course | -0.054 |
neath | -0.052 |
pped | -0.051 |
That | -0.050 |
Token | � |
Token ID | 241 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
ting | +0.070 |
course | +0.058 |
neath | +0.055 |
pped | +0.054 |
You | +0.052 |
Neg logit contributions | |
uth | -0.067 |
packs | -0.066 |
eth | -0.065 |
aj | -0.061 |
majesty | -0.058 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ting | +0.049 |
course | +0.035 |
neath | +0.033 |
pped | +0.031 |
wheel | +0.027 |
Neg logit contributions | |
uth | -0.085 |
packs | -0.085 |
eth | -0.084 |
aj | -0.075 |
ifi | -0.075 |
Token | â |
Token ID | 22940 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
ting | +0.205 |
neath | +0.156 |
course | +0.155 |
pped | +0.155 |
Any | +0.155 |
Neg logit contributions | |
eth | -0.194 |
uth | -0.194 |
packs | -0.190 |
ies | -0.183 |
patients | -0.170 |
Token | € |
Token ID | 26391 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
ting | +0.094 |
neath | +0.074 |
pped | +0.072 |
ted | +0.071 |
Good | +0.069 |
Neg logit contributions | |
eth | -0.060 |
packs | -0.058 |
uth | -0.058 |
ighed | -0.052 |
ifi | -0.051 |
Token | ™ |
Token ID | 8151 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
packs | +0.053 |
uth | +0.052 |
eth | +0.051 |
aj | +0.048 |
majesty | +0.046 |
Neg logit contributions | |
ting | -0.054 |
course | -0.044 |
neath | -0.043 |
pped | -0.042 |
That | -0.041 |
Token | s |
Token ID | 82 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
ting | +0.069 |
course | +0.058 |
neath | +0.055 |
pped | +0.055 |
That | +0.054 |
Neg logit contributions | |
packs | -0.053 |
uth | -0.051 |
eth | -0.050 |
aj | -0.047 |
majesty | -0.045 |
Token | see |
Token ID | 766 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
packs | +0.050 |
uth | +0.048 |
eth | +0.047 |
majesty | +0.043 |
aj | +0.043 |
Neg logit contributions | |
ting | -0.064 |
course | -0.051 |
pped | -0.049 |
neath | -0.049 |
You | -0.048 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.39e-03 |
Pos logit contributions | |
uth | +0.024 |
packs | +0.023 |
eth | +0.021 |
aj | +0.021 |
teeth | +0.021 |
Neg logit contributions | |
ting | -0.049 |
course | -0.042 |
pped | -0.041 |
neath | -0.040 |
you | -0.039 |
Token | y |
Token ID | 88 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
ting | +0.003 |
Good | +0.003 |
course | +0.003 |
neath | +0.003 |
Great | +0.003 |
Neg logit contributions | |
packs | -0.002 |
uth | -0.002 |
eth | -0.002 |
ies | -0.002 |
aj | -0.002 |
Token | hill |
Token ID | 12788 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
packs | +0.013 |
uth | +0.012 |
eth | +0.012 |
aj | +0.011 |
ies | +0.011 |
Neg logit contributions | |
ting | -0.015 |
course | -0.013 |
neath | -0.012 |
pped | -0.012 |
That | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ting | +0.007 |
pped | +0.006 |
course | +0.006 |
neath | +0.006 |
Good | +0.006 |
Neg logit contributions | |
packs | -0.005 |
eth | -0.004 |
uth | -0.004 |
ies | -0.004 |
aj | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
ting | +0.034 |
course | +0.026 |
neath | +0.026 |
That | +0.025 |
You | +0.025 |
Neg logit contributions | |
packs | -0.043 |
uth | -0.041 |
eth | -0.041 |
aj | -0.039 |
ies | -0.039 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ting | +0.106 |
course | +0.079 |
wheel | +0.072 |
causing | +0.069 |
neath | +0.069 |
Neg logit contributions | |
uth | -0.185 |
packs | -0.180 |
eth | -0.172 |
ifi | -0.167 |
ighed | -0.162 |
Token | 's |
Token ID | 338 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ting | +0.193 |
pped | +0.143 |
neath | +0.142 |
course | +0.141 |
Any | +0.136 |
Neg logit contributions | |
uth | -0.217 |
packs | -0.213 |
eth | -0.211 |
ies | -0.198 |
aj | -0.192 |
Token | go |
Token ID | 467 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
packs | +0.029 |
uth | +0.027 |
eth | +0.027 |
aj | +0.025 |
majesty | +0.024 |
Neg logit contributions | |
ting | -0.031 |
course | -0.025 |
neath | -0.024 |
pped | -0.024 |
You | -0.023 |
Token | up |
Token ID | 510 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
ting | +0.048 |
course | +0.042 |
That | +0.040 |
pped | +0.039 |
neath | +0.039 |
Neg logit contributions | |
packs | -0.038 |
eth | -0.037 |
uth | -0.034 |
ies | -0.033 |
aj | -0.032 |
Token | there |
Token ID | 612 |
Feature activation | +7.74e-03 |
Pos logit contributions | |
packs | +0.011 |
uth | +0.011 |
eth | +0.011 |
aj | +0.010 |
ies | +0.010 |
Neg logit contributions | |
ting | -0.011 |
course | -0.009 |
neath | -0.008 |
pped | -0.008 |
That | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ting | +0.015 |
course | +0.013 |
neath | +0.012 |
pped | +0.012 |
You | +0.012 |
Neg logit contributions | |
packs | -0.014 |
uth | -0.014 |
eth | -0.014 |
aj | -0.013 |
majesty | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
ting | +0.050 |
course | +0.041 |
neath | +0.039 |
pped | +0.038 |
You | +0.037 |
Neg logit contributions | |
packs | -0.061 |
uth | -0.059 |
eth | -0.058 |
aj | -0.055 |
majesty | -0.052 |
Token | an |
Token ID | 281 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
ting | +0.115 |
course | +0.091 |
neath | +0.088 |
pped | +0.085 |
That | +0.082 |
Neg logit contributions | |
packs | -0.135 |
uth | -0.131 |
eth | -0.127 |
aj | -0.121 |
majesty | -0.118 |
Token | idea |
Token ID | 2126 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
packs | +0.001 |
uth | +0.001 |
eth | +0.001 |
aj | +0.001 |
majesty | +0.001 |
Neg logit contributions | |
ting | -0.003 |
course | -0.003 |
neath | -0.003 |
pped | -0.003 |
You | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
packs | +0.057 |
uth | +0.053 |
eth | +0.053 |
aj | +0.048 |
ies | +0.047 |
Neg logit contributions | |
ting | -0.079 |
neath | -0.066 |
course | -0.065 |
pped | -0.064 |
That | -0.062 |
Token | " |
Token ID | 366 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
ting | +0.023 |
course | +0.018 |
neath | +0.018 |
That | +0.017 |
You | +0.017 |
Neg logit contributions | |
packs | -0.027 |
uth | -0.027 |
eth | -0.026 |
aj | -0.025 |
majesty | -0.024 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ting | +0.097 |
course | +0.062 |
neath | +0.060 |
pped | +0.060 |
wheel | +0.051 |
Neg logit contributions | |
packs | -0.200 |
uth | -0.195 |
eth | -0.192 |
ighed | -0.176 |
ifi | -0.175 |
Token | 's |
Token ID | 338 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
ting | +0.197 |
neath | +0.146 |
pped | +0.146 |
course | +0.144 |
Any | +0.140 |
Neg logit contributions | |
packs | -0.215 |
uth | -0.208 |
eth | -0.208 |
ies | -0.200 |
patients | -0.190 |
Token | use |
Token ID | 779 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
packs | +0.031 |
uth | +0.030 |
eth | +0.029 |
aj | +0.027 |
majesty | +0.026 |
Neg logit contributions | |
ting | -0.035 |
course | -0.028 |
neath | -0.027 |
pped | -0.027 |
That | -0.026 |
Token | glue |
Token ID | 22749 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
ting | +0.082 |
course | +0.060 |
pped | +0.059 |
That | +0.059 |
You | +0.058 |
Neg logit contributions | |
packs | -0.112 |
uth | -0.105 |
eth | -0.105 |
aj | -0.100 |
patients | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
ting | +0.080 |
course | +0.066 |
neath | +0.063 |
pped | +0.062 |
You | +0.060 |
Neg logit contributions | |
packs | -0.074 |
uth | -0.073 |
eth | -0.070 |
aj | -0.066 |
majesty | -0.064 |
Token | fix |
Token ID | 4259 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
packs | +0.099 |
uth | +0.095 |
eth | +0.094 |
aj | +0.088 |
majesty | +0.085 |
Neg logit contributions | |
ting | -0.098 |
course | -0.079 |
neath | -0.076 |
pped | -0.075 |
That | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
ting | +0.063 |
course | +0.048 |
neath | +0.046 |
pped | +0.045 |
That | +0.043 |
Neg logit contributions | |
packs | -0.095 |
uth | -0.092 |
eth | -0.091 |
aj | -0.086 |
majesty | -0.084 |
Token | village |
Token ID | 7404 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
ting | +0.064 |
course | +0.054 |
neath | +0.052 |
pped | +0.052 |
That | +0.050 |
Neg logit contributions | |
packs | -0.049 |
uth | -0.048 |
eth | -0.046 |
aj | -0.043 |
majesty | -0.042 |
Token | back |
Token ID | 736 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
packs | +0.081 |
uth | +0.081 |
eth | +0.079 |
aj | +0.074 |
majesty | +0.070 |
Neg logit contributions | |
ting | -0.089 |
course | -0.073 |
neath | -0.070 |
pped | -0.067 |
You | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
uth | +0.106 |
eth | +0.104 |
packs | +0.103 |
aj | +0.096 |
majesty | +0.092 |
Neg logit contributions | |
ting | -0.121 |
course | -0.099 |
neath | -0.096 |
pped | -0.091 |
You | -0.090 |
Token | its |
Token ID | 663 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
packs | +0.115 |
uth | +0.112 |
eth | +0.109 |
aj | +0.102 |
majesty | +0.100 |
Neg logit contributions | |
ting | -0.113 |
course | -0.091 |
neath | -0.088 |
pped | -0.087 |
That | -0.084 |
Token | former |
Token ID | 1966 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
eth | +0.044 |
packs | +0.043 |
uth | +0.040 |
aj | +0.038 |
ifi | +0.036 |
Neg logit contributions | |
ting | -0.060 |
course | -0.053 |
neath | -0.048 |
Good | -0.047 |
You | -0.046 |
Token | glory |
Token ID | 13476 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
eth | +0.273 |
packs | +0.271 |
ilot | +0.259 |
uffy | +0.254 |
uth | +0.247 |
Neg logit contributions | |
ting | -0.237 |
course | -0.227 |
neath | -0.193 |
Good | -0.180 |
elling | -0.176 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
packs | +0.104 |
uth | +0.101 |
eth | +0.099 |
aj | +0.092 |
majesty | +0.088 |
Neg logit contributions | |
ting | -0.134 |
course | -0.113 |
neath | -0.108 |
pped | -0.107 |
That | -0.104 |
Token | |
Token ID | 220 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
ting | +0.016 |
pped | +0.014 |
neath | +0.013 |
course | +0.013 |
That | +0.012 |
Neg logit contributions | |
packs | -0.012 |
uth | -0.012 |
eth | -0.012 |
aj | -0.011 |
patients | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
packs | +0.044 |
uth | +0.042 |
eth | +0.041 |
aj | +0.039 |
ies | +0.038 |
Neg logit contributions | |
ting | -0.044 |
neath | -0.036 |
course | -0.036 |
pped | -0.035 |
You | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
packs | +0.076 |
uth | +0.074 |
eth | +0.073 |
aj | +0.067 |
majesty | +0.064 |
Neg logit contributions | |
ting | -0.097 |
course | -0.080 |
neath | -0.077 |
pped | -0.077 |
You | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
ting | +0.012 |
course | +0.010 |
neath | +0.010 |
pped | +0.009 |
You | +0.009 |
Neg logit contributions | |
packs | -0.011 |
uth | -0.011 |
eth | -0.010 |
aj | -0.010 |
majesty | -0.009 |
Token | be |
Token ID | 307 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
packs | +0.117 |
uth | +0.116 |
eth | +0.111 |
aj | +0.108 |
majesty | +0.102 |
Neg logit contributions | |
ting | -0.118 |
course | -0.100 |
neath | -0.094 |
pped | -0.091 |
You | -0.089 |
Token | restored |
Token ID | 15032 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
uth | +0.037 |
packs | +0.037 |
eth | +0.036 |
aj | +0.033 |
majesty | +0.033 |
Neg logit contributions | |
ting | -0.034 |
course | -0.028 |
neath | -0.027 |
pped | -0.027 |
You | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
ting | +0.033 |
course | +0.026 |
neath | +0.025 |
pped | +0.025 |
You | +0.025 |
Neg logit contributions | |
uth | -0.030 |
packs | -0.029 |
eth | -0.028 |
aj | -0.027 |
majesty | -0.026 |
Token | its |
Token ID | 663 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
packs | +0.116 |
uth | +0.115 |
eth | +0.114 |
aj | +0.109 |
majesty | +0.102 |
Neg logit contributions | |
ting | -0.107 |
course | -0.089 |
neath | -0.083 |
pped | -0.080 |
You | -0.080 |
Token | former |
Token ID | 1966 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
eth | +0.037 |
packs | +0.036 |
uth | +0.036 |
aj | +0.034 |
ilot | +0.032 |
Neg logit contributions | |
ting | -0.051 |
course | -0.046 |
neath | -0.041 |
You | -0.040 |
Good | -0.040 |
Token | glory |
Token ID | 13476 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
eth | +0.263 |
packs | +0.255 |
uth | +0.254 |
ilot | +0.254 |
uffy | +0.248 |
Neg logit contributions | |
ting | -0.242 |
course | -0.230 |
neath | -0.197 |
causing | -0.180 |
elling | -0.178 |
Token | ." |
Token ID | 526 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
uth | +0.107 |
packs | +0.105 |
eth | +0.103 |
aj | +0.095 |
majesty | +0.093 |
Neg logit contributions | |
ting | -0.134 |
course | -0.112 |
neath | -0.107 |
pped | -0.105 |
You | -0.103 |
Token | |
Token ID | 220 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
packs | +0.013 |
uth | +0.013 |
eth | +0.012 |
aj | +0.012 |
majesty | +0.011 |
Neg logit contributions | |
ting | -0.012 |
course | -0.010 |
neath | -0.010 |
That | -0.010 |
You | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
packs | +0.053 |
uth | +0.051 |
eth | +0.047 |
patients | +0.047 |
majesty | +0.047 |
Neg logit contributions | |
ting | -0.037 |
neath | -0.031 |
You | -0.030 |
That | -0.029 |
course | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
packs | +0.093 |
uth | +0.088 |
eth | +0.084 |
aj | +0.082 |
patients | +0.081 |
Neg logit contributions | |
ting | -0.084 |
course | -0.071 |
That | -0.068 |
neath | -0.067 |
You | -0.067 |
Token | back |
Token ID | 736 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
ting | +0.067 |
course | +0.053 |
pped | +0.052 |
neath | +0.051 |
That | +0.050 |
Neg logit contributions | |
packs | -0.074 |
uth | -0.071 |
eth | -0.069 |
aj | -0.065 |
ies | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
packs | +0.102 |
uth | +0.098 |
eth | +0.096 |
aj | +0.091 |
majesty | +0.088 |
Neg logit contributions | |
ting | -0.089 |
course | -0.071 |
neath | -0.068 |
pped | -0.068 |
That | -0.066 |
Token | village |
Token ID | 7404 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
ting | +0.070 |
pped | +0.056 |
neath | +0.056 |
course | +0.056 |
That | +0.053 |
Neg logit contributions | |
packs | -0.051 |
uth | -0.051 |
eth | -0.049 |
aj | -0.045 |
majesty | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
packs | +0.076 |
uth | +0.075 |
eth | +0.074 |
aj | +0.070 |
majesty | +0.067 |
Neg logit contributions | |
ting | -0.081 |
course | -0.067 |
neath | -0.064 |
pped | -0.062 |
That | -0.061 |
Token | its |
Token ID | 663 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
packs | +0.106 |
uth | +0.102 |
eth | +0.100 |
aj | +0.093 |
patients | +0.093 |
Neg logit contributions | |
ting | -0.099 |
course | -0.079 |
pped | -0.077 |
neath | -0.077 |
That | -0.074 |
Token | former |
Token ID | 1966 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
eth | +0.040 |
packs | +0.040 |
uth | +0.037 |
aj | +0.035 |
ilot | +0.034 |
Neg logit contributions | |
ting | -0.051 |
course | -0.045 |
neath | -0.040 |
Any | -0.039 |
Good | -0.039 |
Token | state |
Token ID | 1181 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
packs | +0.268 |
eth | +0.263 |
ilot | +0.250 |
uffy | +0.246 |
uth | +0.241 |
Neg logit contributions | |
ting | -0.240 |
course | -0.236 |
neath | -0.199 |
Good | -0.189 |
pped | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
packs | +0.026 |
uth | +0.025 |
eth | +0.024 |
aj | +0.023 |
majesty | +0.022 |
Neg logit contributions | |
ting | -0.033 |
course | -0.028 |
neath | -0.027 |
pped | -0.026 |
That | -0.026 |
Token | With |
Token ID | 2080 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ting | +0.049 |
course | +0.041 |
pped | +0.040 |
neath | +0.038 |
wheel | +0.037 |
Neg logit contributions | |
packs | -0.036 |
uth | -0.035 |
eth | -0.034 |
aj | -0.030 |
majesty | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
ting | +0.045 |
pped | +0.033 |
neath | +0.033 |
course | +0.033 |
You | +0.032 |
Neg logit contributions | |
packs | -0.053 |
uth | -0.051 |
eth | -0.049 |
aj | -0.046 |
patients | -0.046 |
Token | help |
Token ID | 1037 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
ting | +0.058 |
pped | +0.048 |
neath | +0.047 |
course | +0.045 |
That | +0.044 |
Neg logit contributions | |
uth | -0.041 |
eth | -0.040 |
packs | -0.040 |
majesty | -0.037 |
patients | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
ting | +0.082 |
course | +0.065 |
neath | +0.061 |
pped | +0.059 |
That | +0.057 |
Neg logit contributions | |
packs | -0.111 |
uth | -0.108 |
eth | -0.107 |
aj | -0.102 |
majesty | -0.098 |
Token | tree |
Token ID | 5509 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ting | +0.071 |
course | +0.060 |
neath | +0.056 |
You | +0.054 |
pped | +0.054 |
Neg logit contributions | |
packs | -0.070 |
uth | -0.067 |
eth | -0.067 |
aj | -0.063 |
majesty | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
packs | +0.027 |
uth | +0.026 |
eth | +0.025 |
aj | +0.024 |
majesty | +0.023 |
Neg logit contributions | |
ting | -0.030 |
course | -0.025 |
neath | -0.024 |
pped | -0.024 |
That | -0.023 |
Token | its |
Token ID | 663 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
packs | +0.098 |
uth | +0.095 |
eth | +0.093 |
aj | +0.087 |
majesty | +0.085 |
Neg logit contributions | |
ting | -0.095 |
course | -0.076 |
neath | -0.073 |
pped | -0.073 |
That | -0.070 |
Token | once |
Token ID | 1752 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
packs | +0.018 |
eth | +0.018 |
uth | +0.016 |
aj | +0.016 |
ilot | +0.015 |
Neg logit contributions | |
ting | -0.023 |
course | -0.021 |
neath | -0.018 |
Good | -0.018 |
Any | -0.018 |
Token | former |
Token ID | 1966 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
packs | +0.175 |
uth | +0.172 |
eth | +0.169 |
aj | +0.160 |
majesty | +0.154 |
Neg logit contributions | |
ting | -0.167 |
course | -0.140 |
neath | -0.131 |
pped | -0.128 |
That | -0.125 |
Token | beauty |
Token ID | 8737 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
eth | +0.257 |
packs | +0.255 |
ilot | +0.234 |
uth | +0.231 |
uffy | +0.229 |
Neg logit contributions | |
ting | -0.253 |
course | -0.247 |
neath | -0.197 |
causing | -0.183 |
Good | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
packs | +0.038 |
uth | +0.036 |
eth | +0.035 |
aj | +0.033 |
ies | +0.031 |
Neg logit contributions | |
ting | -0.053 |
course | -0.044 |
neath | -0.043 |
pped | -0.043 |
That | -0.042 |
Token | He |
Token ID | 679 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
ting | +0.038 |
course | +0.031 |
neath | +0.029 |
pped | +0.028 |
That | +0.028 |
Neg logit contributions | |
packs | -0.042 |
uth | -0.041 |
eth | -0.040 |
aj | -0.038 |
ies | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | +8.59e-03 |
Pos logit contributions | |
ting | +0.006 |
course | +0.005 |
neath | +0.004 |
pped | +0.004 |
You | +0.004 |
Neg logit contributions | |
packs | -0.007 |
uth | -0.007 |
eth | -0.007 |
aj | -0.006 |
majesty | -0.006 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
ting | +0.015 |
course | +0.012 |
neath | +0.011 |
pped | +0.011 |
That | +0.010 |
Neg logit contributions | |
packs | -0.019 |
uth | -0.019 |
eth | -0.018 |
aj | -0.017 |
majesty | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
packs | +0.034 |
uth | +0.032 |
eth | +0.032 |
aj | +0.028 |
ies | +0.028 |
Neg logit contributions | |
ting | -0.053 |
course | -0.045 |
pped | -0.044 |
neath | -0.044 |
You | -0.043 |
Token | leaving |
Token ID | 4305 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
packs | +0.039 |
uth | +0.036 |
eth | +0.034 |
aj | +0.033 |
ies | +0.033 |
Neg logit contributions | |
ting | -0.050 |
course | -0.042 |
pped | -0.042 |
Hey | -0.041 |
neath | -0.041 |
Token | it |
Token ID | 340 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
ting | +0.011 |
course | +0.009 |
pped | +0.009 |
neath | +0.009 |
That | +0.008 |
Neg logit contributions | |
packs | -0.013 |
uth | -0.013 |
eth | -0.012 |
aj | -0.011 |
ies | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
ting | +0.059 |
course | +0.049 |
neath | +0.046 |
That | +0.045 |
You | +0.045 |
Neg logit contributions | |
packs | -0.060 |
uth | -0.055 |
eth | -0.055 |
aj | -0.053 |
ies | -0.052 |
Token | its |
Token ID | 663 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
packs | +0.065 |
uth | +0.063 |
eth | +0.061 |
majesty | +0.057 |
aj | +0.056 |
Neg logit contributions | |
ting | -0.071 |
course | -0.056 |
pped | -0.055 |
neath | -0.055 |
That | -0.053 |
Token | former |
Token ID | 1966 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
packs | +0.025 |
eth | +0.025 |
uth | +0.024 |
aj | +0.022 |
ait | +0.021 |
Neg logit contributions | |
ting | -0.033 |
course | -0.028 |
neath | -0.027 |
Good | -0.026 |
You | -0.025 |
Token | state |
Token ID | 1181 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
packs | +0.237 |
eth | +0.237 |
uth | +0.226 |
uffy | +0.221 |
ilot | +0.219 |
Neg logit contributions | |
ting | -0.247 |
course | -0.219 |
neath | -0.201 |
pped | -0.191 |
Good | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
packs | +0.017 |
uth | +0.016 |
eth | +0.016 |
aj | +0.014 |
ies | +0.014 |
Neg logit contributions | |
ting | -0.024 |
course | -0.021 |
neath | -0.020 |
pped | -0.019 |
That | -0.019 |
Token | |
Token ID | 220 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
ting | +0.029 |
course | +0.024 |
pped | +0.023 |
neath | +0.023 |
That | +0.022 |
Neg logit contributions | |
packs | -0.026 |
uth | -0.025 |
eth | -0.024 |
aj | -0.023 |
majesty | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
packs | +0.035 |
uth | +0.034 |
eth | +0.033 |
aj | +0.031 |
ies | +0.030 |
Neg logit contributions | |
ting | -0.038 |
course | -0.031 |
neath | -0.031 |
pped | -0.030 |
You | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
packs | +0.065 |
uth | +0.063 |
eth | +0.061 |
aj | +0.057 |
majesty | +0.055 |
Neg logit contributions | |
ting | -0.080 |
course | -0.067 |
neath | -0.064 |
pped | -0.063 |
That | -0.062 |
Token | be |
Token ID | 307 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
packs | +0.051 |
uth | +0.049 |
eth | +0.049 |
aj | +0.045 |
majesty | +0.042 |
Neg logit contributions | |
ting | -0.067 |
course | -0.057 |
neath | -0.054 |
pped | -0.053 |
You | -0.053 |
Token | there |
Token ID | 612 |
Feature activation | -3.92e-04 |
Pos logit contributions | |
packs | +0.005 |
uth | +0.005 |
eth | +0.005 |
aj | +0.005 |
majesty | +0.005 |
Neg logit contributions | |
ting | -0.005 |
course | -0.004 |
neath | -0.004 |
pped | -0.003 |
You | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
packs | +0.001 |
uth | +0.001 |
eth | +0.001 |
aj | +0.001 |
majesty | +0.001 |
Neg logit contributions | |
ting | -0.001 |
course | -0.001 |
neath | -0.001 |
pped | -0.001 |
That | -0.001 |
Token | support |
Token ID | 1104 |
Feature activation | -1.11e-04 |
Pos logit contributions | |
packs | +0.087 |
uth | +0.083 |
eth | +0.082 |
aj | +0.078 |
majesty | +0.073 |
Neg logit contributions | |
ting | -0.090 |
course | -0.077 |
neath | -0.072 |
pped | -0.071 |
You | -0.069 |
Token | her |
Token ID | 607 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
packs | +0.000 |
eth | +0.000 |
uth | +0.000 |
aj | +0.000 |
majesty | +0.000 |
Neg logit contributions | |
ting | -0.000 |
course | -0.000 |
You | -0.000 |
neath | -0.000 |
That | -0.000 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
eth | +0.144 |
uth | +0.143 |
packs | +0.139 |
ifi | +0.127 |
aj | +0.126 |
Neg logit contributions | |
ting | -0.162 |
course | -0.133 |
neath | -0.123 |
You | -0.119 |
Any | -0.119 |
Token | n |
Token ID | 77 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
packs | +0.258 |
uth | +0.249 |
eth | +0.244 |
aj | +0.230 |
majesty | +0.221 |
Neg logit contributions | |
ting | -0.263 |
course | -0.217 |
neath | -0.206 |
pped | -0.203 |
That | -0.198 |
Token | ics |
Token ID | 873 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
packs | +0.056 |
uth | +0.054 |
eth | +0.053 |
aj | +0.049 |
majesty | +0.047 |
Neg logit contributions | |
ting | -0.074 |
course | -0.062 |
neath | -0.060 |
pped | -0.059 |
That | -0.057 |
Token | -- |
Token ID | 438 |
Feature activation | +7.69e-03 |
Pos logit contributions | |
packs | +0.047 |
uth | +0.046 |
eth | +0.045 |
aj | +0.043 |
majesty | +0.041 |
Neg logit contributions | |
ting | -0.051 |
course | -0.042 |
neath | -0.040 |
pped | -0.039 |
You | -0.038 |
Token | no |
Token ID | 3919 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
ting | +0.014 |
course | +0.011 |
neath | +0.011 |
pped | +0.010 |
Good | +0.010 |
Neg logit contributions | |
packs | -0.016 |
uth | -0.016 |
eth | -0.015 |
aj | -0.014 |
patients | -0.014 |
Token | matter |
Token ID | 2300 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
packs | +0.058 |
uth | +0.057 |
eth | +0.054 |
patients | +0.052 |
ies | +0.052 |
Neg logit contributions | |
ting | -0.064 |
neath | -0.052 |
That | -0.049 |
pped | -0.049 |
Good | -0.048 |
Token | were |
Token ID | 547 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ting | +0.026 |
course | +0.021 |
neath | +0.020 |
pped | +0.020 |
That | +0.019 |
Neg logit contributions | |
packs | -0.030 |
uth | -0.029 |
eth | -0.028 |
aj | -0.026 |
patients | -0.026 |
Token | probably |
Token ID | 2192 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
packs | +0.027 |
uth | +0.026 |
eth | +0.026 |
aj | +0.024 |
majesty | +0.024 |
Neg logit contributions | |
ting | -0.021 |
course | -0.017 |
neath | -0.016 |
pped | -0.016 |
You | -0.015 |
Token | celebrating |
Token ID | 17499 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
packs | +0.030 |
uth | +0.030 |
eth | +0.029 |
aj | +0.027 |
majesty | +0.026 |
Neg logit contributions | |
ting | -0.026 |
course | -0.021 |
neath | -0.020 |
pped | -0.020 |
You | -0.019 |
Token | their |
Token ID | 511 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
packs | +0.041 |
uth | +0.040 |
eth | +0.040 |
aj | +0.037 |
majesty | +0.036 |
Neg logit contributions | |
ting | -0.042 |
course | -0.035 |
neath | -0.033 |
pped | -0.032 |
That | -0.032 |
Token | own |
Token ID | 898 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
eth | +0.085 |
packs | +0.085 |
uth | +0.082 |
aj | +0.073 |
ifi | +0.073 |
Neg logit contributions | |
ting | -0.111 |
course | -0.098 |
You | -0.091 |
That | -0.089 |
Any | -0.088 |
Token | birth |
Token ID | 4082 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
eth | +0.090 |
packs | +0.089 |
uth | +0.088 |
aj | +0.079 |
ifi | +0.077 |
Neg logit contributions | |
ting | -0.115 |
course | -0.101 |
You | -0.092 |
neath | -0.092 |
That | -0.091 |
Token | days |
Token ID | 12545 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
uth | +0.172 |
eth | +0.154 |
majesty | +0.151 |
packs | +0.147 |
aj | +0.142 |
Neg logit contributions | |
ting | -0.344 |
course | -0.292 |
pped | -0.283 |
neath | -0.283 |
You | -0.282 |
Token | . |
Token ID | 13 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
packs | +0.065 |
eth | +0.060 |
uth | +0.060 |
aj | +0.055 |
ies | +0.053 |
Neg logit contributions | |
ting | -0.100 |
course | -0.085 |
neath | -0.084 |
pped | -0.083 |
That | -0.080 |
Token | Just |
Token ID | 2329 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
ting | +0.017 |
course | +0.014 |
neath | +0.013 |
That | +0.013 |
You | +0.013 |
Neg logit contributions | |
packs | -0.021 |
uth | -0.021 |
eth | -0.020 |
ies | -0.020 |
aj | -0.020 |
Token | when |
Token ID | 618 |
Feature activation | +9.51e-03 |
Pos logit contributions | |
packs | +0.021 |
eth | +0.020 |
uth | +0.020 |
aj | +0.019 |
majesty | +0.018 |
Neg logit contributions | |
ting | -0.014 |
course | -0.011 |
neath | -0.010 |
pped | -0.010 |
You | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
ting | +0.015 |
course | +0.012 |
neath | +0.011 |
That | +0.010 |
You | +0.010 |
Neg logit contributions | |
packs | -0.023 |
uth | -0.022 |
eth | -0.022 |
aj | -0.021 |
majesty | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
uth | +0.155 |
ifi | +0.152 |
packs | +0.148 |
eth | +0.143 |
iri | +0.138 |
Neg logit contributions | |
ting | -0.097 |
Any | -0.066 |
course | -0.063 |
causing | -0.063 |
wheel | -0.063 |
Token | ready |
Token ID | 3492 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
packs | +0.013 |
uth | +0.013 |
eth | +0.013 |
aj | +0.012 |
majesty | +0.011 |
Neg logit contributions | |
ting | -0.017 |
course | -0.014 |
neath | -0.013 |
That | -0.013 |
You | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
packs | +0.053 |
uth | +0.052 |
eth | +0.050 |
aj | +0.047 |
majesty | +0.045 |
Neg logit contributions | |
ting | -0.059 |
course | -0.048 |
neath | -0.046 |
pped | -0.045 |
That | -0.044 |
Token | have |
Token ID | 423 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
packs | +0.077 |
uth | +0.074 |
eth | +0.073 |
aj | +0.068 |
majesty | +0.066 |
Neg logit contributions | |
ting | -0.080 |
course | -0.066 |
neath | -0.063 |
pped | -0.062 |
That | -0.061 |
Token | more |
Token ID | 517 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
ting | +0.120 |
neath | +0.092 |
course | +0.088 |
pped | +0.087 |
That | +0.084 |
Neg logit contributions | |
packs | -0.133 |
uth | -0.128 |
eth | -0.119 |
aj | -0.118 |
patients | -0.113 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
eth | +0.140 |
uth | +0.124 |
spine | +0.118 |
packs | +0.118 |
ifi | +0.118 |
Neg logit contributions | |
course | -0.081 |
ting | -0.077 |
Any | -0.065 |
You | -0.065 |
Good | -0.057 |
Token | n |
Token ID | 77 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
uth | +0.225 |
packs | +0.223 |
eth | +0.218 |
aj | +0.202 |
majesty | +0.194 |
Neg logit contributions | |
ting | -0.277 |
neath | -0.220 |
course | -0.218 |
pped | -0.210 |
You | -0.209 |
Token | ics |
Token ID | 873 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
packs | +0.028 |
uth | +0.027 |
eth | +0.026 |
aj | +0.024 |
ies | +0.023 |
Neg logit contributions | |
ting | -0.041 |
course | -0.035 |
neath | -0.034 |
pped | -0.033 |
That | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
uth | +0.028 |
eth | +0.028 |
packs | +0.027 |
aj | +0.026 |
majesty | +0.025 |
Neg logit contributions | |
ting | -0.027 |
course | -0.023 |
You | -0.020 |
pped | -0.020 |
neath | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
uth | +0.114 |
eth | +0.113 |
packs | +0.109 |
aj | +0.108 |
majesty | +0.106 |
Neg logit contributions | |
ting | -0.051 |
course | -0.044 |
neath | -0.039 |
You | -0.034 |
That | -0.033 |
Token | future |
Token ID | 2003 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
ting | +0.062 |
pped | +0.051 |
neath | +0.048 |
wheel | +0.047 |
course | +0.045 |
Neg logit contributions | |
packs | -0.042 |
uth | -0.041 |
eth | -0.040 |
aj | -0.039 |
majesty | -0.036 |
Token | his |
Token ID | 465 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
ting | +0.008 |
course | +0.006 |
neath | +0.006 |
pped | +0.006 |
That | +0.006 |
Neg logit contributions | |
packs | -0.008 |
uth | -0.008 |
eth | -0.007 |
aj | -0.007 |
majesty | -0.007 |
Token | parents |
Token ID | 3397 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
packs | +0.093 |
eth | +0.081 |
ighed | +0.078 |
aj | +0.075 |
uth | +0.073 |
Neg logit contributions | |
ting | -0.126 |
course | -0.112 |
That | -0.107 |
Good | -0.106 |
� | -0.102 |
Token | about |
Token ID | 546 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
packs | +0.042 |
uth | +0.039 |
eth | +0.039 |
ies | +0.037 |
patients | +0.036 |
Neg logit contributions | |
ting | -0.047 |
neath | -0.039 |
course | -0.039 |
pped | -0.038 |
That | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
packs | +0.047 |
uth | +0.046 |
eth | +0.042 |
patients | +0.042 |
majesty | +0.041 |
Neg logit contributions | |
ting | -0.044 |
pped | -0.035 |
neath | -0.035 |
course | -0.034 |
That | -0.033 |
Token | mysterious |
Token ID | 11428 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ting | +0.079 |
course | +0.069 |
You | +0.061 |
neath | +0.060 |
That | +0.060 |
Neg logit contributions | |
packs | -0.075 |
eth | -0.071 |
uth | -0.068 |
aj | -0.066 |
ies | -0.060 |
Token | Gor |
Token ID | 19097 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
packs | +0.034 |
eth | +0.033 |
aj | +0.032 |
uth | +0.030 |
ouses | +0.028 |
Neg logit contributions | |
ting | -0.029 |
course | -0.028 |
rising | -0.021 |
Good | -0.021 |
Hey | -0.020 |
Token | illa |
Token ID | 5049 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
eth | +0.262 |
packs | +0.249 |
aj | +0.248 |
majesty | +0.241 |
tant | +0.234 |
Neg logit contributions | |
ting | -0.239 |
course | -0.185 |
pped | -0.173 |
neath | -0.168 |
That | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
packs | +0.073 |
uth | +0.071 |
eth | +0.069 |
aj | +0.065 |
ies | +0.063 |
Neg logit contributions | |
ting | -0.082 |
course | -0.068 |
neath | -0.066 |
pped | -0.065 |
That | -0.063 |
Token | His |
Token ID | 2399 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
ting | +0.036 |
course | +0.029 |
neath | +0.028 |
That | +0.027 |
pped | +0.027 |
Neg logit contributions | |
packs | -0.032 |
uth | -0.031 |
eth | -0.030 |
aj | -0.028 |
majesty | -0.027 |
Token | parents |
Token ID | 3397 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
packs | +0.086 |
eth | +0.080 |
heads | +0.071 |
ifi | +0.071 |
uth | +0.071 |
Neg logit contributions | |
ting | -0.083 |
course | -0.072 |
That | -0.067 |
You | -0.066 |
Good | -0.065 |
Token | were |
Token ID | 547 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
packs | +0.032 |
uth | +0.032 |
eth | +0.031 |
ies | +0.029 |
aj | +0.028 |
Neg logit contributions | |
ting | -0.036 |
neath | -0.029 |
course | -0.029 |
pped | -0.028 |
Good | -0.028 |
Token | decided |
Token ID | 3066 |
Feature activation | +6.44e-03 |
Pos logit contributions | |
packs | +0.021 |
uth | +0.021 |
eth | +0.020 |
aj | +0.019 |
ies | +0.019 |
Neg logit contributions | |
ting | -0.019 |
course | -0.015 |
neath | -0.015 |
pped | -0.014 |
You | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
ting | +0.016 |
course | +0.013 |
neath | +0.013 |
pped | +0.013 |
Looks | +0.012 |
Neg logit contributions | |
packs | -0.009 |
uth | -0.009 |
eth | -0.009 |
aj | -0.008 |
ies | -0.008 |
Token | share |
Token ID | 2648 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
packs | +0.067 |
uth | +0.065 |
eth | +0.064 |
aj | +0.060 |
majesty | +0.057 |
Neg logit contributions | |
ting | -0.073 |
course | -0.060 |
neath | -0.058 |
pped | -0.057 |
That | -0.055 |
Token | his |
Token ID | 465 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
ting | +0.010 |
course | +0.008 |
neath | +0.008 |
pped | +0.008 |
That | +0.007 |
Neg logit contributions | |
packs | -0.012 |
uth | -0.012 |
eth | -0.012 |
aj | -0.011 |
majesty | -0.011 |
Token | sa |
Token ID | 473 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
packs | +0.160 |
uth | +0.154 |
eth | +0.149 |
ifi | +0.134 |
ighed | +0.131 |
Neg logit contributions | |
ting | -0.158 |
course | -0.134 |
Good | -0.124 |
neath | -0.123 |
You | -0.122 |
Token | us |
Token ID | 385 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
packs | +0.171 |
uth | +0.168 |
eth | +0.154 |
majesty | +0.151 |
aj | +0.147 |
Neg logit contributions | |
ting | -0.177 |
pped | -0.137 |
course | -0.134 |
neath | -0.130 |
You | -0.128 |
Token | ages |
Token ID | 1095 |
Feature activation | -7.80e-03 |
Pos logit contributions | |
packs | +0.205 |
uth | +0.190 |
eth | +0.182 |
ifi | +0.167 |
apartment | +0.165 |
Neg logit contributions | |
ting | -0.279 |
You | -0.226 |
you | -0.222 |
That | -0.220 |
course | -0.214 |
Token | with |
Token ID | 351 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
packs | +0.014 |
uth | +0.013 |
eth | +0.013 |
aj | +0.012 |
ies | +0.012 |
Neg logit contributions | |
ting | -0.017 |
course | -0.014 |
neath | -0.013 |
pped | -0.013 |
That | -0.013 |
Token | his |
Token ID | 465 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
packs | +0.039 |
uth | +0.038 |
eth | +0.037 |
aj | +0.035 |
majesty | +0.034 |
Neg logit contributions | |
ting | -0.033 |
course | -0.026 |
neath | -0.025 |
pped | -0.024 |
That | -0.024 |
Token | brother |
Token ID | 3956 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
packs | +0.145 |
eth | +0.126 |
uth | +0.123 |
heads | +0.115 |
ifi | +0.115 |
Neg logit contributions | |
ting | -0.176 |
course | -0.148 |
Any | -0.144 |
Good | -0.136 |
You | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
packs | +0.022 |
uth | +0.021 |
eth | +0.021 |
aj | +0.019 |
majesty | +0.019 |
Neg logit contributions | |
ting | -0.029 |
course | -0.024 |
neath | -0.023 |
pped | -0.022 |
You | -0.022 |
Token | promised |
Token ID | 8072 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
packs | +0.000 |
uth | +0.000 |
eth | +0.000 |
aj | +0.000 |
majesty | +0.000 |
Neg logit contributions | |
ting | -0.000 |
course | -0.000 |
neath | -0.000 |
pped | -0.000 |
That | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
packs | +0.015 |
uth | +0.015 |
eth | +0.014 |
aj | +0.013 |
majesty | +0.013 |
Neg logit contributions | |
ting | -0.018 |
course | -0.015 |
neath | -0.014 |
pped | -0.014 |
That | -0.014 |
Token | celebrate |
Token ID | 10648 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
packs | +0.095 |
uth | +0.090 |
eth | +0.088 |
aj | +0.085 |
ies | +0.080 |
Neg logit contributions | |
ting | -0.092 |
course | -0.079 |
pped | -0.073 |
neath | -0.073 |
That | -0.071 |
Token | all |
Token ID | 477 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
packs | +0.065 |
eth | +0.064 |
uth | +0.064 |
aj | +0.059 |
majesty | +0.058 |
Neg logit contributions | |
ting | -0.058 |
course | -0.047 |
neath | -0.043 |
You | -0.042 |
That | -0.042 |
Token | her |
Token ID | 607 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
packs | +0.042 |
uth | +0.040 |
eth | +0.039 |
aj | +0.037 |
ies | +0.036 |
Neg logit contributions | |
ting | -0.034 |
course | -0.027 |
pped | -0.026 |
neath | -0.026 |
That | -0.025 |
Token | birth |
Token ID | 4082 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
eth | +0.154 |
packs | +0.147 |
uth | +0.144 |
ifi | +0.132 |
aj | +0.130 |
Neg logit contributions | |
ting | -0.176 |
course | -0.163 |
Any | -0.144 |
You | -0.144 |
That | -0.142 |
Token | days |
Token ID | 12545 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
uth | +0.177 |
eth | +0.165 |
majesty | +0.155 |
packs | +0.154 |
aj | +0.151 |
Neg logit contributions | |
ting | -0.305 |
course | -0.255 |
pped | -0.247 |
You | -0.247 |
neath | -0.245 |
Token | together |
Token ID | 1978 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
packs | +0.052 |
uth | +0.049 |
eth | +0.049 |
aj | +0.046 |
ies | +0.044 |
Neg logit contributions | |
ting | -0.062 |
course | -0.052 |
neath | -0.050 |
pped | -0.050 |
That | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
packs | +0.105 |
uth | +0.102 |
eth | +0.100 |
aj | +0.093 |
majesty | +0.089 |
Neg logit contributions | |
ting | -0.139 |
course | -0.117 |
neath | -0.111 |
pped | -0.110 |
You | -0.108 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
ting | +0.037 |
course | +0.030 |
pped | +0.029 |
neath | +0.028 |
You | +0.027 |
Neg logit contributions | |
packs | -0.034 |
uth | -0.033 |
eth | -0.032 |
aj | -0.030 |
majesty | -0.028 |
Token | Once |
Token ID | 7454 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
packs | +0.011 |
uth | +0.010 |
eth | +0.010 |
aj | +0.009 |
majesty | +0.009 |
Neg logit contributions | |
ting | -0.011 |
course | -0.009 |
pped | -0.009 |
neath | -0.009 |
That | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
packs | +0.011 |
eth | +0.010 |
uth | +0.010 |
aj | +0.009 |
ies | +0.009 |
Neg logit contributions | |
ting | -0.010 |
course | -0.008 |
pped | -0.008 |
neath | -0.008 |
You | -0.008 |
Token | n |
Token ID | 299 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
ting | +0.037 |
course | +0.031 |
neath | +0.030 |
You | +0.029 |
That | +0.028 |
Neg logit contributions | |
uth | -0.030 |
packs | -0.029 |
eth | -0.028 |
majesty | -0.026 |
aj | -0.026 |
Token | ooks |
Token ID | 31085 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
uth | +0.093 |
packs | +0.089 |
eth | +0.082 |
patients | +0.080 |
allowance | +0.077 |
Neg logit contributions | |
ting | -0.186 |
pped | -0.163 |
neath | -0.159 |
course | -0.155 |
Any | -0.150 |
Token | and |
Token ID | 290 |
Feature activation | -9.43e-03 |
Pos logit contributions | |
uth | +0.109 |
packs | +0.105 |
eth | +0.105 |
majesty | +0.100 |
aj | +0.098 |
Neg logit contributions | |
ting | -0.092 |
course | -0.069 |
pped | -0.067 |
neath | -0.066 |
You | -0.059 |
Token | cr |
Token ID | 1067 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
packs | +0.018 |
uth | +0.017 |
eth | +0.017 |
aj | +0.016 |
majesty | +0.015 |
Neg logit contributions | |
ting | -0.019 |
course | -0.016 |
neath | -0.015 |
pped | -0.015 |
That | -0.014 |
Token | ann |
Token ID | 1236 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
packs | +0.031 |
uth | +0.030 |
eth | +0.029 |
aj | +0.027 |
majesty | +0.027 |
Neg logit contributions | |
ting | -0.041 |
course | -0.034 |
pped | -0.033 |
neath | -0.033 |
That | -0.031 |
Token | ies |
Token ID | 444 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
uth | +0.100 |
ifi | +0.088 |
packs | +0.083 |
eth | +0.080 |
majesty | +0.077 |
Neg logit contributions | |
ting | -0.358 |
pped | -0.306 |
course | -0.295 |
hed | -0.290 |
neath | -0.287 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
packs | +0.049 |
uth | +0.047 |
eth | +0.046 |
aj | +0.043 |
majesty | +0.041 |
Neg logit contributions | |
ting | -0.067 |
course | -0.057 |
neath | -0.055 |
pped | -0.054 |
That | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
ting | +0.030 |
course | +0.024 |
neath | +0.024 |
That | +0.024 |
You | +0.023 |
Neg logit contributions | |
packs | -0.033 |
uth | -0.032 |
eth | -0.031 |
aj | -0.030 |
ies | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
packs | +0.079 |
uth | +0.075 |
eth | +0.072 |
aj | +0.070 |
ies | +0.070 |
Neg logit contributions | |
ting | -0.069 |
course | -0.059 |
That | -0.057 |
neath | -0.057 |
You | -0.055 |
Token | After |
Token ID | 3260 |
Feature activation | -1.56e-03 |
Pos logit contributions | |
uth | +0.054 |
packs | +0.053 |
eth | +0.053 |
aj | +0.048 |
ilot | +0.047 |
Neg logit contributions | |
ting | -0.057 |
course | -0.044 |
neath | -0.042 |
pped | -0.041 |
wheel | -0.039 |
Token | on |
Token ID | 319 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
uth | +0.139 |
packs | +0.133 |
eth | +0.133 |
aj | +0.124 |
ifi | +0.120 |
Neg logit contributions | |
ting | -0.124 |
course | -0.101 |
neath | -0.092 |
You | -0.091 |
pped | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
packs | +0.048 |
uth | +0.046 |
eth | +0.046 |
aj | +0.043 |
majesty | +0.041 |
Neg logit contributions | |
ting | -0.047 |
course | -0.039 |
neath | -0.037 |
pped | -0.036 |
That | -0.035 |
Token | row |
Token ID | 5752 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
ting | +0.096 |
course | +0.079 |
neath | +0.078 |
pped | +0.078 |
That | +0.074 |
Neg logit contributions | |
packs | -0.071 |
uth | -0.069 |
eth | -0.067 |
aj | -0.062 |
patients | -0.061 |
Token | of |
Token ID | 286 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
packs | +0.011 |
eth | +0.010 |
uth | +0.010 |
aj | +0.009 |
ies | +0.009 |
Neg logit contributions | |
ting | -0.013 |
course | -0.011 |
neath | -0.011 |
pped | -0.011 |
That | -0.011 |
Token | books |
Token ID | 3835 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
eth | +0.010 |
uth | +0.009 |
packs | +0.009 |
aj | +0.009 |
ies | +0.008 |
Neg logit contributions | |
ting | -0.011 |
course | -0.010 |
neath | -0.009 |
You | -0.009 |
That | -0.008 |
Token | hel |
Token ID | 2978 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
packs | +0.053 |
eth | +0.049 |
uth | +0.048 |
aj | +0.045 |
ies | +0.043 |
Neg logit contributions | |
ting | -0.060 |
course | -0.050 |
neath | -0.048 |
pped | -0.047 |
You | -0.047 |
Token | ves |
Token ID | 1158 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
eth | +0.190 |
aj | +0.189 |
uth | +0.187 |
packs | +0.180 |
majesty | +0.178 |
Neg logit contributions | |
ting | -0.258 |
course | -0.218 |
pped | -0.211 |
neath | -0.204 |
you | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ting | +0.028 |
course | +0.024 |
neath | +0.023 |
That | +0.023 |
pped | +0.023 |
Neg logit contributions | |
packs | -0.024 |
eth | -0.022 |
uth | -0.022 |
ies | -0.020 |
aj | -0.020 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
ting | +0.019 |
course | +0.016 |
neath | +0.015 |
That | +0.015 |
You | +0.015 |
Neg logit contributions | |
packs | -0.023 |
uth | -0.022 |
eth | -0.022 |
aj | -0.021 |
ies | -0.020 |
Token | Tom |
Token ID | 13787 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
packs | +0.015 |
uth | +0.014 |
eth | +0.014 |
aj | +0.013 |
majesty | +0.012 |
Neg logit contributions | |
ting | -0.017 |
course | -0.014 |
pped | -0.014 |
neath | -0.014 |
That | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
packs | +0.005 |
uth | +0.004 |
eth | +0.004 |
aj | +0.004 |
majesty | +0.004 |
Neg logit contributions | |
ting | -0.003 |
course | -0.003 |
neath | -0.002 |
pped | -0.002 |
That | -0.002 |
Token | box |
Token ID | 3091 |
Feature activation | -4.65e-03 |
Pos logit contributions | |
ting | +0.078 |
course | +0.064 |
neath | +0.061 |
pped | +0.059 |
That | +0.058 |
Neg logit contributions | |
packs | -0.081 |
uth | -0.079 |
eth | -0.077 |
aj | -0.073 |
majesty | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
uth | +0.009 |
packs | +0.009 |
eth | +0.009 |
aj | +0.009 |
majesty | +0.008 |
Neg logit contributions | |
ting | -0.009 |
course | -0.007 |
neath | -0.007 |
pped | -0.007 |
That | -0.007 |
Token | share |
Token ID | 2648 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
ting | +0.078 |
course | +0.066 |
pped | +0.062 |
neath | +0.062 |
That | +0.061 |
Neg logit contributions | |
packs | -0.062 |
uth | -0.058 |
eth | -0.057 |
aj | -0.054 |
majesty | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
ting | +0.008 |
course | +0.006 |
neath | +0.005 |
That | +0.005 |
You | +0.005 |
Neg logit contributions | |
eth | -0.014 |
uth | -0.014 |
packs | -0.014 |
aj | -0.013 |
majesty | -0.013 |
Token | ch |
Token ID | 442 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
ting | +0.074 |
course | +0.063 |
neath | +0.059 |
pped | +0.058 |
You | +0.057 |
Neg logit contributions | |
packs | -0.065 |
uth | -0.063 |
eth | -0.062 |
aj | -0.057 |
majesty | -0.055 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
packs | +0.105 |
uth | +0.103 |
eth | +0.097 |
aj | +0.096 |
patients | +0.092 |
Neg logit contributions | |
ting | -0.134 |
course | -0.118 |
pped | -0.113 |
neath | -0.107 |
You | -0.100 |
Token | ates |
Token ID | 689 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
uth | +0.198 |
eth | +0.197 |
packs | +0.189 |
aj | +0.184 |
patients | +0.180 |
Neg logit contributions | |
ting | -0.251 |
course | -0.213 |
pped | -0.213 |
neath | -0.195 |
You | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
eth | +0.083 |
uth | +0.083 |
packs | +0.082 |
aj | +0.079 |
majesty | +0.079 |
Neg logit contributions | |
ting | -0.084 |
course | -0.067 |
That | -0.064 |
You | -0.063 |
neath | -0.061 |
Token | They |
Token ID | 1119 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
ting | +0.068 |
course | +0.056 |
neath | +0.054 |
pped | +0.053 |
That | +0.051 |
Neg logit contributions | |
packs | -0.060 |
uth | -0.058 |
eth | -0.057 |
aj | -0.053 |
majesty | -0.051 |
Token | are |
Token ID | 389 |
Feature activation | +3.08e-03 |
Pos logit contributions | |
ting | +0.045 |
course | +0.039 |
neath | +0.037 |
pped | +0.035 |
You | +0.035 |
Neg logit contributions | |
packs | -0.046 |
uth | -0.045 |
eth | -0.044 |
aj | -0.042 |
ies | -0.039 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
ting | +0.006 |
You | +0.005 |
That | +0.005 |
course | +0.005 |
Any | +0.005 |
Neg logit contributions | |
eth | -0.006 |
uth | -0.006 |
packs | -0.006 |
aj | -0.005 |
ifi | -0.005 |
Token | should |
Token ID | 815 |
Feature activation | -1.87e-03 |
Pos logit contributions | |
ting | +0.062 |
course | +0.052 |
You | +0.049 |
That | +0.049 |
neath | +0.048 |
Neg logit contributions | |
packs | -0.064 |
uth | -0.062 |
eth | -0.059 |
aj | -0.057 |
majesty | -0.055 |
Token | have |
Token ID | 423 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
packs | +0.003 |
uth | +0.003 |
eth | +0.003 |
aj | +0.003 |
majesty | +0.003 |
Neg logit contributions | |
ting | -0.004 |
course | -0.003 |
neath | -0.003 |
pped | -0.003 |
That | -0.003 |
Token | shared |
Token ID | 4888 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ting | +0.119 |
neath | +0.095 |
course | +0.092 |
pped | +0.089 |
That | +0.084 |
Neg logit contributions | |
packs | -0.113 |
uth | -0.111 |
eth | -0.103 |
aj | -0.101 |
majesty | -0.098 |
Token | my |
Token ID | 616 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
ting | +0.025 |
course | +0.022 |
You | +0.020 |
That | +0.019 |
pped | +0.018 |
Neg logit contributions | |
eth | -0.038 |
packs | -0.036 |
uth | -0.036 |
aj | -0.034 |
majesty | -0.033 |
Token | l |
Token ID | 300 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
packs | +0.159 |
eth | +0.156 |
uth | +0.144 |
ilot | +0.135 |
ait | +0.132 |
Neg logit contributions | |
ting | -0.115 |
course | -0.113 |
You | -0.096 |
That | -0.093 |
Any | -0.091 |
Token | oll |
Token ID | 692 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
packs | +0.109 |
uth | +0.101 |
eth | +0.101 |
patients | +0.092 |
aj | +0.091 |
Neg logit contributions | |
ting | -0.102 |
course | -0.085 |
pped | -0.082 |
wheel | -0.079 |
You | -0.079 |
Token | ipop |
Token ID | 42800 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
packs | +0.219 |
uth | +0.211 |
apartment | +0.205 |
eth | +0.203 |
patients | +0.187 |
Neg logit contributions | |
ting | -0.243 |
course | -0.212 |
pped | -0.196 |
on | -0.194 |
ted | -0.192 |
Token | with |
Token ID | 351 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
packs | +0.075 |
uth | +0.073 |
eth | +0.072 |
aj | +0.066 |
majesty | +0.064 |
Neg logit contributions | |
ting | -0.080 |
course | -0.067 |
pped | -0.062 |
You | -0.062 |
That | -0.061 |
Token | you |
Token ID | 345 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
packs | +0.036 |
uth | +0.035 |
eth | +0.034 |
aj | +0.033 |
majesty | +0.031 |
Neg logit contributions | |
ting | -0.020 |
course | -0.015 |
neath | -0.014 |
pped | -0.014 |
You | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
uth | +0.086 |
eth | +0.086 |
packs | +0.086 |
aj | +0.076 |
majesty | +0.075 |
Neg logit contributions | |
ting | -0.107 |
course | -0.090 |
You | -0.083 |
pped | -0.083 |
That | -0.081 |
Token | It |
Token ID | 632 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
ting | +0.062 |
pped | +0.048 |
course | +0.048 |
neath | +0.047 |
wheel | +0.041 |
Neg logit contributions | |
uth | -0.082 |
packs | -0.081 |
eth | -0.079 |
majesty | -0.076 |
aj | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
ting | +0.060 |
pped | +0.050 |
course | +0.050 |
Higher | +0.045 |
neath | +0.045 |
Neg logit contributions | |
eth | -0.037 |
packs | -0.036 |
uth | -0.035 |
ies | -0.034 |
patients | -0.033 |
Token | time |
Token ID | 640 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
packs | +0.007 |
uth | +0.006 |
eth | +0.006 |
aj | +0.006 |
patients | +0.006 |
Neg logit contributions | |
ting | -0.005 |
course | -0.004 |
neath | -0.004 |
pped | -0.004 |
That | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
packs | +0.060 |
uth | +0.058 |
eth | +0.057 |
aj | +0.053 |
majesty | +0.051 |
Neg logit contributions | |
ting | -0.071 |
course | -0.059 |
neath | -0.057 |
pped | -0.056 |
That | -0.055 |
Token | celebrate |
Token ID | 10648 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
packs | +0.085 |
uth | +0.082 |
eth | +0.081 |
aj | +0.076 |
majesty | +0.074 |
Neg logit contributions | |
ting | -0.082 |
course | -0.066 |
neath | -0.063 |
pped | -0.062 |
That | -0.061 |
Token | their |
Token ID | 511 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
packs | +0.057 |
uth | +0.056 |
eth | +0.056 |
aj | +0.051 |
majesty | +0.050 |
Neg logit contributions | |
ting | -0.063 |
course | -0.052 |
neath | -0.049 |
You | -0.048 |
That | -0.048 |
Token | birth |
Token ID | 4082 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
eth | +0.078 |
packs | +0.077 |
uth | +0.077 |
ifi | +0.066 |
aj | +0.063 |
Neg logit contributions | |
ting | -0.130 |
course | -0.121 |
neath | -0.110 |
You | -0.110 |
That | -0.109 |
Token | days |
Token ID | 12545 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
uth | +0.165 |
majesty | +0.144 |
eth | +0.143 |
packs | +0.136 |
ifi | +0.135 |
Neg logit contributions | |
ting | -0.293 |
course | -0.245 |
You | -0.242 |
you | -0.241 |
neath | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
packs | +0.046 |
eth | +0.042 |
uth | +0.041 |
aj | +0.038 |
ies | +0.037 |
Neg logit contributions | |
ting | -0.077 |
course | -0.067 |
neath | -0.065 |
pped | -0.065 |
That | -0.062 |
Token | Max |
Token ID | 5436 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
ting | +0.011 |
course | +0.009 |
pped | +0.009 |
neath | +0.009 |
You | +0.008 |
Neg logit contributions | |
packs | -0.011 |
uth | -0.010 |
eth | -0.010 |
aj | -0.010 |
majesty | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
ting | +0.007 |
course | +0.006 |
neath | +0.005 |
pped | +0.005 |
That | +0.005 |
Neg logit contributions | |
packs | -0.007 |
uth | -0.007 |
eth | -0.006 |
aj | -0.006 |
majesty | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
ting | +0.094 |
course | +0.072 |
neath | +0.068 |
pped | +0.065 |
That | +0.063 |
Neg logit contributions | |
packs | -0.134 |
uth | -0.129 |
eth | -0.126 |
aj | -0.122 |
patients | -0.118 |
Token | 't |
Token ID | 470 |
Feature activation | -2.92e-03 |
Pos logit contributions | |
ting | +0.051 |
course | +0.043 |
neath | +0.039 |
Looks | +0.038 |
pped | +0.038 |
Neg logit contributions | |
eth | -0.054 |
packs | -0.053 |
uth | -0.053 |
aj | -0.048 |
patients | -0.047 |
Token | lend |
Token ID | 22096 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
packs | +0.006 |
uth | +0.006 |
aj | +0.006 |
eth | +0.006 |
majesty | +0.006 |
Neg logit contributions | |
ting | -0.005 |
course | -0.004 |
You | -0.004 |
That | -0.004 |
pped | -0.004 |
Token | me |
Token ID | 502 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
ting | +0.035 |
course | +0.027 |
You | +0.024 |
That | +0.023 |
pped | +0.023 |
Neg logit contributions | |
packs | -0.063 |
eth | -0.061 |
uth | -0.061 |
aj | -0.059 |
majesty | -0.057 |
Token | her |
Token ID | 607 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
packs | +0.183 |
uth | +0.179 |
eth | +0.176 |
aj | +0.167 |
majesty | +0.161 |
Neg logit contributions | |
ting | -0.137 |
course | -0.109 |
pped | -0.099 |
neath | -0.098 |
You | -0.094 |
Token | re |
Token ID | 302 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
uth | +0.172 |
eth | +0.165 |
packs | +0.158 |
ifi | +0.155 |
aj | +0.153 |
Neg logit contributions | |
ting | -0.155 |
course | -0.116 |
Good | -0.107 |
neath | -0.104 |
ter | -0.102 |
Token | ind |
Token ID | 521 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
packs | +0.213 |
spine | +0.209 |
majesty | +0.201 |
uth | +0.196 |
allowance | +0.195 |
Neg logit contributions | |
ting | -0.135 |
we | -0.093 |
pped | -0.090 |
course | -0.090 |
ted | -0.078 |
Token | eer |
Token ID | 28153 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
aj | +0.228 |
uth | +0.215 |
packs | +0.209 |
eth | +0.207 |
majesty | +0.201 |
Neg logit contributions | |
ting | -0.224 |
ted | -0.158 |
You | -0.152 |
course | -0.138 |
ing | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
uth | +0.068 |
packs | +0.066 |
eth | +0.065 |
aj | +0.062 |
majesty | +0.059 |
Neg logit contributions | |
ting | -0.067 |
course | -0.057 |
pped | -0.050 |
You | -0.049 |
wheel | -0.049 |
Token | She |
Token ID | 1375 |
Feature activation | +6.70e-03 |
Pos logit contributions | |
ting | +0.052 |
course | +0.039 |
neath | +0.037 |
You | +0.037 |
That | +0.036 |
Neg logit contributions | |
packs | -0.076 |
uth | -0.074 |
eth | -0.072 |
aj | -0.069 |
ies | -0.068 |
Token | is |
Token ID | 318 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
ting | +0.012 |
course | +0.009 |
neath | +0.009 |
pped | +0.009 |
That | +0.009 |
Neg logit contributions | |
packs | -0.014 |
uth | -0.014 |
eth | -0.014 |
aj | -0.013 |
majesty | -0.013 |
Token | mean |
Token ID | 1612 |
Feature activation | +2.06e-03 |
Pos logit contributions | |
ting | +0.002 |
course | +0.002 |
pped | +0.002 |
You | +0.002 |
neath | +0.002 |
Neg logit contributions | |
packs | -0.003 |
uth | -0.003 |
eth | -0.003 |
aj | -0.003 |
majesty | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -5.18e-04 |
Pos logit contributions | |
packs | +0.037 |
uth | +0.036 |
eth | +0.035 |
aj | +0.033 |
majesty | +0.032 |
Neg logit contributions | |
ting | -0.041 |
course | -0.034 |
neath | -0.032 |
pped | -0.032 |
That | -0.032 |
Token | they |
Token ID | 484 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
packs | +0.001 |
uth | +0.001 |
eth | +0.001 |
aj | +0.001 |
ies | +0.001 |
Neg logit contributions | |
ting | -0.001 |
course | -0.001 |
neath | -0.001 |
pped | -0.001 |
You | -0.001 |
Token | shared |
Token ID | 4888 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ting | +0.029 |
course | +0.023 |
neath | +0.022 |
You | +0.022 |
Good | +0.022 |
Neg logit contributions | |
packs | -0.029 |
uth | -0.028 |
eth | -0.027 |
ies | -0.025 |
aj | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
ting | +0.016 |
course | +0.013 |
That | +0.011 |
neath | +0.011 |
You | +0.011 |
Neg logit contributions | |
eth | -0.035 |
packs | -0.033 |
uth | -0.033 |
aj | -0.032 |
majesty | -0.032 |
Token | ch |
Token ID | 442 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
ting | +0.060 |
course | +0.048 |
neath | +0.047 |
pped | +0.047 |
You | +0.044 |
Neg logit contributions | |
packs | -0.054 |
uth | -0.053 |
eth | -0.052 |
aj | -0.049 |
majesty | -0.047 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
packs | +0.118 |
uth | +0.106 |
eth | +0.102 |
aj | +0.095 |
patients | +0.094 |
Neg logit contributions | |
ting | -0.147 |
course | -0.130 |
pped | -0.120 |
neath | -0.118 |
wheel | -0.115 |
Token | ates |
Token ID | 689 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
eth | +0.204 |
packs | +0.197 |
uth | +0.196 |
patients | +0.186 |
aj | +0.186 |
Neg logit contributions | |
ting | -0.244 |
course | -0.208 |
pped | -0.207 |
neath | -0.187 |
You | -0.187 |
Token | with |
Token ID | 351 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
eth | +0.103 |
packs | +0.103 |
uth | +0.103 |
aj | +0.099 |
majesty | +0.097 |
Neg logit contributions | |
ting | -0.083 |
course | -0.067 |
That | -0.060 |
neath | -0.060 |
You | -0.059 |
Token | everyone |
Token ID | 2506 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
packs | +0.022 |
eth | +0.022 |
aj | +0.021 |
uth | +0.021 |
majesty | +0.020 |
Neg logit contributions | |
ting | -0.023 |
course | -0.019 |
neath | -0.017 |
That | -0.017 |
You | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
eth | +0.049 |
packs | +0.049 |
uth | +0.049 |
aj | +0.046 |
majesty | +0.044 |
Neg logit contributions | |
ting | -0.051 |
course | -0.042 |
That | -0.039 |
neath | -0.039 |
You | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
aj | +0.156 |
eth | +0.153 |
uth | +0.150 |
packs | +0.145 |
majesty | +0.143 |
Neg logit contributions | |
ting | -0.071 |
course | -0.063 |
neath | -0.054 |
That | -0.049 |
You | -0.047 |
Token | like |
Token ID | 588 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ting | +0.089 |
course | +0.074 |
neath | +0.071 |
pped | +0.070 |
That | +0.069 |
Neg logit contributions | |
packs | -0.069 |
uth | -0.067 |
eth | -0.065 |
aj | -0.061 |
majesty | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
ting | +0.048 |
neath | +0.040 |
pped | +0.040 |
course | +0.038 |
Looks | +0.037 |
Neg logit contributions | |
packs | -0.042 |
uth | -0.039 |
patients | -0.037 |
majesty | -0.037 |
eth | -0.036 |
Token | pick |
Token ID | 2298 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
packs | +0.052 |
uth | +0.050 |
eth | +0.049 |
aj | +0.047 |
ies | +0.044 |
Neg logit contributions | |
ting | -0.051 |
course | -0.045 |
neath | -0.040 |
You | -0.040 |
pped | -0.040 |
Token | flowers |
Token ID | 12734 |
Feature activation | +8.47e-03 |
Pos logit contributions | |
ting | +0.135 |
Looks | +0.124 |
pped | +0.124 |
neath | +0.121 |
wheel | +0.120 |
Neg logit contributions | |
packs | -0.146 |
uth | -0.142 |
ies | -0.133 |
teeth | -0.132 |
aj | -0.129 |
Token | on |
Token ID | 319 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
ting | +0.019 |
course | +0.016 |
neath | +0.016 |
pped | +0.016 |
That | +0.015 |
Neg logit contributions | |
packs | -0.014 |
uth | -0.013 |
eth | -0.013 |
aj | -0.012 |
ies | -0.012 |
Token | Tues |
Token ID | 48496 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
packs | +0.076 |
uth | +0.074 |
eth | +0.072 |
aj | +0.068 |
majesty | +0.066 |
Neg logit contributions | |
ting | -0.067 |
course | -0.053 |
neath | -0.051 |
pped | -0.050 |
That | -0.049 |
Token | days |
Token ID | 12545 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
uth | +0.147 |
eth | +0.145 |
majesty | +0.132 |
patients | +0.130 |
packs | +0.129 |
Neg logit contributions | |
ting | -0.296 |
course | -0.271 |
pped | -0.261 |
neath | -0.260 |
You | -0.251 |
Token | ." |
Token ID | 526 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
packs | +0.032 |
uth | +0.029 |
eth | +0.029 |
aj | +0.027 |
ies | +0.025 |
Neg logit contributions | |
ting | -0.049 |
course | -0.042 |
neath | -0.041 |
pped | -0.041 |
That | -0.039 |
Token | |
Token ID | 220 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
packs | +0.018 |
uth | +0.017 |
eth | +0.017 |
aj | +0.016 |
majesty | +0.015 |
Neg logit contributions | |
ting | -0.015 |
course | -0.013 |
neath | -0.012 |
You | -0.012 |
That | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
packs | +0.051 |
uth | +0.050 |
eth | +0.048 |
patients | +0.045 |
majesty | +0.045 |
Neg logit contributions | |
ting | -0.044 |
course | -0.035 |
You | -0.035 |
neath | -0.035 |
That | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
packs | +0.077 |
uth | +0.073 |
eth | +0.072 |
aj | +0.068 |
majesty | +0.067 |
Neg logit contributions | |
ting | -0.079 |
course | -0.068 |
That | -0.063 |
neath | -0.062 |
You | -0.062 |
Token | son |
Token ID | 3367 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
packs | +0.061 |
uth | +0.055 |
eth | +0.054 |
ifi | +0.049 |
ighed | +0.048 |
Neg logit contributions | |
ting | -0.081 |
course | -0.072 |
Good | -0.065 |
You | -0.064 |
neath | -0.063 |
Token | is |
Token ID | 318 |
Feature activation | -6.45e-03 |
Pos logit contributions | |
packs | +0.036 |
uth | +0.035 |
eth | +0.034 |
aj | +0.032 |
patients | +0.031 |
Neg logit contributions | |
ting | -0.033 |
course | -0.027 |
neath | -0.025 |
pped | -0.025 |
You | -0.024 |
Token | eating |
Token ID | 6600 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
packs | +0.014 |
uth | +0.013 |
eth | +0.013 |
aj | +0.012 |
majesty | +0.012 |
Neg logit contributions | |
ting | -0.012 |
course | -0.009 |
neath | -0.009 |
pped | -0.009 |
That | -0.008 |
Token | our |
Token ID | 674 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
ting | +0.047 |
course | +0.037 |
neath | +0.036 |
pped | +0.036 |
That | +0.035 |
Neg logit contributions | |
packs | -0.057 |
uth | -0.055 |
eth | -0.053 |
aj | -0.052 |
majesty | -0.050 |
Token | ch |
Token ID | 442 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
packs | +0.093 |
eth | +0.092 |
uth | +0.088 |
ifi | +0.080 |
aj | +0.080 |
Neg logit contributions | |
ting | -0.084 |
course | -0.074 |
neath | -0.064 |
Good | -0.062 |
You | -0.061 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
packs | +0.107 |
uth | +0.103 |
eth | +0.098 |
aj | +0.090 |
ifi | +0.089 |
Neg logit contributions | |
ting | -0.112 |
course | -0.097 |
pped | -0.091 |
neath | -0.084 |
pping | -0.079 |
Token | ates |
Token ID | 689 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
eth | +0.206 |
uth | +0.202 |
packs | +0.193 |
patients | +0.189 |
majesty | +0.188 |
Neg logit contributions | |
ting | -0.232 |
pped | -0.200 |
course | -0.195 |
neath | -0.174 |
You | -0.170 |
Token | !" |
Token ID | 2474 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
packs | +0.079 |
uth | +0.075 |
eth | +0.073 |
aj | +0.069 |
ies | +0.066 |
Neg logit contributions | |
ting | -0.094 |
course | -0.079 |
neath | -0.076 |
pped | -0.074 |
That | -0.073 |
Token | |
Token ID | 220 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
ting | +0.009 |
course | +0.007 |
neath | +0.007 |
That | +0.007 |
You | +0.007 |
Neg logit contributions | |
packs | -0.010 |
uth | -0.009 |
eth | -0.009 |
ies | -0.009 |
aj | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
packs | +0.059 |
uth | +0.057 |
eth | +0.054 |
ies | +0.054 |
majesty | +0.053 |
Neg logit contributions | |
ting | -0.047 |
neath | -0.038 |
You | -0.037 |
That | -0.037 |
Good | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
packs | +0.105 |
uth | +0.094 |
ies | +0.093 |
eth | +0.093 |
majesty | +0.090 |
Neg logit contributions | |
ting | -0.072 |
That | -0.061 |
course | -0.059 |
You | -0.057 |
pped | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
packs | +0.038 |
uth | +0.036 |
eth | +0.035 |
aj | +0.032 |
majesty | +0.030 |
Neg logit contributions | |
ting | -0.072 |
course | -0.062 |
neath | -0.060 |
pped | -0.059 |
That | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +8.00e-03 |
Pos logit contributions | |
packs | +0.040 |
uth | +0.039 |
eth | +0.038 |
patients | +0.036 |
ies | +0.035 |
Neg logit contributions | |
ting | -0.032 |
course | -0.025 |
pped | -0.024 |
neath | -0.023 |
That | -0.022 |
Token | creature |
Token ID | 7185 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
ting | +0.020 |
course | +0.017 |
neath | +0.016 |
pped | +0.016 |
You | +0.016 |
Neg logit contributions | |
packs | -0.011 |
uth | -0.011 |
eth | -0.011 |
aj | -0.010 |
majesty | -0.009 |
Token | appeared |
Token ID | 4120 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
ting | +0.058 |
Great | +0.048 |
neath | +0.047 |
That | +0.047 |
Good | +0.047 |
Neg logit contributions | |
packs | -0.058 |
uth | -0.054 |
ies | -0.053 |
eth | -0.051 |
patients | -0.049 |
Token | on |
Token ID | 319 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
ting | +0.068 |
course | +0.067 |
Looks | +0.065 |
Watch | +0.064 |
neath | +0.064 |
Neg logit contributions | |
packs | -0.044 |
ies | -0.036 |
eth | -0.035 |
uth | -0.033 |
aj | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
packs | +0.034 |
uth | +0.033 |
eth | +0.033 |
patients | +0.030 |
aj | +0.030 |
Neg logit contributions | |
ting | -0.025 |
course | -0.019 |
pped | -0.019 |
neath | -0.018 |
That | -0.018 |
Token | red |
Token ID | 2266 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ting | +0.127 |
pped | +0.110 |
neath | +0.107 |
course | +0.107 |
You | +0.105 |
Neg logit contributions | |
packs | -0.070 |
uth | -0.068 |
eth | -0.066 |
spine | -0.061 |
patients | -0.060 |
Token | planet |
Token ID | 5440 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
ting | +0.040 |
Looks | +0.035 |
You | +0.034 |
pped | +0.034 |
Any | +0.034 |
Neg logit contributions | |
packs | -0.023 |
eth | -0.021 |
uth | -0.019 |
ies | -0.019 |
apartment | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
ting | +0.020 |
pped | +0.018 |
neath | +0.017 |
Looks | +0.017 |
Good | +0.017 |
Neg logit contributions | |
packs | -0.011 |
uth | -0.010 |
eth | -0.010 |
ies | -0.009 |
aj | -0.008 |
Token | It |
Token ID | 632 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
ting | +0.052 |
pped | +0.044 |
course | +0.043 |
neath | +0.039 |
Looks | +0.037 |
Neg logit contributions | |
eth | -0.057 |
packs | -0.055 |
uth | -0.054 |
aj | -0.049 |
patients | -0.049 |
Token | was |
Token ID | 373 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ting | +0.125 |
course | +0.101 |
pped | +0.099 |
neath | +0.096 |
You | +0.091 |
Neg logit contributions | |
packs | -0.112 |
uth | -0.112 |
eth | -0.108 |
ies | -0.102 |
aj | -0.101 |
Token | into |
Token ID | 656 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
ting | +0.020 |
course | +0.015 |
neath | +0.014 |
pped | +0.014 |
You | +0.013 |
Neg logit contributions | |
packs | -0.029 |
uth | -0.028 |
eth | -0.028 |
aj | -0.027 |
majesty | -0.026 |
Token | one |
Token ID | 530 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
packs | +0.091 |
uth | +0.089 |
eth | +0.088 |
aj | +0.084 |
majesty | +0.081 |
Neg logit contributions | |
ting | -0.065 |
course | -0.052 |
neath | -0.049 |
pped | -0.048 |
That | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
eth | +0.073 |
uth | +0.073 |
packs | +0.072 |
aj | +0.069 |
majesty | +0.068 |
Neg logit contributions | |
ting | -0.066 |
course | -0.059 |
neath | -0.052 |
That | -0.050 |
pped | -0.048 |
Token | said |
Token ID | 531 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ting | +0.033 |
course | +0.027 |
neath | +0.025 |
pped | +0.025 |
You | +0.025 |
Neg logit contributions | |
packs | -0.038 |
uth | -0.037 |
eth | -0.036 |
aj | -0.034 |
majesty | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
packs | +0.025 |
uth | +0.024 |
eth | +0.023 |
aj | +0.021 |
majesty | +0.020 |
Neg logit contributions | |
ting | -0.041 |
course | -0.035 |
neath | -0.034 |
pped | -0.033 |
That | -0.033 |
Token | " |
Token ID | 366 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
uth | +0.062 |
eth | +0.062 |
packs | +0.058 |
aj | +0.057 |
majesty | +0.056 |
Neg logit contributions | |
ting | -0.065 |
course | -0.056 |
neath | -0.052 |
pped | -0.052 |
Hey | -0.049 |
Token | Y |
Token ID | 56 |
Feature activation | +5.55e-03 |
Pos logit contributions | |
ting | +0.115 |
neath | +0.075 |
course | +0.075 |
causing | +0.074 |
wheel | +0.072 |
Neg logit contributions | |
uth | -0.178 |
packs | -0.164 |
eth | -0.163 |
ifi | -0.153 |
aj | -0.152 |
Token | um |
Token ID | 388 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
ting | +0.014 |
course | +0.011 |
neath | +0.011 |
pped | +0.011 |
You | +0.011 |
Neg logit contributions | |
eth | -0.008 |
uth | -0.008 |
packs | -0.008 |
aj | -0.007 |
ies | -0.007 |
Token | ! |
Token ID | 0 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
packs | +0.020 |
uth | +0.019 |
eth | +0.019 |
aj | +0.018 |
ies | +0.018 |
Neg logit contributions | |
ting | -0.025 |
neath | -0.020 |
course | -0.020 |
pped | -0.020 |
That | -0.019 |
Token | G |
Token ID | 402 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
ting | +0.064 |
course | +0.048 |
pped | +0.047 |
neath | +0.044 |
wheel | +0.039 |
Neg logit contributions | |
uth | -0.097 |
packs | -0.095 |
eth | -0.095 |
aj | -0.089 |
majesty | -0.088 |
Token | rap |
Token ID | 2416 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
packs | +0.070 |
uth | +0.069 |
eth | +0.068 |
aj | +0.066 |
majesty | +0.062 |
Neg logit contributions | |
ting | -0.099 |
course | -0.079 |
That | -0.079 |
You | -0.079 |
neath | -0.077 |
Token | all |
Token ID | 477 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
uth | +0.047 |
packs | +0.045 |
eth | +0.045 |
majesty | +0.044 |
aj | +0.043 |
Neg logit contributions | |
ting | -0.037 |
neath | -0.029 |
course | -0.028 |
pped | -0.027 |
ted | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
uth | +0.030 |
packs | +0.030 |
eth | +0.029 |
aj | +0.028 |
majesty | +0.028 |
Neg logit contributions | |
ting | -0.021 |
course | -0.017 |
neath | -0.016 |
pped | -0.014 |
That | -0.014 |
Token | way |
Token ID | 835 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ting | +0.052 |
course | +0.044 |
neath | +0.041 |
pped | +0.039 |
You | +0.039 |
Neg logit contributions | |
packs | -0.047 |
uth | -0.047 |
eth | -0.044 |
aj | -0.041 |
majesty | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
uth | +0.025 |
packs | +0.024 |
eth | +0.023 |
aj | +0.023 |
majesty | +0.022 |
Neg logit contributions | |
ting | -0.028 |
course | -0.022 |
neath | -0.022 |
pped | -0.021 |
That | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
ting | +0.029 |
course | +0.023 |
neath | +0.022 |
pped | +0.022 |
That | +0.021 |
Neg logit contributions | |
packs | -0.029 |
uth | -0.028 |
eth | -0.027 |
aj | -0.026 |
majesty | -0.025 |
Token | fell |
Token ID | 3214 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
ting | +0.009 |
course | +0.007 |
neath | +0.007 |
pped | +0.007 |
That | +0.007 |
Neg logit contributions | |
packs | -0.014 |
uth | -0.014 |
eth | -0.014 |
aj | -0.013 |
majesty | -0.013 |
Token | sound |
Token ID | 2128 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ting | +0.114 |
neath | +0.089 |
course | +0.089 |
pped | +0.088 |
That | +0.084 |
Neg logit contributions | |
uth | -0.091 |
packs | -0.088 |
eth | -0.081 |
majesty | -0.079 |
aj | -0.078 |
Token | asleep |
Token ID | 16039 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
ting | +0.021 |
course | +0.018 |
neath | +0.017 |
You | +0.017 |
pped | +0.017 |
Neg logit contributions | |
packs | -0.019 |
uth | -0.018 |
eth | -0.018 |
aj | -0.016 |
ies | -0.016 |
Token | with |
Token ID | 351 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
packs | +0.098 |
uth | +0.094 |
eth | +0.091 |
aj | +0.086 |
majesty | +0.083 |
Neg logit contributions | |
ting | -0.113 |
course | -0.093 |
neath | -0.088 |
pped | -0.087 |
You | -0.085 |
Token | one |
Token ID | 530 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
packs | +0.006 |
uth | +0.006 |
eth | +0.006 |
aj | +0.006 |
majesty | +0.006 |
Neg logit contributions | |
ting | -0.005 |
course | -0.004 |
neath | -0.004 |
pped | -0.004 |
That | -0.004 |
Token | finger |
Token ID | 7660 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
packs | +0.078 |
uth | +0.078 |
eth | +0.076 |
aj | +0.071 |
majesty | +0.071 |
Neg logit contributions | |
ting | -0.073 |
course | -0.063 |
neath | -0.056 |
pped | -0.054 |
That | -0.054 |
Token | for |
Token ID | 329 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
uth | +0.007 |
packs | +0.007 |
eth | +0.007 |
aj | +0.007 |
majesty | +0.007 |
Neg logit contributions | |
ting | -0.009 |
course | -0.008 |
neath | -0.007 |
pped | -0.007 |
You | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -5.63e-03 |
Pos logit contributions | |
packs | +0.021 |
uth | +0.020 |
eth | +0.020 |
aj | +0.019 |
majesty | +0.018 |
Neg logit contributions | |
ting | -0.013 |
course | -0.010 |
pped | -0.009 |
neath | -0.009 |
You | -0.009 |
Token | science |
Token ID | 3783 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
packs | +0.010 |
uth | +0.010 |
eth | +0.009 |
aj | +0.009 |
ies | +0.008 |
Neg logit contributions | |
ting | -0.012 |
course | -0.010 |
That | -0.009 |
neath | -0.009 |
Good | -0.009 |
Token | project |
Token ID | 1628 |
Feature activation | +3.28e-03 |
Pos logit contributions | |
packs | +0.061 |
uth | +0.059 |
eth | +0.058 |
aj | +0.054 |
majesty | +0.052 |
Neg logit contributions | |
ting | -0.068 |
course | -0.058 |
neath | -0.053 |
pped | -0.052 |
You | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
ting | +0.007 |
course | +0.006 |
You | +0.005 |
wheel | +0.005 |
pped | +0.005 |
Neg logit contributions | |
uth | -0.006 |
packs | -0.006 |
eth | -0.006 |
majesty | -0.005 |
aj | -0.005 |
Token | It |
Token ID | 632 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
ting | +0.065 |
course | +0.054 |
pped | +0.051 |
neath | +0.049 |
That | +0.044 |
Neg logit contributions | |
uth | -0.087 |
eth | -0.087 |
packs | -0.085 |
majesty | -0.081 |
aj | -0.080 |
Token | must |
Token ID | 1276 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ting | +0.122 |
pped | +0.099 |
course | +0.094 |
neath | +0.092 |
Higher | +0.090 |
Neg logit contributions | |
packs | -0.109 |
eth | -0.105 |
uth | -0.105 |
patients | -0.100 |
ies | -0.100 |
Token | have |
Token ID | 423 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
packs | +0.018 |
uth | +0.017 |
eth | +0.017 |
aj | +0.016 |
ies | +0.015 |
Neg logit contributions | |
ting | -0.023 |
course | -0.020 |
neath | -0.019 |
pped | -0.018 |
You | -0.018 |
Token | escaped |
Token ID | 13537 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ting | +0.137 |
course | +0.110 |
neath | +0.104 |
pped | +0.102 |
That | +0.100 |
Neg logit contributions | |
packs | -0.162 |
uth | -0.158 |
eth | -0.155 |
aj | -0.147 |
majesty | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
ting | +0.031 |
course | +0.026 |
neath | +0.024 |
pped | +0.024 |
You | +0.023 |
Neg logit contributions | |
packs | -0.029 |
uth | -0.029 |
eth | -0.028 |
aj | -0.026 |
majesty | -0.026 |
Token | I |
Token ID | 314 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
ting | +0.051 |
course | +0.041 |
neath | +0.038 |
pped | +0.038 |
That | +0.034 |
Neg logit contributions | |
uth | -0.072 |
packs | -0.070 |
eth | -0.070 |
aj | -0.066 |
majesty | -0.065 |
Token | slipped |
Token ID | 18859 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
ting | +0.079 |
course | +0.064 |
You | +0.058 |
neath | +0.057 |
Good | +0.057 |
Neg logit contributions | |
packs | -0.086 |
eth | -0.085 |
uth | -0.085 |
aj | -0.081 |
ies | -0.079 |
Token | from |
Token ID | 422 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ting | +0.135 |
course | +0.125 |
Looks | +0.117 |
Any | +0.113 |
Great | +0.112 |
Neg logit contributions | |
eth | -0.093 |
packs | -0.089 |
ies | -0.077 |
heads | -0.074 |
ilot | -0.073 |
Token | her |
Token ID | 607 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
packs | +0.042 |
uth | +0.041 |
eth | +0.040 |
aj | +0.037 |
majesty | +0.036 |
Neg logit contributions | |
ting | -0.039 |
course | -0.031 |
neath | -0.030 |
pped | -0.029 |
That | -0.029 |
Token | hand |
Token ID | 1021 |
Feature activation | +4.82e-03 |
Pos logit contributions | |
eth | +0.104 |
uth | +0.104 |
packs | +0.102 |
ifi | +0.092 |
common | +0.089 |
Neg logit contributions | |
ting | -0.128 |
course | -0.115 |
neath | -0.102 |
� | -0.101 |
pped | -0.101 |
Token | and |
Token ID | 290 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ting | +0.011 |
course | +0.010 |
Looks | +0.010 |
Great | +0.010 |
neath | +0.010 |
Neg logit contributions | |
packs | -0.007 |
eth | -0.007 |
uth | -0.006 |
aj | -0.006 |
ies | -0.006 |
Token | fell |
Token ID | 3214 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
ting | +0.075 |
course | +0.063 |
neath | +0.058 |
Any | +0.056 |
That | +0.056 |
Neg logit contributions | |
packs | -0.068 |
eth | -0.065 |
uth | -0.063 |
ies | -0.059 |
aj | -0.059 |
Token | on |
Token ID | 319 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ting | +0.102 |
course | +0.088 |
neath | +0.081 |
That | +0.078 |
You | +0.077 |
Neg logit contributions | |
packs | -0.108 |
eth | -0.105 |
uth | -0.100 |
aj | -0.097 |
ies | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
packs | +0.024 |
uth | +0.023 |
eth | +0.023 |
aj | +0.022 |
majesty | +0.021 |
Neg logit contributions | |
ting | -0.017 |
course | -0.013 |
neath | -0.012 |
pped | -0.012 |
That | -0.012 |
Token | floor |
Token ID | 4314 |
Feature activation | +2.75e-03 |
Pos logit contributions | |
ting | +0.109 |
course | +0.090 |
neath | +0.087 |
pped | +0.085 |
That | +0.083 |
Neg logit contributions | |
packs | -0.101 |
uth | -0.098 |
eth | -0.097 |
aj | -0.091 |
majesty | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
ting | +0.007 |
course | +0.006 |
neath | +0.006 |
pped | +0.005 |
You | +0.005 |
Neg logit contributions | |
packs | -0.004 |
eth | -0.004 |
uth | -0.004 |
aj | -0.003 |
ies | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
ting | +0.039 |
course | +0.031 |
neath | +0.030 |
That | +0.029 |
pped | +0.029 |
Neg logit contributions | |
packs | -0.046 |
uth | -0.045 |
eth | -0.043 |
aj | -0.041 |
ies | -0.040 |
Token | way |
Token ID | 835 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
packs | +0.097 |
uth | +0.091 |
eth | +0.090 |
aj | +0.086 |
ies | +0.085 |
Neg logit contributions | |
ting | -0.113 |
course | -0.106 |
That | -0.096 |
neath | -0.094 |
� | -0.094 |
Token | across |
Token ID | 1973 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
packs | +0.024 |
uth | +0.023 |
eth | +0.022 |
aj | +0.022 |
majesty | +0.021 |
Neg logit contributions | |
ting | -0.033 |
course | -0.028 |
neath | -0.027 |
pped | -0.027 |
That | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
ting | +0.018 |
course | +0.014 |
pped | +0.013 |
neath | +0.013 |
That | +0.013 |
Neg logit contributions | |
packs | -0.024 |
uth | -0.023 |
eth | -0.023 |
aj | -0.022 |
majesty | -0.021 |
Token | field |
Token ID | 2214 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ting | +0.079 |
course | +0.065 |
neath | +0.062 |
pped | +0.060 |
That | +0.060 |
Neg logit contributions | |
packs | -0.089 |
uth | -0.085 |
eth | -0.084 |
aj | -0.080 |
majesty | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
packs | +0.025 |
uth | +0.025 |
eth | +0.024 |
aj | +0.023 |
majesty | +0.022 |
Neg logit contributions | |
ting | -0.033 |
course | -0.028 |
neath | -0.026 |
pped | -0.026 |
That | -0.025 |
Token | Jim |
Token ID | 5395 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
packs | +0.029 |
uth | +0.028 |
ies | +0.024 |
customers | +0.024 |
majesty | +0.023 |
Neg logit contributions | |
ting | -0.036 |
course | -0.030 |
pped | -0.029 |
neath | -0.029 |
wheel | -0.028 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
packs | +0.012 |
uth | +0.012 |
eth | +0.012 |
aj | +0.011 |
majesty | +0.011 |
Neg logit contributions | |
ting | -0.009 |
course | -0.007 |
pped | -0.007 |
neath | -0.007 |
That | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
ting | +0.038 |
course | +0.032 |
neath | +0.031 |
pped | +0.031 |
That | +0.030 |
Neg logit contributions | |
packs | -0.032 |
uth | -0.030 |
eth | -0.029 |
aj | -0.027 |
ies | -0.027 |
Token | pick |
Token ID | 2298 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
packs | +0.046 |
uth | +0.043 |
eth | +0.041 |
majesty | +0.039 |
aj | +0.038 |
Neg logit contributions | |
ting | -0.067 |
pped | -0.053 |
course | -0.053 |
That | -0.053 |
You | -0.052 |
Token | some |
Token ID | 617 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
ting | +0.149 |
pped | +0.132 |
Looks | +0.132 |
Did | +0.131 |
course | +0.130 |
Neg logit contributions | |
packs | -0.140 |
ies | -0.123 |
by | -0.123 |
uth | -0.122 |
teeth | -0.121 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
packs | +0.009 |
uth | +0.009 |
eth | +0.009 |
aj | +0.008 |
majesty | +0.008 |
Neg logit contributions | |
ting | -0.009 |
course | -0.008 |
neath | -0.007 |
pped | -0.007 |
That | -0.007 |
Token | ." |
Token ID | 526 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
uth | +0.124 |
packs | +0.124 |
eth | +0.122 |
aj | +0.116 |
majesty | +0.112 |
Neg logit contributions | |
ting | -0.127 |
course | -0.099 |
neath | -0.093 |
You | -0.092 |
pped | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
packs | +0.015 |
uth | +0.014 |
eth | +0.014 |
aj | +0.013 |
majesty | +0.013 |
Neg logit contributions | |
ting | -0.011 |
course | -0.009 |
You | -0.009 |
That | -0.009 |
neath | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
packs | +0.112 |
uth | +0.101 |
majesty | +0.100 |
ies | +0.100 |
eth | +0.098 |
Neg logit contributions | |
ting | -0.081 |
course | -0.075 |
That | -0.073 |
You | -0.070 |
This | -0.065 |
Token | The |
Token ID | 464 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
packs | +0.086 |
uth | +0.082 |
eth | +0.081 |
aj | +0.078 |
majesty | +0.076 |
Neg logit contributions | |
ting | -0.065 |
course | -0.053 |
That | -0.050 |
neath | -0.049 |
You | -0.049 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
ting | +0.118 |
course | +0.100 |
neath | +0.097 |
pped | +0.096 |
That | +0.094 |
Neg logit contributions | |
packs | -0.075 |
uth | -0.073 |
eth | -0.071 |
aj | -0.065 |
majesty | -0.062 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
ting | +0.005 |
course | +0.004 |
That | +0.004 |
pped | +0.004 |
neath | +0.004 |
Neg logit contributions | |
packs | -0.008 |
uth | -0.008 |
eth | -0.008 |
aj | -0.007 |
majesty | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
ting | +0.082 |
course | +0.068 |
ted | +0.059 |
Looks | +0.059 |
neath | +0.059 |
Neg logit contributions | |
eth | -0.074 |
uth | -0.067 |
packs | -0.067 |
ilot | -0.060 |
aj | -0.059 |
Token | listen |
Token ID | 6004 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
ting | +0.004 |
You | +0.003 |
wheel | +0.003 |
course | +0.003 |
That | +0.003 |
Neg logit contributions | |
packs | -0.004 |
aj | -0.004 |
uth | -0.004 |
majesty | -0.004 |
eth | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ting | +0.004 |
course | +0.003 |
That | +0.003 |
pped | +0.003 |
You | +0.003 |
Neg logit contributions | |
packs | -0.005 |
uth | -0.004 |
majesty | -0.004 |
aj | -0.004 |
eth | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -1.29e-03 |
Pos logit contributions | |
ting | +0.019 |
course | +0.015 |
neath | +0.014 |
That | +0.014 |
You | +0.014 |
Neg logit contributions | |
packs | -0.026 |
uth | -0.025 |
eth | -0.024 |
aj | -0.023 |
ies | -0.023 |
Token | took |
Token ID | 1718 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
packs | +0.003 |
uth | +0.003 |
eth | +0.003 |
aj | +0.003 |
majesty | +0.003 |
Neg logit contributions | |
ting | -0.002 |
course | -0.002 |
pped | -0.002 |
neath | -0.002 |
That | -0.001 |
Token | chair |
Token ID | 5118 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
packs | +0.036 |
uth | +0.036 |
eth | +0.034 |
aj | +0.031 |
ifi | +0.030 |
Neg logit contributions | |
ting | -0.046 |
course | -0.041 |
neath | -0.037 |
pped | -0.036 |
That | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
packs | +0.021 |
eth | +0.019 |
uth | +0.019 |
aj | +0.018 |
ies | +0.017 |
Neg logit contributions | |
ting | -0.024 |
course | -0.020 |
neath | -0.020 |
You | -0.019 |
pped | -0.019 |
Token | sat |
Token ID | 3332 |
Feature activation | +5.67e-03 |
Pos logit contributions | |
ting | +0.044 |
course | +0.035 |
neath | +0.033 |
pped | +0.032 |
That | +0.031 |
Neg logit contributions | |
packs | -0.057 |
uth | -0.055 |
eth | -0.054 |
aj | -0.052 |
majesty | -0.050 |
Token | down |
Token ID | 866 |
Feature activation | -7.99e-05 |
Pos logit contributions | |
ting | +0.010 |
course | +0.009 |
neath | +0.009 |
Good | +0.008 |
wheel | +0.008 |
Neg logit contributions | |
packs | -0.011 |
aj | -0.010 |
ies | -0.010 |
eth | -0.010 |
uth | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
packs | +0.000 |
eth | +0.000 |
uth | +0.000 |
aj | +0.000 |
ies | +0.000 |
Neg logit contributions | |
ting | -0.000 |
course | -0.000 |
pped | -0.000 |
neath | -0.000 |
Good | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | +8.54e-03 |
Pos logit contributions | |
ting | +0.043 |
course | +0.035 |
pped | +0.034 |
neath | +0.033 |
You | +0.032 |
Neg logit contributions | |
packs | -0.042 |
uth | -0.041 |
eth | -0.040 |
aj | -0.038 |
majesty | -0.037 |
Token | felt |
Token ID | 2936 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
ting | +0.015 |
course | +0.012 |
neath | +0.012 |
pped | +0.011 |
That | +0.011 |
Neg logit contributions | |
packs | -0.018 |
uth | -0.018 |
eth | -0.017 |
aj | -0.016 |
majesty | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
ting | +0.102 |
course | +0.083 |
neath | +0.081 |
pped | +0.077 |
That | +0.075 |
Neg logit contributions | |
packs | -0.086 |
uth | -0.084 |
eth | -0.080 |
aj | -0.079 |
patients | -0.077 |
Token | soft |
Token ID | 2705 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ting | +0.075 |
course | +0.062 |
neath | +0.060 |
pped | +0.059 |
That | +0.057 |
Neg logit contributions | |
packs | -0.064 |
uth | -0.063 |
eth | -0.062 |
aj | -0.058 |
majesty | -0.056 |
Token | cushion |
Token ID | 33579 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
packs | +0.029 |
uth | +0.029 |
eth | +0.028 |
aj | +0.026 |
majesty | +0.025 |
Neg logit contributions | |
ting | -0.033 |
course | -0.028 |
neath | -0.026 |
pped | -0.026 |
That | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
packs | +0.022 |
eth | +0.021 |
toes | +0.019 |
ies | +0.019 |
uth | +0.019 |
Neg logit contributions | |
ting | -0.030 |
course | -0.025 |
Hey | -0.025 |
neath | -0.025 |
Watch | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
packs | +0.064 |
uth | +0.062 |
eth | +0.060 |
aj | +0.055 |
majesty | +0.053 |
Neg logit contributions | |
ting | -0.109 |
course | -0.094 |
neath | -0.091 |
pped | -0.089 |
That | -0.087 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
packs | +0.065 |
uth | +0.063 |
eth | +0.061 |
aj | +0.058 |
ies | +0.056 |
Neg logit contributions | |
ting | -0.070 |
course | -0.057 |
neath | -0.055 |
pped | -0.055 |
That | -0.052 |
Token | was |
Token ID | 373 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
ting | +0.027 |
course | +0.022 |
neath | +0.022 |
Looks | +0.022 |
pped | +0.021 |
Neg logit contributions | |
packs | -0.020 |
uth | -0.019 |
ies | -0.019 |
eth | -0.019 |
by | -0.018 |
Token | never |
Token ID | 1239 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
uth | +0.003 |
packs | +0.003 |
eth | +0.002 |
patients | +0.002 |
majesty | +0.002 |
Neg logit contributions | |
ting | -0.004 |
neath | -0.003 |
course | -0.003 |
pped | -0.003 |
Hey | -0.003 |
Token | alone |
Token ID | 3436 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ting | +0.011 |
course | +0.009 |
neath | +0.008 |
pped | +0.008 |
You | +0.008 |
Neg logit contributions | |
packs | -0.009 |
uth | -0.008 |
eth | -0.008 |
aj | -0.008 |
majesty | -0.007 |
Token | when |
Token ID | 618 |
Feature activation | -4.57e-03 |
Pos logit contributions | |
packs | +0.053 |
uth | +0.051 |
eth | +0.050 |
aj | +0.047 |
ies | +0.047 |
Neg logit contributions | |
ting | -0.049 |
course | -0.041 |
neath | -0.040 |
pped | -0.038 |
That | -0.038 |
Token | she |
Token ID | 673 |
Feature activation | -9.47e-04 |
Pos logit contributions | |
packs | +0.010 |
uth | +0.009 |
eth | +0.009 |
aj | +0.009 |
ies | +0.008 |
Neg logit contributions | |
ting | -0.008 |
course | -0.007 |
neath | -0.006 |
pped | -0.006 |
That | -0.006 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
packs | +0.002 |
uth | +0.002 |
eth | +0.002 |
aj | +0.002 |
ies | +0.002 |
Neg logit contributions | |
ting | -0.002 |
neath | -0.001 |
course | -0.001 |
Good | -0.001 |
That | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
ting | +0.056 |
course | +0.047 |
neath | +0.046 |
pped | +0.045 |
That | +0.044 |
Neg logit contributions | |
packs | -0.041 |
uth | -0.039 |
eth | -0.038 |
aj | -0.035 |
ies | -0.034 |
Token | sing |
Token ID | 1702 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
packs | +0.067 |
eth | +0.064 |
uth | +0.064 |
aj | +0.062 |
majesty | +0.056 |
Neg logit contributions | |
ting | -0.071 |
course | -0.061 |
neath | -0.056 |
pped | -0.055 |
You | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ting | +0.058 |
course | +0.047 |
neath | +0.046 |
pped | +0.045 |
That | +0.044 |
Neg logit contributions | |
packs | -0.055 |
uth | -0.052 |
eth | -0.052 |
aj | -0.049 |
ies | -0.047 |
Token | back |
Token ID | 736 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
packs | +0.065 |
eth | +0.061 |
uth | +0.059 |
aj | +0.057 |
ies | +0.055 |
Neg logit contributions | |
ting | -0.064 |
course | -0.053 |
neath | -0.050 |
That | -0.049 |
pped | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +9.23e-03 |
Pos logit contributions | |
packs | +0.120 |
uth | +0.119 |
eth | +0.117 |
aj | +0.109 |
majesty | +0.107 |
Neg logit contributions | |
ting | -0.105 |
course | -0.084 |
neath | -0.080 |
pped | -0.079 |
You | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
ting | +0.018 |
course | +0.014 |
neath | +0.014 |
That | +0.013 |
You | +0.013 |
Neg logit contributions | |
packs | -0.019 |
uth | -0.018 |
eth | -0.017 |
aj | -0.017 |
ies | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
packs | +0.087 |
uth | +0.082 |
eth | +0.079 |
aj | +0.077 |
ies | +0.077 |
Neg logit contributions | |
ting | -0.072 |
course | -0.062 |
That | -0.059 |
neath | -0.058 |
You | -0.057 |
Token | He |
Token ID | 1544 |
Feature activation | -7.05e-03 |
Pos logit contributions | |
uth | +0.052 |
eth | +0.052 |
packs | +0.048 |
ifi | +0.045 |
heads | +0.044 |
Neg logit contributions | |
ting | -0.065 |
neath | -0.051 |
course | -0.050 |
ted | -0.047 |
pped | -0.046 |
Token | headed |
Token ID | 9153 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
packs | +0.014 |
uth | +0.014 |
eth | +0.014 |
aj | +0.013 |
majesty | +0.013 |
Neg logit contributions | |
ting | -0.013 |
course | -0.011 |
neath | -0.010 |
pped | -0.010 |
You | -0.010 |
Token | back |
Token ID | 736 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
ting | +0.046 |
course | +0.039 |
neath | +0.037 |
pped | +0.037 |
That | +0.036 |
Neg logit contributions | |
packs | -0.033 |
uth | -0.032 |
eth | -0.031 |
aj | -0.029 |
majesty | -0.027 |
Token | home |
Token ID | 1363 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
uth | +0.074 |
eth | +0.066 |
majesty | +0.066 |
aj | +0.065 |
patients | +0.064 |
Neg logit contributions | |
ting | -0.095 |
neath | -0.078 |
course | -0.074 |
ted | -0.069 |
pped | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
uth | +0.199 |
packs | +0.192 |
ifi | +0.184 |
eth | +0.183 |
majesty | +0.179 |
Neg logit contributions | |
ting | -0.109 |
wheel | -0.067 |
over | -0.067 |
causing | -0.067 |
this | -0.064 |
Token | told |
Token ID | 1297 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
ting | +0.027 |
course | +0.022 |
neath | +0.021 |
pped | +0.021 |
That | +0.020 |
Neg logit contributions | |
packs | -0.031 |
uth | -0.030 |
eth | -0.030 |
aj | -0.028 |
majesty | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
packs | +0.012 |
uth | +0.011 |
eth | +0.011 |
aj | +0.011 |
ighed | +0.010 |
Neg logit contributions | |
ting | -0.008 |
course | -0.006 |
ted | -0.005 |
pped | -0.005 |
neath | -0.005 |
Token | he |
Token ID | 339 |
Feature activation | -8.28e-03 |
Pos logit contributions | |
packs | +0.014 |
uth | +0.014 |
eth | +0.013 |
aj | +0.013 |
majesty | +0.012 |
Neg logit contributions | |
ting | -0.011 |
course | -0.009 |
neath | -0.008 |
pped | -0.008 |
That | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
packs | +0.018 |
uth | +0.017 |
eth | +0.016 |
aj | +0.015 |
majesty | +0.015 |
Neg logit contributions | |
ting | -0.015 |
course | -0.012 |
That | -0.012 |
neath | -0.011 |
You | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
packs | +0.052 |
uth | +0.052 |
aj | +0.048 |
eth | +0.048 |
majesty | +0.046 |
Neg logit contributions | |
ting | -0.059 |
course | -0.046 |
pped | -0.045 |
neath | -0.045 |
You | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
ting | +0.018 |
course | +0.015 |
neath | +0.014 |
pped | +0.014 |
That | +0.013 |
Neg logit contributions | |
packs | -0.015 |
uth | -0.015 |
eth | -0.015 |
aj | -0.014 |
majesty | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
packs | +0.096 |
uth | +0.090 |
eth | +0.087 |
ies | +0.083 |
patients | +0.083 |
Neg logit contributions | |
ting | -0.089 |
course | -0.076 |
That | -0.071 |
neath | -0.070 |
You | -0.070 |
Token | F |
Token ID | 37 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
uth | +0.073 |
eth | +0.073 |
packs | +0.070 |
aj | +0.067 |
majesty | +0.062 |
Neg logit contributions | |
ting | -0.074 |
neath | -0.058 |
course | -0.057 |
pped | -0.055 |
Good | -0.051 |
Token | ro |
Token ID | 305 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
packs | +0.049 |
uth | +0.043 |
eth | +0.042 |
patients | +0.040 |
aj | +0.038 |
Neg logit contributions | |
ting | -0.111 |
course | -0.099 |
pped | -0.096 |
neath | -0.095 |
That | -0.094 |
Token | ggie |
Token ID | 23571 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
packs | +0.035 |
uth | +0.031 |
eth | +0.031 |
aj | +0.028 |
patients | +0.027 |
Neg logit contributions | |
ting | -0.063 |
course | -0.055 |
pped | -0.053 |
That | -0.052 |
neath | -0.052 |
Token | hopped |
Token ID | 45230 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
packs | +0.049 |
uth | +0.048 |
eth | +0.047 |
aj | +0.045 |
majesty | +0.043 |
Neg logit contributions | |
ting | -0.046 |
course | -0.037 |
neath | -0.035 |
pped | -0.035 |
You | -0.034 |
Token | out |
Token ID | 503 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
ting | +0.079 |
course | +0.068 |
Good | +0.062 |
neath | +0.062 |
You | +0.062 |
Neg logit contributions | |
eth | -0.080 |
packs | -0.076 |
uth | -0.071 |
aj | -0.067 |
ies | -0.067 |
Token | of |
Token ID | 286 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
packs | +0.101 |
uth | +0.100 |
eth | +0.096 |
aj | +0.093 |
majesty | +0.090 |
Neg logit contributions | |
ting | -0.098 |
course | -0.080 |
neath | -0.077 |
pped | -0.074 |
That | -0.072 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
ting | +0.044 |
course | +0.037 |
neath | +0.036 |
pped | +0.036 |
You | +0.035 |
Neg logit contributions | |
uth | -0.023 |
packs | -0.023 |
eth | -0.022 |
aj | -0.020 |
majesty | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ting | +0.117 |
aling | +0.102 |
wheel | +0.101 |
pping | +0.098 |
Looks | +0.095 |
Neg logit contributions | |
packs | -0.086 |
wife | -0.075 |
mom | -0.074 |
dad | -0.073 |
ies | -0.071 |
Token | big |
Token ID | 1263 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
ting | +0.048 |
course | +0.040 |
pped | +0.040 |
neath | +0.039 |
You | +0.038 |
Neg logit contributions | |
packs | -0.031 |
uth | -0.030 |
eth | -0.029 |
aj | -0.027 |
ies | -0.027 |
Token | oct |
Token ID | 19318 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
ting | +0.056 |
pped | +0.046 |
You | +0.045 |
neath | +0.044 |
Any | +0.044 |
Neg logit contributions | |
packs | -0.042 |
uth | -0.039 |
ies | -0.039 |
eth | -0.038 |
majesty | -0.037 |
Token | opus |
Token ID | 25790 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
ting | +0.005 |
neath | +0.004 |
course | +0.004 |
pped | +0.004 |
You | +0.004 |
Neg logit contributions | |
eth | -0.005 |
uth | -0.005 |
packs | -0.005 |
aj | -0.005 |
majesty | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
ting | +0.101 |
Great | +0.093 |
neath | +0.093 |
Higher | +0.090 |
Looks | +0.090 |
Neg logit contributions | |
packs | -0.059 |
ies | -0.054 |
eth | -0.045 |
uth | -0.045 |
aj | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
packs | +0.047 |
uth | +0.045 |
eth | +0.044 |
aj | +0.041 |
ies | +0.040 |
Neg logit contributions | |
ting | -0.037 |
course | -0.028 |
pped | -0.027 |
neath | -0.026 |
That | -0.025 |
Token | water |
Token ID | 1660 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ting | +0.082 |
pped | +0.066 |
Any | +0.066 |
course | +0.065 |
wheel | +0.065 |
Neg logit contributions | |
packs | -0.056 |
eth | -0.048 |
aj | -0.048 |
uth | -0.047 |
by | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ting | +0.050 |
neath | +0.043 |
course | +0.043 |
pped | +0.042 |
That | +0.041 |
Neg logit contributions | |
packs | -0.025 |
eth | -0.021 |
uth | -0.021 |
ies | -0.021 |
aj | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
ting | +0.029 |
course | +0.023 |
neath | +0.023 |
That | +0.022 |
You | +0.021 |
Neg logit contributions | |
packs | -0.039 |
uth | -0.038 |
eth | -0.037 |
aj | -0.035 |
majesty | -0.034 |
Token | said |
Token ID | 531 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
ting | +0.007 |
course | +0.005 |
neath | +0.005 |
pped | +0.005 |
That | +0.005 |
Neg logit contributions | |
packs | -0.008 |
uth | -0.007 |
eth | -0.007 |
aj | -0.007 |
majesty | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
packs | +0.053 |
uth | +0.051 |
eth | +0.050 |
aj | +0.047 |
majesty | +0.045 |
Neg logit contributions | |
ting | -0.057 |
course | -0.048 |
You | -0.044 |
That | -0.041 |
pped | -0.041 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
packs | +0.029 |
eth | +0.028 |
uth | +0.027 |
aj | +0.026 |
majesty | +0.024 |
Neg logit contributions | |
ting | -0.026 |
course | -0.022 |
You | -0.020 |
That | -0.020 |
neath | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
ting | +0.034 |
course | +0.028 |
You | +0.026 |
That | +0.026 |
pped | +0.026 |
Neg logit contributions | |
packs | -0.027 |
uth | -0.026 |
eth | -0.025 |
aj | -0.024 |
majesty | -0.023 |
Token | You |
Token ID | 921 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
ting | +0.038 |
pped | +0.028 |
neath | +0.027 |
course | +0.027 |
wheel | +0.024 |
Neg logit contributions | |
packs | -0.071 |
uth | -0.070 |
eth | -0.068 |
majesty | -0.066 |
aj | -0.065 |
Token | are |
Token ID | 389 |
Feature activation | -8.55e-03 |
Pos logit contributions | |
ting | +0.069 |
course | +0.054 |
neath | +0.053 |
pped | +0.052 |
That | +0.050 |
Neg logit contributions | |
packs | -0.068 |
uth | -0.065 |
eth | -0.065 |
aj | -0.060 |
majesty | -0.059 |
Token | sweet |
Token ID | 6029 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
packs | +0.017 |
uth | +0.017 |
eth | +0.016 |
aj | +0.015 |
majesty | +0.015 |
Neg logit contributions | |
ting | -0.016 |
course | -0.013 |
neath | -0.013 |
pped | -0.013 |
That | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
eth | +0.050 |
uth | +0.049 |
packs | +0.049 |
aj | +0.045 |
majesty | +0.044 |
Neg logit contributions | |
ting | -0.045 |
course | -0.036 |
You | -0.033 |
That | -0.031 |
pped | -0.031 |
Token | I |
Token ID | 314 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
ting | +0.041 |
pped | +0.031 |
neath | +0.031 |
course | +0.031 |
wheel | +0.027 |
Neg logit contributions | |
packs | -0.070 |
uth | -0.069 |
eth | -0.066 |
majesty | -0.063 |
aj | -0.063 |
Token | love |
Token ID | 1842 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ting | +0.074 |
course | +0.062 |
You | +0.059 |
neath | +0.058 |
That | +0.058 |
Neg logit contributions | |
packs | -0.069 |
uth | -0.067 |
eth | -0.064 |
aj | -0.062 |
majesty | -0.058 |
Token | your |
Token ID | 534 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
packs | +0.034 |
uth | +0.033 |
eth | +0.032 |
aj | +0.031 |
majesty | +0.030 |
Neg logit contributions | |
ting | -0.019 |
course | -0.014 |
neath | -0.013 |
pped | -0.013 |
That | -0.012 |
Token | haircut |
Token ID | 45548 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
packs | +0.066 |
eth | +0.065 |
uth | +0.064 |
ifi | +0.060 |
ighed | +0.054 |
Neg logit contributions | |
ting | -0.075 |
course | -0.075 |
You | -0.066 |
Any | -0.063 |
I | -0.062 |
Token | blocks |
Token ID | 7021 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
ting | +0.014 |
course | +0.011 |
neath | +0.011 |
pped | +0.011 |
That | +0.010 |
Neg logit contributions | |
packs | -0.012 |
uth | -0.012 |
eth | -0.012 |
aj | -0.011 |
majesty | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | +6.58e-03 |
Pos logit contributions | |
ting | +0.002 |
course | +0.002 |
neath | +0.002 |
pped | +0.002 |
You | +0.002 |
Neg logit contributions | |
packs | -0.002 |
uth | -0.002 |
eth | -0.002 |
aj | -0.002 |
ies | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
ting | +0.012 |
course | +0.010 |
neath | +0.009 |
pped | +0.009 |
That | +0.009 |
Neg logit contributions | |
packs | -0.014 |
uth | -0.013 |
eth | -0.013 |
aj | -0.012 |
majesty | -0.012 |
Token | blue |
Token ID | 4171 |
Feature activation | -7.25e-03 |
Pos logit contributions | |
ting | +0.066 |
course | +0.057 |
neath | +0.053 |
You | +0.049 |
That | +0.048 |
Neg logit contributions | |
uth | -0.084 |
packs | -0.082 |
eth | -0.079 |
aj | -0.074 |
ifi | -0.072 |
Token | blocks |
Token ID | 7021 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
packs | +0.014 |
uth | +0.014 |
eth | +0.013 |
aj | +0.013 |
majesty | +0.012 |
Neg logit contributions | |
ting | -0.015 |
course | -0.012 |
neath | -0.012 |
pped | -0.011 |
That | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
packs | +0.015 |
uth | +0.015 |
eth | +0.014 |
aj | +0.013 |
majesty | +0.013 |
Neg logit contributions | |
ting | -0.022 |
course | -0.018 |
neath | -0.018 |
pped | -0.018 |
You | -0.017 |
Token | but |
Token ID | 475 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
mind | +0.016 |
packs | +0.015 |
toes | +0.015 |
patients | +0.014 |
teeth | +0.014 |
Neg logit contributions | |
ting | -0.059 |
pped | -0.053 |
Good | -0.051 |
neath | -0.051 |
course | -0.050 |
Token | they |
Token ID | 484 |
Feature activation | +5.98e-03 |
Pos logit contributions | |
ting | +0.004 |
course | +0.003 |
neath | +0.003 |
pped | +0.003 |
You | +0.003 |
Neg logit contributions | |
packs | -0.006 |
uth | -0.006 |
eth | -0.006 |
aj | -0.006 |
ies | -0.005 |
Token | didn |
Token ID | 1422 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ting | +0.009 |
course | +0.007 |
pped | +0.007 |
neath | +0.006 |
That | +0.006 |
Neg logit contributions | |
packs | -0.015 |
uth | -0.015 |
eth | -0.014 |
aj | -0.014 |
majesty | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | +1.60e-03 |
Pos logit contributions | |
ting | +0.100 |
course | +0.082 |
ted | +0.075 |
Looks | +0.073 |
Good | +0.071 |
Neg logit contributions | |
eth | -0.067 |
packs | -0.060 |
uth | -0.056 |
allowance | -0.053 |
ilot | -0.053 |
Token | fit |
Token ID | 4197 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ting | +0.003 |
wheel | +0.003 |
course | +0.003 |
You | +0.002 |
That | +0.002 |
Neg logit contributions | |
uth | -0.003 |
packs | -0.003 |
aj | -0.003 |
eth | -0.003 |
majesty | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
ting | +0.057 |
course | +0.047 |
neath | +0.044 |
pped | +0.043 |
You | +0.042 |
Neg logit contributions | |
packs | -0.061 |
uth | -0.060 |
eth | -0.059 |
aj | -0.056 |
majesty | -0.054 |
Token | eat |
Token ID | 4483 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
packs | +0.042 |
uth | +0.041 |
aj | +0.040 |
eth | +0.040 |
ies | +0.037 |
Neg logit contributions | |
ting | -0.027 |
course | -0.026 |
neath | -0.022 |
wheel | -0.022 |
pped | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
ting | +0.044 |
course | +0.034 |
neath | +0.033 |
pped | +0.032 |
That | +0.031 |
Neg logit contributions | |
packs | -0.057 |
uth | -0.055 |
eth | -0.054 |
aj | -0.052 |
ies | -0.050 |
Token | cookies |
Token ID | 14746 |
Feature activation | -7.83e-03 |
Pos logit contributions | |
ting | +0.106 |
course | +0.086 |
neath | +0.085 |
pped | +0.085 |
That | +0.082 |
Neg logit contributions | |
packs | -0.089 |
uth | -0.085 |
eth | -0.084 |
aj | -0.080 |
patients | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
packs | +0.014 |
uth | +0.014 |
eth | +0.014 |
aj | +0.013 |
majesty | +0.012 |
Neg logit contributions | |
ting | -0.017 |
course | -0.014 |
neath | -0.013 |
pped | -0.013 |
That | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
ting | +0.020 |
course | +0.017 |
You | +0.016 |
That | +0.016 |
neath | +0.016 |
Neg logit contributions | |
packs | -0.027 |
uth | -0.026 |
eth | -0.025 |
ies | -0.025 |
aj | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
packs | +0.096 |
uth | +0.092 |
majesty | +0.091 |
spine | +0.088 |
aj | +0.088 |
Neg logit contributions | |
ting | -0.061 |
course | -0.056 |
That | -0.055 |
You | -0.054 |
neath | -0.050 |
Token | " |
Token ID | 1 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
packs | +0.063 |
uth | +0.061 |
eth | +0.059 |
aj | +0.057 |
majesty | +0.056 |
Neg logit contributions | |
ting | -0.055 |
course | -0.046 |
That | -0.044 |
You | -0.043 |
neath | -0.043 |
Token | Mom |
Token ID | 29252 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
ting | +0.103 |
course | +0.074 |
neath | +0.072 |
pped | +0.071 |
wheel | +0.063 |
Neg logit contributions | |
uth | -0.155 |
packs | -0.154 |
eth | -0.151 |
aj | -0.141 |
patients | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
packs | +0.010 |
uth | +0.010 |
eth | +0.010 |
aj | +0.009 |
majesty | +0.009 |
Neg logit contributions | |
ting | -0.015 |
course | -0.013 |
neath | -0.012 |
pped | -0.012 |
That | -0.012 |
Token | can |
Token ID | 460 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
packs | +0.026 |
uth | +0.025 |
eth | +0.025 |
aj | +0.024 |
majesty | +0.024 |
Neg logit contributions | |
ting | -0.023 |
course | -0.018 |
neath | -0.017 |
pped | -0.017 |
That | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
packs | +0.086 |
uth | +0.084 |
eth | +0.083 |
aj | +0.078 |
patients | +0.072 |
Neg logit contributions | |
ting | -0.125 |
course | -0.106 |
neath | -0.100 |
pped | -0.099 |
You | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
packs | +0.069 |
uth | +0.067 |
eth | +0.066 |
aj | +0.063 |
majesty | +0.061 |
Neg logit contributions | |
ting | -0.053 |
course | -0.042 |
neath | -0.040 |
pped | -0.040 |
That | -0.038 |
Token | cell |
Token ID | 2685 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ting | +0.088 |
course | +0.075 |
neath | +0.072 |
pped | +0.071 |
That | +0.070 |
Neg logit contributions | |
packs | -0.060 |
uth | -0.057 |
eth | -0.056 |
aj | -0.052 |
majesty | -0.049 |
Token | was |
Token ID | 373 |
Feature activation | +9.21e-03 |
Pos logit contributions | |
ting | +0.024 |
course | +0.019 |
neath | +0.018 |
pped | +0.018 |
That | +0.017 |
Neg logit contributions | |
packs | -0.030 |
uth | -0.029 |
eth | -0.029 |
aj | -0.027 |
majesty | -0.026 |
Token | mighty |
Token ID | 18680 |
Feature activation | -2.78e-03 |
Pos logit contributions | |
ting | +0.018 |
course | +0.014 |
neath | +0.014 |
pped | +0.013 |
That | +0.013 |
Neg logit contributions | |
packs | -0.018 |
uth | -0.018 |
eth | -0.018 |
aj | -0.017 |
majesty | -0.016 |
Token | once |
Token ID | 1752 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
packs | +0.005 |
uth | +0.004 |
eth | +0.004 |
ies | +0.004 |
patients | +0.004 |
Neg logit contributions | |
ting | -0.006 |
pped | -0.005 |
neath | -0.005 |
That | -0.005 |
course | -0.005 |
Token | again |
Token ID | 757 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
packs | +0.175 |
uth | +0.171 |
eth | +0.165 |
aj | +0.155 |
ies | +0.153 |
Neg logit contributions | |
ting | -0.153 |
course | -0.121 |
neath | -0.120 |
pped | -0.117 |
That | -0.113 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
packs | +0.085 |
uth | +0.082 |
eth | +0.082 |
aj | +0.077 |
majesty | +0.074 |
Neg logit contributions | |
ting | -0.095 |
course | -0.079 |
neath | -0.073 |
pped | -0.072 |
You | -0.072 |
Token | it |
Token ID | 340 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
ting | +0.023 |
course | +0.019 |
neath | +0.019 |
pped | +0.018 |
That | +0.017 |
Neg logit contributions | |
packs | -0.027 |
uth | -0.027 |
eth | -0.025 |
ies | -0.025 |
majesty | -0.024 |
Token | never |
Token ID | 1239 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
ting | +0.060 |
pped | +0.046 |
course | +0.046 |
neath | +0.045 |
Higher | +0.042 |
Neg logit contributions | |
packs | -0.065 |
uth | -0.063 |
eth | -0.062 |
ies | -0.059 |
patients | -0.058 |
Token | again |
Token ID | 757 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
packs | +0.017 |
uth | +0.017 |
eth | +0.016 |
aj | +0.016 |
majesty | +0.015 |
Neg logit contributions | |
ting | -0.015 |
course | -0.012 |
neath | -0.012 |
pped | -0.011 |
That | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
ting | +0.053 |
course | +0.044 |
neath | +0.042 |
pped | +0.041 |
You | +0.040 |
Neg logit contributions | |
packs | -0.055 |
uth | -0.054 |
eth | -0.053 |
aj | -0.050 |
majesty | -0.048 |
Token | big |
Token ID | 1263 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
uth | +0.139 |
packs | +0.135 |
eth | +0.130 |
ifi | +0.117 |
aj | +0.117 |
Neg logit contributions | |
ting | -0.171 |
course | -0.152 |
neath | -0.141 |
pped | -0.134 |
You | -0.132 |
Token | heart |
Token ID | 2612 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
uth | +0.029 |
packs | +0.027 |
eth | +0.026 |
aj | +0.024 |
ifi | +0.024 |
Neg logit contributions | |
ting | -0.036 |
course | -0.034 |
neath | -0.031 |
pped | -0.029 |
Good | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
uth | +0.067 |
packs | +0.062 |
eth | +0.061 |
majesty | +0.059 |
ifi | +0.058 |
Neg logit contributions | |
ting | -0.060 |
course | -0.048 |
neath | -0.046 |
pped | -0.045 |
wheel | -0.045 |
Token | support |
Token ID | 1104 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
packs | +0.123 |
uth | +0.119 |
eth | +0.116 |
aj | +0.110 |
majesty | +0.105 |
Neg logit contributions | |
ting | -0.132 |
course | -0.109 |
neath | -0.104 |
pped | -0.102 |
That | -0.100 |
Token | her |
Token ID | 607 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
packs | +0.010 |
uth | +0.010 |
eth | +0.009 |
aj | +0.009 |
majesty | +0.009 |
Neg logit contributions | |
ting | -0.009 |
course | -0.008 |
neath | -0.007 |
You | -0.007 |
pped | -0.007 |
Token | family |
Token ID | 1641 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
uth | +0.144 |
eth | +0.138 |
packs | +0.136 |
ifi | +0.131 |
aj | +0.124 |
Neg logit contributions | |
ting | -0.187 |
course | -0.160 |
neath | -0.145 |
You | -0.139 |
That | -0.138 |
Token | , |
Token ID | 11 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
packs | +0.070 |
uth | +0.070 |
eth | +0.068 |
aj | +0.064 |
majesty | +0.062 |
Neg logit contributions | |
ting | -0.085 |
course | -0.071 |
neath | -0.067 |
pped | -0.065 |
That | -0.065 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
packs | +0.087 |
uth | +0.084 |
eth | +0.083 |
aj | +0.078 |
majesty | +0.076 |
Neg logit contributions | |
ting | -0.078 |
course | -0.063 |
neath | -0.060 |
pped | -0.059 |
That | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
packs | +0.044 |
uth | +0.043 |
eth | +0.042 |
aj | +0.039 |
majesty | +0.038 |
Neg logit contributions | |
ting | -0.054 |
course | -0.045 |
neath | -0.043 |
pped | -0.043 |
That | -0.042 |
Token | even |
Token ID | 772 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
packs | +0.007 |
uth | +0.007 |
eth | +0.007 |
aj | +0.007 |
majesty | +0.006 |
Neg logit contributions | |
ting | -0.007 |
course | -0.006 |
neath | -0.005 |
pped | -0.005 |
You | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
packs | +0.031 |
uth | +0.030 |
eth | +0.030 |
aj | +0.028 |
majesty | +0.027 |
Neg logit contributions | |
ting | -0.024 |
course | -0.018 |
neath | -0.018 |
pped | -0.017 |
You | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
ting | +0.043 |
course | +0.034 |
neath | +0.034 |
pped | +0.034 |
That | +0.031 |
Neg logit contributions | |
packs | -0.049 |
uth | -0.046 |
eth | -0.044 |
patients | -0.043 |
ies | -0.042 |
Token | was |
Token ID | 373 |
Feature activation | -3.83e-05 |
Pos logit contributions | |
ting | +0.005 |
neath | +0.004 |
course | +0.004 |
pped | +0.004 |
Higher | +0.003 |
Neg logit contributions | |
packs | -0.005 |
uth | -0.005 |
eth | -0.005 |
ies | -0.004 |
patients | -0.004 |
Token | indeed |
Token ID | 5600 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
packs | +0.000 |
uth | +0.000 |
eth | +0.000 |
patients | +0.000 |
majesty | +0.000 |
Neg logit contributions | |
ting | -0.000 |
course | -0.000 |
neath | -0.000 |
pped | -0.000 |
That | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
packs | +0.089 |
uth | +0.086 |
eth | +0.083 |
aj | +0.079 |
majesty | +0.077 |
Neg logit contributions | |
ting | -0.083 |
course | -0.068 |
neath | -0.065 |
pped | -0.064 |
That | -0.061 |
Token | very |
Token ID | 845 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
uth | +0.004 |
packs | +0.004 |
eth | +0.004 |
majesty | +0.004 |
patients | +0.004 |
Neg logit contributions | |
ting | -0.006 |
pped | -0.005 |
neath | -0.005 |
course | -0.005 |
You | -0.005 |
Token | creative |
Token ID | 7325 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
packs | +0.164 |
uth | +0.153 |
eth | +0.152 |
aj | +0.142 |
ies | +0.132 |
Neg logit contributions | |
ting | -0.170 |
course | -0.142 |
neath | -0.132 |
You | -0.132 |
That | -0.132 |
Token | boy |
Token ID | 2933 |
Feature activation | -7.59e-03 |
Pos logit contributions | |
packs | +0.010 |
uth | +0.010 |
eth | +0.010 |
aj | +0.009 |
majesty | +0.008 |
Neg logit contributions | |
ting | -0.016 |
course | -0.014 |
neath | -0.013 |
pped | -0.013 |
That | -0.013 |
Token | ! |
Token ID | 0 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
packs | +0.014 |
uth | +0.013 |
eth | +0.013 |
aj | +0.012 |
majesty | +0.012 |
Neg logit contributions | |
ting | -0.016 |
course | -0.013 |
neath | -0.013 |
pped | -0.013 |
That | -0.012 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.28e-03 |
Pos logit contributions | |
ting | +0.053 |
course | +0.044 |
neath | +0.042 |
pped | +0.042 |
That | +0.041 |
Neg logit contributions | |
packs | -0.045 |
uth | -0.043 |
eth | -0.042 |
aj | -0.040 |
majesty | -0.038 |
Token | Once |
Token ID | 7454 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
packs | +0.013 |
eth | +0.012 |
uth | +0.012 |
aj | +0.011 |
ilot | +0.011 |
Neg logit contributions | |
ting | -0.015 |
course | -0.012 |
pped | -0.012 |
neath | -0.012 |
wheel | -0.011 |
Token | sound |
Token ID | 2128 |
Feature activation | +5.65e-03 |
Pos logit contributions | |
ting | +0.013 |
course | +0.011 |
neath | +0.010 |
pped | +0.010 |
That | +0.010 |
Neg logit contributions | |
packs | -0.014 |
uth | -0.014 |
aj | -0.013 |
eth | -0.013 |
majesty | -0.012 |
Token | echoed |
Token ID | 22211 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ting | +0.010 |
course | +0.008 |
neath | +0.008 |
pped | +0.008 |
You | +0.008 |
Neg logit contributions | |
packs | -0.011 |
uth | -0.011 |
eth | -0.011 |
ies | -0.010 |
aj | -0.010 |
Token | through |
Token ID | 832 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
packs | +0.028 |
uth | +0.027 |
eth | +0.027 |
aj | +0.025 |
ies | +0.024 |
Neg logit contributions | |
ting | -0.025 |
course | -0.020 |
neath | -0.019 |
pped | -0.019 |
You | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
packs | +0.049 |
uth | +0.047 |
eth | +0.047 |
aj | +0.045 |
majesty | +0.043 |
Neg logit contributions | |
ting | -0.032 |
course | -0.025 |
neath | -0.023 |
pped | -0.023 |
That | -0.022 |
Token | field |
Token ID | 2214 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
ting | +0.045 |
course | +0.036 |
neath | +0.034 |
pped | +0.033 |
That | +0.032 |
Neg logit contributions | |
packs | -0.055 |
uth | -0.054 |
eth | -0.053 |
aj | -0.050 |
majesty | -0.048 |
Token | once |
Token ID | 1752 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
packs | +0.050 |
uth | +0.048 |
eth | +0.047 |
aj | +0.043 |
ies | +0.042 |
Neg logit contributions | |
ting | -0.063 |
course | -0.052 |
neath | -0.051 |
pped | -0.050 |
You | -0.049 |
Token | more |
Token ID | 517 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
packs | +0.187 |
uth | +0.182 |
eth | +0.181 |
aj | +0.173 |
majesty | +0.167 |
Neg logit contributions | |
ting | -0.140 |
course | -0.112 |
neath | -0.103 |
pped | -0.102 |
That | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
packs | +0.123 |
eth | +0.116 |
uth | +0.116 |
aj | +0.114 |
majesty | +0.108 |
Neg logit contributions | |
ting | -0.124 |
course | -0.101 |
pped | -0.090 |
neath | -0.090 |
That | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
ting | +0.019 |
course | +0.015 |
neath | +0.015 |
pped | +0.015 |
You | +0.014 |
Neg logit contributions | |
packs | -0.024 |
uth | -0.023 |
eth | -0.022 |
aj | -0.021 |
ies | -0.021 |
Token | sky |
Token ID | 6766 |
Feature activation | +3.52e-03 |
Pos logit contributions | |
ting | +0.071 |
course | +0.059 |
neath | +0.056 |
pped | +0.055 |
That | +0.054 |
Neg logit contributions | |
packs | -0.064 |
uth | -0.062 |
eth | -0.061 |
aj | -0.057 |
majesty | -0.054 |
Token | lit |
Token ID | 6578 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
ting | +0.006 |
course | +0.005 |
neath | +0.004 |
pped | +0.004 |
That | +0.004 |
Neg logit contributions | |
packs | -0.008 |
uth | -0.008 |
eth | -0.008 |
aj | -0.007 |
majesty | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
packs | +0.017 |
uth | +0.016 |
eth | +0.016 |
aj | +0.015 |
patients | +0.014 |
Neg logit contributions | |
ting | -0.015 |
course | -0.013 |
neath | -0.012 |
pped | -0.012 |
That | -0.012 |
Token | park |
Token ID | 3952 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ting | +0.094 |
course | +0.077 |
neath | +0.074 |
pped | +0.073 |
You | +0.070 |
Neg logit contributions | |
packs | -0.090 |
uth | -0.087 |
eth | -0.085 |
aj | -0.081 |
majesty | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
packs | +0.025 |
uth | +0.025 |
eth | +0.024 |
aj | +0.024 |
majesty | +0.023 |
Neg logit contributions | |
ting | -0.025 |
course | -0.020 |
That | -0.017 |
You | -0.017 |
wheel | -0.017 |
Token | showing |
Token ID | 4478 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
packs | +0.034 |
uth | +0.033 |
eth | +0.031 |
aj | +0.031 |
ies | +0.029 |
Neg logit contributions | |
ting | -0.039 |
course | -0.033 |
neath | -0.033 |
pped | -0.031 |
That | -0.030 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ting | +0.037 |
course | +0.029 |
neath | +0.028 |
pped | +0.027 |
That | +0.026 |
Neg logit contributions | |
packs | -0.054 |
uth | -0.053 |
eth | -0.052 |
aj | -0.049 |
majesty | -0.048 |
Token | her |
Token ID | 607 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
packs | +0.027 |
uth | +0.025 |
eth | +0.024 |
ies | +0.023 |
aj | +0.023 |
Neg logit contributions | |
ting | -0.025 |
course | -0.021 |
neath | -0.020 |
pped | -0.020 |
You | -0.019 |
Token | special |
Token ID | 2041 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
uth | +0.171 |
packs | +0.166 |
eth | +0.165 |
ifi | +0.146 |
ilot | +0.141 |
Neg logit contributions | |
ting | -0.159 |
course | -0.145 |
pped | -0.133 |
neath | -0.129 |
That | -0.129 |
Token | treasure |
Token ID | 14068 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
packs | +0.084 |
uth | +0.082 |
eth | +0.080 |
aj | +0.074 |
patients | +0.071 |
Neg logit contributions | |
ting | -0.075 |
course | -0.066 |
pped | -0.059 |
neath | -0.059 |
That | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
packs | +0.091 |
uth | +0.091 |
eth | +0.088 |
aj | +0.082 |
majesty | +0.079 |
Neg logit contributions | |
ting | -0.116 |
course | -0.098 |
pped | -0.092 |
neath | -0.092 |
You | -0.089 |
Token | From |
Token ID | 3574 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ting | +0.033 |
course | +0.027 |
pped | +0.026 |
neath | +0.025 |
wheel | +0.024 |
Neg logit contributions | |
packs | -0.025 |
eth | -0.025 |
uth | -0.024 |
aj | -0.022 |
majesty | -0.021 |
Token | then |
Token ID | 788 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ting | +0.020 |
neath | +0.014 |
course | +0.014 |
pped | +0.013 |
You | +0.013 |
Neg logit contributions | |
uth | -0.034 |
packs | -0.034 |
eth | -0.032 |
aj | -0.032 |
ies | -0.031 |