Token | goes |
Token ID | 2925 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
o | +0.104 |
alone | +0.103 |
tank | +0.093 |
afloat | +0.088 |
forth | +0.087 |
Neg logit contributions | |
ves | -0.158 |
vows | -0.156 |
Her | -0.153 |
brist | -0.148 |
growth | -0.139 |
Token | " |
Token ID | 366 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
o | +0.164 |
alone | +0.135 |
forth | +0.132 |
polar | +0.132 |
tank | +0.131 |
Neg logit contributions | |
ves | -0.203 |
Her | -0.201 |
vows | -0.199 |
brist | -0.190 |
ork | -0.182 |
Token | ch |
Token ID | 354 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Her | +0.061 |
ves | +0.058 |
vows | +0.058 |
brist | +0.058 |
growth | +0.052 |
Neg logit contributions | |
o | -0.068 |
alone | -0.065 |
tank | -0.061 |
afloat | -0.059 |
forth | -0.059 |
Token | oo |
Token ID | 2238 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
o | +0.379 |
alone | +0.354 |
forth | +0.329 |
tank | +0.323 |
afloat | +0.316 |
Neg logit contributions | |
ves | -0.380 |
Her | -0.368 |
vows | -0.362 |
brist | -0.358 |
growth | -0.324 |
Token | cho |
Token ID | 1727 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Her | +0.022 |
vows | +0.021 |
ves | +0.021 |
brist | +0.021 |
blonde | +0.020 |
Neg logit contributions | |
o | -0.018 |
alone | -0.017 |
forth | -0.015 |
tank | -0.015 |
my | -0.014 |
Token | o |
Token ID | 78 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
alone | +0.410 |
o | +0.407 |
forth | +0.381 |
tank | +0.376 |
afloat | +0.370 |
Neg logit contributions | |
ves | -0.369 |
Her | -0.356 |
vows | -0.349 |
brist | -0.344 |
ork | -0.314 |
Token | cho |
Token ID | 1727 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
o | +0.972 |
alone | +0.915 |
forth | +0.826 |
tank | +0.817 |
afloat | +0.796 |
Neg logit contributions | |
ves | -1.206 |
vows | -1.183 |
Her | -1.182 |
brist | -1.159 |
growth | -1.053 |
Token | o |
Token ID | 78 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
alone | +0.403 |
o | +0.382 |
forth | +0.375 |
tank | +0.372 |
afloat | +0.365 |
Neg logit contributions | |
ves | -0.362 |
Her | -0.345 |
vows | -0.336 |
brist | -0.331 |
ork | -0.309 |
Token | ". |
Token ID | 1911 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
o | +0.948 |
alone | +0.909 |
forth | +0.825 |
tank | +0.819 |
afloat | +0.795 |
Neg logit contributions | |
ves | -1.195 |
vows | -1.154 |
Her | -1.150 |
brist | -1.124 |
ork | -1.045 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
o | +0.114 |
alone | +0.106 |
forth | +0.097 |
tank | +0.093 |
afloat | +0.092 |
Neg logit contributions | |
Her | -0.155 |
ves | -0.154 |
vows | -0.152 |
brist | -0.150 |
blonde | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
o | +0.235 |
alone | +0.233 |
forth | +0.227 |
afloat | +0.209 |
tank | +0.209 |
Neg logit contributions | |
Her | -0.299 |
ves | -0.295 |
vows | -0.269 |
brist | -0.268 |
ork | -0.257 |
Token | ch |
Token ID | 354 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Her | +0.061 |
ves | +0.058 |
vows | +0.058 |
brist | +0.058 |
growth | +0.052 |
Neg logit contributions | |
o | -0.068 |
alone | -0.065 |
tank | -0.061 |
afloat | -0.059 |
forth | -0.059 |
Token | oo |
Token ID | 2238 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
o | +0.379 |
alone | +0.354 |
forth | +0.329 |
tank | +0.323 |
afloat | +0.316 |
Neg logit contributions | |
ves | -0.380 |
Her | -0.368 |
vows | -0.362 |
brist | -0.358 |
growth | -0.324 |
Token | cho |
Token ID | 1727 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Her | +0.022 |
vows | +0.021 |
ves | +0.021 |
brist | +0.021 |
blonde | +0.020 |
Neg logit contributions | |
o | -0.018 |
alone | -0.017 |
forth | -0.015 |
tank | -0.015 |
my | -0.014 |
Token | o |
Token ID | 78 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
alone | +0.410 |
o | +0.407 |
forth | +0.381 |
tank | +0.376 |
afloat | +0.370 |
Neg logit contributions | |
ves | -0.369 |
Her | -0.356 |
vows | -0.349 |
brist | -0.344 |
ork | -0.314 |
Token | cho |
Token ID | 1727 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
o | +0.972 |
alone | +0.915 |
forth | +0.826 |
tank | +0.817 |
afloat | +0.796 |
Neg logit contributions | |
ves | -1.206 |
vows | -1.183 |
Her | -1.182 |
brist | -1.159 |
growth | -1.053 |
Token | o |
Token ID | 78 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
alone | +0.403 |
o | +0.382 |
forth | +0.375 |
tank | +0.372 |
afloat | +0.365 |
Neg logit contributions | |
ves | -0.362 |
Her | -0.345 |
vows | -0.336 |
brist | -0.331 |
ork | -0.309 |
Token | ". |
Token ID | 1911 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
o | +0.948 |
alone | +0.909 |
forth | +0.825 |
tank | +0.819 |
afloat | +0.795 |
Neg logit contributions | |
ves | -1.195 |
vows | -1.154 |
Her | -1.150 |
brist | -1.124 |
ork | -1.045 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
o | +0.114 |
alone | +0.106 |
forth | +0.097 |
tank | +0.093 |
afloat | +0.092 |
Neg logit contributions | |
Her | -0.155 |
ves | -0.154 |
vows | -0.152 |
brist | -0.150 |
blonde | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
o | +0.235 |
alone | +0.233 |
forth | +0.227 |
afloat | +0.209 |
tank | +0.209 |
Neg logit contributions | |
Her | -0.299 |
ves | -0.295 |
vows | -0.269 |
brist | -0.268 |
ork | -0.257 |
Token | They |
Token ID | 2990 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
o | +0.265 |
alone | +0.248 |
forth | +0.227 |
tank | +0.224 |
afloat | +0.219 |
Neg logit contributions | |
Her | -0.254 |
ves | -0.254 |
vows | -0.250 |
brist | -0.246 |
blonde | -0.223 |
Token | both |
Token ID | 1111 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
ves | +0.045 |
Her | +0.045 |
vows | +0.044 |
brist | +0.044 |
growth | +0.040 |
Neg logit contributions | |
o | -0.039 |
alone | -0.036 |
forth | -0.032 |
tank | -0.032 |
my | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
vows | +0.113 |
ves | +0.110 |
brist | +0.108 |
Her | +0.108 |
growth | +0.100 |
Neg logit contributions | |
alone | -0.085 |
o | -0.084 |
forth | -0.075 |
my | -0.072 |
tank | -0.067 |
Token | when |
Token ID | 618 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
o | +0.038 |
alone | +0.036 |
forth | +0.033 |
my | +0.032 |
tank | +0.031 |
Neg logit contributions | |
vows | -0.043 |
ves | -0.043 |
Her | -0.042 |
brist | -0.041 |
growth | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
o | +0.065 |
alone | +0.062 |
forth | +0.057 |
tank | +0.054 |
my | +0.054 |
Neg logit contributions | |
ves | -0.072 |
vows | -0.072 |
Her | -0.072 |
brist | -0.071 |
growth | -0.065 |
Token | k |
Token ID | 479 |
Feature activation | +1.63e-04 |
Pos logit contributions | |
o | +0.253 |
alone | +0.241 |
tank | +0.219 |
forth | +0.219 |
polar | +0.210 |
Neg logit contributions | |
Her | -0.277 |
ves | -0.276 |
vows | -0.270 |
brist | -0.263 |
growth | -0.245 |
Token | idd |
Token ID | 1638 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
o | +0.000 |
alone | +0.000 |
forth | +0.000 |
tank | +0.000 |
afloat | +0.000 |
Neg logit contributions | |
Her | -0.000 |
ves | -0.000 |
vows | -0.000 |
brist | -0.000 |
blonde | -0.000 |
Token | o |
Token ID | 78 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
o | +0.263 |
alone | +0.222 |
forth | +0.182 |
tank | +0.179 |
my | +0.171 |
Neg logit contributions | |
ves | -0.718 |
Her | -0.714 |
vows | -0.712 |
brist | -0.704 |
blonde | -0.661 |
Token | got |
Token ID | 1392 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
o | +1.036 |
alone | +0.945 |
tank | +0.847 |
forth | +0.842 |
my | +0.829 |
Neg logit contributions | |
Her | -1.150 |
ves | -1.141 |
vows | -1.130 |
brist | -1.116 |
growth | -1.019 |
Token | to |
Token ID | 284 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
o | +0.068 |
alone | +0.062 |
forth | +0.057 |
tank | +0.056 |
afloat | +0.054 |
Neg logit contributions | |
Her | -0.095 |
ves | -0.093 |
vows | -0.093 |
brist | -0.093 |
blonde | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ves | +0.015 |
Her | +0.015 |
vows | +0.015 |
brist | +0.014 |
blonde | +0.013 |
Neg logit contributions | |
o | -0.011 |
alone | -0.010 |
tank | -0.009 |
forth | -0.009 |
afloat | -0.009 |
Token | university |
Token ID | 6403 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
o | +0.259 |
alone | +0.251 |
tank | +0.230 |
forth | +0.225 |
wreck | +0.220 |
Neg logit contributions | |
ves | -0.268 |
Her | -0.264 |
vows | -0.256 |
brist | -0.253 |
growth | -0.233 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
Her | +0.239 |
brist | +0.238 |
vows | +0.236 |
ves | +0.235 |
growth | +0.220 |
Neg logit contributions | |
o | -0.194 |
alone | -0.188 |
forth | -0.162 |
tank | -0.160 |
my | -0.159 |
Token | L |
Token ID | 43 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
o | +0.306 |
alone | +0.292 |
forth | +0.274 |
tank | +0.270 |
afloat | +0.265 |
Neg logit contributions | |
Her | -0.228 |
ves | -0.219 |
vows | -0.209 |
brist | -0.205 |
blonde | -0.186 |
Token | ila |
Token ID | 10102 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
o | +0.151 |
alone | +0.142 |
my | +0.131 |
forth | +0.126 |
tank | +0.125 |
Neg logit contributions | |
vows | -0.104 |
ves | -0.101 |
brist | -0.097 |
Her | -0.096 |
blonde | -0.090 |
Token | screamed |
Token ID | 25421 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
o | +0.060 |
alone | +0.055 |
my | +0.049 |
forth | +0.048 |
tank | +0.048 |
Neg logit contributions | |
ves | -0.075 |
Her | -0.074 |
vows | -0.073 |
brist | -0.071 |
growth | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
o | +0.124 |
alone | +0.120 |
forth | +0.103 |
tank | +0.101 |
my | +0.099 |
Neg logit contributions | |
ves | -0.178 |
vows | -0.176 |
Her | -0.168 |
brist | -0.166 |
growth | -0.163 |
Token | Nem |
Token ID | 22547 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
o | +0.120 |
alone | +0.111 |
forth | +0.102 |
tank | +0.101 |
afloat | +0.099 |
Neg logit contributions | |
ves | -0.122 |
Her | -0.122 |
vows | -0.121 |
brist | -0.119 |
blonde | -0.109 |
Token | o |
Token ID | 78 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
alone | +0.158 |
forth | +0.114 |
wreck | +0.080 |
afloat | +0.078 |
igator | +0.054 |
Neg logit contributions | |
ves | -1.395 |
vows | -1.380 |
Her | -1.362 |
brist | -1.321 |
ork | -1.280 |
Token | hid |
Token ID | 24519 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
o | +1.018 |
alone | +0.935 |
tank | +0.831 |
forth | +0.826 |
my | +0.806 |
Neg logit contributions | |
Her | -1.159 |
ves | -1.145 |
vows | -1.136 |
brist | -1.133 |
blonde | -1.055 |
Token | behind |
Token ID | 2157 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
o | +0.146 |
alone | +0.117 |
| | +0.115 |
my | +0.114 |
tank | +0.114 |
Neg logit contributions | |
Her | -0.172 |
ves | -0.170 |
brist | -0.167 |
vows | -0.165 |
growth | -0.152 |
Token | a |
Token ID | 257 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
o | +0.289 |
alone | +0.281 |
tank | +0.244 |
polar | +0.239 |
my | +0.224 |
Neg logit contributions | |
ves | -0.482 |
vows | -0.472 |
Her | -0.468 |
brist | -0.458 |
blonde | -0.417 |
Token | coral |
Token ID | 29537 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ves | +0.144 |
Her | +0.141 |
vows | +0.139 |
brist | +0.139 |
ork | +0.131 |
Neg logit contributions | |
o | -0.141 |
alone | -0.124 |
forth | -0.123 |
my | -0.112 |
afloat | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
o | +0.182 |
alone | +0.175 |
tank | +0.159 |
forth | +0.149 |
afloat | +0.147 |
Neg logit contributions | |
Her | -0.237 |
ves | -0.233 |
vows | -0.233 |
brist | -0.232 |
blonde | -0.217 |
Token | wide |
Token ID | 3094 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
o | +0.194 |
alone | +0.191 |
tank | +0.166 |
forth | +0.166 |
my | +0.161 |
Neg logit contributions | |
ves | -0.223 |
Her | -0.220 |
vows | -0.218 |
brist | -0.215 |
ork | -0.198 |
Token | eyes |
Token ID | 2951 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
alone | +0.076 |
o | +0.075 |
tank | +0.070 |
forth | +0.069 |
polar | +0.067 |
Neg logit contributions | |
Her | -0.064 |
ves | -0.063 |
brist | -0.058 |
vows | -0.058 |
ork | -0.054 |
Token | as |
Token ID | 355 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
brist | +0.574 |
vows | +0.569 |
ves | +0.568 |
Her | +0.564 |
growth | +0.552 |
Neg logit contributions | |
alone | -0.320 |
o | -0.313 |
my | -0.249 |
tank | -0.235 |
down | -0.229 |
Token | Z |
Token ID | 1168 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
Her | +0.044 |
ves | +0.043 |
vows | +0.043 |
brist | +0.043 |
growth | +0.039 |
Neg logit contributions | |
o | -0.046 |
alone | -0.044 |
forth | -0.039 |
tank | -0.039 |
my | -0.038 |
Token | ipp |
Token ID | 3974 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
o | +0.194 |
alone | +0.181 |
forth | +0.166 |
tank | +0.164 |
my | +0.161 |
Neg logit contributions | |
ves | -0.162 |
Her | -0.161 |
vows | -0.161 |
brist | -0.158 |
blonde | -0.142 |
Token | o |
Token ID | 78 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
ves | +0.092 |
Her | +0.090 |
vows | +0.090 |
brist | +0.087 |
blonde | +0.079 |
Neg logit contributions | |
o | -0.082 |
alone | -0.079 |
forth | -0.075 |
tank | -0.073 |
afloat | -0.072 |
Token | waved |
Token ID | 26834 |
Feature activation | +9.69e-02 |
Pos logit contributions | |
o | +1.040 |
alone | +0.922 |
my | +0.821 |
tank | +0.811 |
forth | +0.796 |
Neg logit contributions | |
Her | -1.162 |
ves | -1.155 |
brist | -1.141 |
vows | -1.119 |
growth | -1.043 |
Token | his |
Token ID | 465 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
o | +0.174 |
alone | +0.168 |
forth | +0.145 |
tank | +0.144 |
polar | +0.142 |
Neg logit contributions | |
ves | -0.192 |
brist | -0.185 |
vows | -0.183 |
Her | -0.183 |
growth | -0.173 |
Token | wand |
Token ID | 11569 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
o | +0.660 |
alone | +0.625 |
forth | +0.570 |
tank | +0.568 |
afloat | +0.552 |
Neg logit contributions | |
ves | -0.556 |
Her | -0.554 |
vows | -0.544 |
brist | -0.537 |
growth | -0.490 |
Token | and |
Token ID | 290 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
brist | +0.425 |
Her | +0.424 |
ves | +0.423 |
vows | +0.420 |
growth | +0.404 |
Neg logit contributions | |
alone | -0.287 |
o | -0.277 |
tank | -0.231 |
forth | -0.228 |
afloat | -0.223 |
Token | said |
Token ID | 531 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
o | +0.097 |
alone | +0.090 |
forth | +0.081 |
tank | +0.080 |
afloat | +0.078 |
Neg logit contributions | |
ves | -0.111 |
Her | -0.110 |
vows | -0.110 |
brist | -0.108 |
blonde | -0.099 |
Token | Pick |
Token ID | 12346 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
o | +0.297 |
alone | +0.287 |
tank | +0.253 |
my | +0.249 |
polar | +0.244 |
Neg logit contributions | |
vows | -0.303 |
ves | -0.296 |
Her | -0.295 |
brist | -0.289 |
growth | -0.262 |
Token | - |
Token ID | 12 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
o | +0.113 |
alone | +0.103 |
forth | +0.091 |
tank | +0.090 |
afloat | +0.087 |
Neg logit contributions | |
ves | -0.168 |
Her | -0.167 |
vows | -0.167 |
brist | -0.164 |
blonde | -0.152 |
Token | a |
Token ID | 64 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
o | +0.047 |
alone | +0.044 |
forth | +0.040 |
my | +0.039 |
tank | +0.039 |
Neg logit contributions | |
ves | -0.044 |
vows | -0.044 |
Her | -0.043 |
brist | -0.042 |
growth | -0.038 |
Token | - |
Token ID | 12 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
ves | +0.069 |
Her | +0.069 |
vows | +0.069 |
brist | +0.068 |
growth | +0.063 |
Neg logit contributions | |
o | -0.055 |
alone | -0.051 |
tank | -0.045 |
forth | -0.045 |
my | -0.044 |
Token | bo |
Token ID | 2127 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
o | +0.050 |
alone | +0.045 |
my | +0.042 |
forth | +0.041 |
tank | +0.040 |
Neg logit contributions | |
ves | -0.041 |
vows | -0.041 |
brist | -0.040 |
Her | -0.039 |
growth | -0.036 |
Token | o |
Token ID | 78 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
o | +0.175 |
alone | +0.126 |
forth | +0.068 |
tank | +0.062 |
my | +0.049 |
Neg logit contributions | |
ves | -1.183 |
vows | -1.179 |
Her | -1.178 |
brist | -1.166 |
blonde | -1.105 |
Token | . |
Token ID | 13 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
o | +0.960 |
alone | +0.885 |
forth | +0.792 |
tank | +0.782 |
my | +0.763 |
Neg logit contributions | |
ves | -1.186 |
vows | -1.179 |
Her | -1.179 |
brist | -1.162 |
growth | -1.069 |
Token | He |
Token ID | 679 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
o | +0.063 |
alone | +0.059 |
forth | +0.055 |
afloat | +0.053 |
tank | +0.052 |
Neg logit contributions | |
Her | -0.072 |
ves | -0.070 |
vows | -0.070 |
brist | -0.069 |
blonde | -0.064 |
Token | hopped |
Token ID | 45230 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
o | +0.505 |
alone | +0.454 |
tank | +0.405 |
forth | +0.405 |
my | +0.400 |
Neg logit contributions | |
ves | -0.628 |
Her | -0.623 |
vows | -0.622 |
brist | -0.618 |
growth | -0.578 |
Token | closer |
Token ID | 5699 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
o | +0.087 |
alone | +0.076 |
forth | +0.074 |
polar | +0.070 |
wreck | +0.070 |
Neg logit contributions | |
Her | -0.142 |
vows | -0.137 |
ves | -0.136 |
brist | -0.134 |
ribbon | -0.126 |
Token | and |
Token ID | 290 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
o | +0.313 |
alone | +0.292 |
forth | +0.248 |
my | +0.242 |
tank | +0.240 |
Neg logit contributions | |
vows | -0.445 |
ves | -0.445 |
brist | -0.439 |
Her | -0.438 |
growth | -0.408 |
Token | Oh |
Token ID | 5812 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
Her | +0.129 |
brist | +0.121 |
ves | +0.120 |
vows | +0.118 |
blonde | +0.108 |
Neg logit contributions | |
o | -0.145 |
alone | -0.138 |
forth | -0.128 |
tank | -0.128 |
afloat | -0.127 |
Token | no |
Token ID | 645 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
o | +0.145 |
alone | +0.132 |
my | +0.119 |
forth | +0.119 |
tank | +0.118 |
Neg logit contributions | |
ves | -0.173 |
Her | -0.171 |
vows | -0.168 |
brist | -0.163 |
growth | -0.158 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
vows | +0.154 |
ves | +0.154 |
Her | +0.153 |
brist | +0.146 |
growth | +0.142 |
Neg logit contributions | |
o | -0.120 |
alone | -0.111 |
forth | -0.103 |
my | -0.099 |
tank | -0.098 |
Token | cried |
Token ID | 16896 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
o | +0.342 |
alone | +0.313 |
tank | +0.273 |
forth | +0.270 |
my | +0.264 |
Neg logit contributions | |
vows | -0.468 |
ves | -0.467 |
brist | -0.456 |
Her | -0.454 |
growth | -0.423 |
Token | Nem |
Token ID | 22547 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
o | +0.260 |
alone | +0.247 |
tank | +0.216 |
forth | +0.213 |
afloat | +0.207 |
Neg logit contributions | |
ves | -0.348 |
vows | -0.345 |
Her | -0.334 |
brist | -0.328 |
growth | -0.311 |
Token | o |
Token ID | 78 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
alone | +0.160 |
forth | +0.142 |
wreck | +0.133 |
tank | +0.118 |
afloat | +0.092 |
Neg logit contributions | |
Her | -1.376 |
ves | -1.368 |
vows | -1.324 |
brist | -1.294 |
Her | -1.268 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
o | +1.035 |
alone | +0.958 |
forth | +0.850 |
tank | +0.844 |
my | +0.835 |
Neg logit contributions | |
ves | -1.124 |
vows | -1.120 |
Her | -1.113 |
brist | -1.099 |
growth | -1.012 |
Token | " |
Token ID | 366 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
o | +0.066 |
alone | +0.063 |
forth | +0.062 |
afloat | +0.058 |
wreck | +0.057 |
Neg logit contributions | |
Her | -0.054 |
vows | -0.053 |
ves | -0.052 |
brist | -0.050 |
Her | -0.048 |
Token | We |
Token ID | 1135 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
Her | +0.073 |
brist | +0.063 |
ves | +0.062 |
growth | +0.058 |
blonde | +0.054 |
Neg logit contributions | |
o | -0.093 |
alone | -0.085 |
tank | -0.084 |
forth | -0.084 |
polar | -0.080 |
Token | have |
Token ID | 423 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
o | +0.173 |
alone | +0.160 |
forth | +0.149 |
afloat | +0.144 |
tank | +0.143 |
Neg logit contributions | |
vows | -0.174 |
ves | -0.172 |
Her | -0.172 |
brist | -0.171 |
blonde | -0.156 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
o | +0.344 |
alone | +0.322 |
tank | +0.288 |
forth | +0.284 |
my | +0.278 |
Neg logit contributions | |
ves | -0.353 |
Her | -0.352 |
vows | -0.347 |
brist | -0.342 |
growth | -0.313 |
Token | with |
Token ID | 351 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
o | +0.442 |
alone | +0.403 |
forth | +0.370 |
tank | +0.367 |
afloat | +0.361 |
Neg logit contributions | |
ves | -0.482 |
vows | -0.478 |
Her | -0.477 |
brist | -0.470 |
blonde | -0.427 |
Token | a |
Token ID | 257 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
o | +0.290 |
alone | +0.273 |
forth | +0.245 |
tank | +0.241 |
my | +0.234 |
Neg logit contributions | |
ves | -0.333 |
vows | -0.330 |
Her | -0.330 |
brist | -0.324 |
growth | -0.296 |
Token | boo |
Token ID | 22513 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ves | +0.122 |
vows | +0.121 |
Her | +0.121 |
brist | +0.118 |
blonde | +0.108 |
Neg logit contributions | |
o | -0.120 |
alone | -0.112 |
forth | -0.102 |
tank | -0.100 |
afloat | -0.098 |
Token | - |
Token ID | 12 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
o | +0.406 |
alone | +0.382 |
tank | +0.362 |
afloat | +0.358 |
forth | +0.355 |
Neg logit contributions | |
ves | -0.347 |
Her | -0.342 |
brist | -0.340 |
vows | -0.334 |
ork | -0.291 |
Token | bo |
Token ID | 2127 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
o | +0.036 |
alone | +0.032 |
forth | +0.029 |
tank | +0.028 |
afloat | +0.027 |
Neg logit contributions | |
ves | -0.058 |
Her | -0.058 |
vows | -0.058 |
brist | -0.057 |
blonde | -0.053 |
Token | o |
Token ID | 78 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
alone | +0.069 |
o | +0.066 |
forth | +0.048 |
afloat | +0.034 |
tank | +0.020 |
Neg logit contributions | |
ves | -1.224 |
Her | -1.205 |
vows | -1.200 |
brist | -1.177 |
ork | -1.128 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
o | +0.969 |
alone | +0.899 |
forth | +0.835 |
afloat | +0.824 |
tank | +0.823 |
Neg logit contributions | |
ves | -1.134 |
vows | -1.119 |
Her | -1.116 |
brist | -1.095 |
blonde | -0.993 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
o | +0.058 |
alone | +0.055 |
forth | +0.055 |
afloat | +0.053 |
tank | +0.050 |
Neg logit contributions | |
Her | -0.058 |
brist | -0.054 |
ves | -0.054 |
vows | -0.054 |
Her | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
forth | +0.235 |
o | +0.231 |
alone | +0.229 |
afloat | +0.217 |
tank | +0.212 |
Neg logit contributions | |
Her | -0.274 |
ves | -0.263 |
brist | -0.236 |
vows | -0.232 |
ork | -0.232 |
Token | Later |
Token ID | 18602 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
o | +0.288 |
alone | +0.273 |
forth | +0.257 |
tank | +0.253 |
afloat | +0.250 |
Neg logit contributions | |
Her | -0.212 |
ves | -0.205 |
vows | -0.196 |
brist | -0.195 |
blonde | -0.175 |
Token | that |
Token ID | 326 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ves | +0.117 |
vows | +0.116 |
Her | +0.115 |
brist | +0.113 |
blonde | +0.102 |
Neg logit contributions | |
o | -0.153 |
alone | -0.146 |
forth | -0.134 |
tank | -0.132 |
polar | -0.129 |
Token | him |
Token ID | 683 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Her | +0.301 |
ves | +0.278 |
brist | +0.263 |
vows | +0.263 |
growth | +0.242 |
Neg logit contributions | |
o | -0.347 |
alone | -0.340 |
forth | -0.319 |
tank | -0.318 |
polar | -0.304 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
o | +0.283 |
alone | +0.259 |
forth | +0.241 |
tank | +0.235 |
afloat | +0.234 |
Neg logit contributions | |
ves | -0.301 |
vows | -0.300 |
Her | -0.295 |
brist | -0.288 |
blonde | -0.266 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
o | +0.039 |
alone | +0.037 |
forth | +0.036 |
afloat | +0.034 |
wreck | +0.033 |
Neg logit contributions | |
Her | -0.048 |
ves | -0.045 |
vows | -0.045 |
brist | -0.044 |
Her | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
o | +0.239 |
alone | +0.233 |
forth | +0.233 |
afloat | +0.214 |
tank | +0.212 |
Neg logit contributions | |
Her | -0.297 |
ves | -0.289 |
brist | -0.264 |
vows | -0.263 |
growth | -0.254 |
Token | Le |
Token ID | 3123 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
o | +0.307 |
alone | +0.292 |
forth | +0.273 |
tank | +0.268 |
afloat | +0.264 |
Neg logit contributions | |
Her | -0.240 |
ves | -0.235 |
vows | -0.226 |
brist | -0.223 |
blonde | -0.201 |
Token | o |
Token ID | 78 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ves | +0.067 |
vows | +0.065 |
Her | +0.064 |
brist | +0.062 |
growth | +0.061 |
Neg logit contributions | |
alone | -0.035 |
forth | -0.032 |
afloat | -0.031 |
o | -0.030 |
tank | -0.030 |
Token | 's |
Token ID | 338 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
o | +1.025 |
alone | +0.940 |
tank | +0.848 |
forth | +0.848 |
my | +0.825 |
Neg logit contributions | |
Her | -1.126 |
ves | -1.123 |
vows | -1.106 |
brist | -1.093 |
blonde | -1.003 |
Token | best |
Token ID | 1266 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
o | +0.222 |
alone | +0.208 |
forth | +0.190 |
tank | +0.190 |
polar | +0.183 |
Neg logit contributions | |
ves | -0.200 |
Her | -0.200 |
vows | -0.197 |
brist | -0.193 |
growth | -0.176 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
o | +0.105 |
alone | +0.097 |
forth | +0.087 |
tank | +0.085 |
afloat | +0.084 |
Neg logit contributions | |
ves | -0.141 |
vows | -0.140 |
Her | -0.140 |
brist | -0.137 |
blonde | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
o | +0.204 |
alone | +0.191 |
forth | +0.176 |
tank | +0.173 |
afloat | +0.173 |
Neg logit contributions | |
ves | -0.208 |
vows | -0.207 |
Her | -0.205 |
brist | -0.200 |
blonde | -0.184 |
Token | a |
Token ID | 257 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
o | +0.038 |
alone | +0.036 |
forth | +0.033 |
afloat | +0.033 |
tank | +0.032 |
Neg logit contributions | |
Her | -0.051 |
ves | -0.050 |
vows | -0.050 |
brist | -0.048 |
blonde | -0.046 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Her | +0.349 |
ves | +0.338 |
brist | +0.329 |
vows | +0.328 |
growth | +0.317 |
Neg logit contributions | |
o | -0.240 |
alone | -0.226 |
tank | -0.196 |
my | -0.195 |
forth | -0.190 |
Token | a |
Token ID | 257 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
o | +0.298 |
alone | +0.289 |
my | +0.256 |
polar | +0.247 |
tank | +0.247 |
Neg logit contributions | |
vows | -0.353 |
ves | -0.332 |
Her | -0.312 |
brist | -0.309 |
ork | -0.295 |
Token | mark |
Token ID | 1317 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
ves | +0.114 |
Her | +0.114 |
vows | +0.114 |
brist | +0.113 |
blonde | +0.103 |
Neg logit contributions | |
o | -0.121 |
alone | -0.111 |
forth | -0.103 |
afloat | -0.099 |
tank | -0.099 |
Token | on |
Token ID | 319 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
o | +0.050 |
alone | +0.048 |
forth | +0.038 |
my | +0.038 |
tank | +0.035 |
Neg logit contributions | |
vows | -0.114 |
Her | -0.110 |
ves | -0.109 |
brist | -0.109 |
growth | -0.106 |
Token | Bob |
Token ID | 5811 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
alone | +0.156 |
o | +0.137 |
tank | +0.118 |
my | +0.117 |
his | +0.115 |
Neg logit contributions | |
vows | -0.475 |
ves | -0.460 |
Her | -0.421 |
owers | -0.417 |
brist | -0.410 |
Token | o |
Token ID | 78 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
o | +0.384 |
alone | +0.361 |
tank | +0.327 |
forth | +0.326 |
afloat | +0.324 |
Neg logit contributions | |
Her | -0.446 |
ves | -0.439 |
brist | -0.433 |
vows | -0.426 |
blonde | -0.400 |
Token | 's |
Token ID | 338 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
o | +0.984 |
alone | +0.909 |
forth | +0.812 |
tank | +0.801 |
my | +0.788 |
Neg logit contributions | |
vows | -1.179 |
ves | -1.172 |
Her | -1.166 |
brist | -1.146 |
growth | -1.055 |
Token | arm |
Token ID | 3211 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
o | +0.202 |
alone | +0.194 |
tank | +0.173 |
forth | +0.172 |
my | +0.168 |
Neg logit contributions | |
ves | -0.215 |
vows | -0.211 |
Her | -0.209 |
brist | -0.202 |
blonde | -0.186 |
Token | and |
Token ID | 290 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
vows | +0.021 |
Her | +0.020 |
ves | +0.020 |
brist | +0.019 |
growth | +0.019 |
Neg logit contributions | |
o | -0.014 |
alone | -0.014 |
my | -0.012 |
forth | -0.011 |
tank | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
o | +0.084 |
alone | +0.076 |
forth | +0.069 |
my | +0.066 |
tank | +0.066 |
Neg logit contributions | |
vows | -0.116 |
ves | -0.115 |
Her | -0.113 |
brist | -0.111 |
ork | -0.109 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
o | +0.179 |
alone | +0.165 |
tank | +0.134 |
polar | +0.127 |
Nem | +0.126 |
Neg logit contributions | |
brist | -0.269 |
growth | -0.268 |
ves | -0.264 |
vows | -0.263 |
Her | -0.258 |
Token | two |
Token ID | 734 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
o | +0.533 |
alone | +0.508 |
forth | +0.454 |
tank | +0.446 |
my | +0.439 |
Neg logit contributions | |
vows | -0.540 |
ves | -0.540 |
Her | -0.532 |
brist | -0.521 |
growth | -0.485 |
Token | best |
Token ID | 1266 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
Her | +0.183 |
ves | +0.181 |
brist | +0.180 |
vows | +0.180 |
growth | +0.165 |
Neg logit contributions | |
o | -0.150 |
alone | -0.141 |
tank | -0.126 |
forth | -0.126 |
my | -0.125 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
o | +0.133 |
alone | +0.122 |
forth | +0.109 |
tank | +0.108 |
my | +0.105 |
Neg logit contributions | |
Her | -0.172 |
ves | -0.170 |
brist | -0.169 |
vows | -0.168 |
growth | -0.156 |
Token | , |
Token ID | 11 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
o | +0.259 |
alone | +0.240 |
forth | +0.214 |
tank | +0.211 |
my | +0.208 |
Neg logit contributions | |
Her | -0.304 |
ves | -0.303 |
brist | -0.302 |
vows | -0.298 |
growth | -0.277 |
Token | Mom |
Token ID | 11254 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
o | +0.051 |
alone | +0.047 |
forth | +0.042 |
tank | +0.042 |
afloat | +0.041 |
Neg logit contributions | |
ves | -0.065 |
Her | -0.064 |
vows | -0.064 |
brist | -0.063 |
blonde | -0.058 |
Token | o |
Token ID | 78 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
o | +0.087 |
alone | +0.081 |
forth | +0.070 |
afloat | +0.069 |
tank | +0.069 |
Neg logit contributions | |
Her | -0.167 |
ves | -0.167 |
vows | -0.167 |
brist | -0.164 |
blonde | -0.153 |
Token | and |
Token ID | 290 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
o | +1.007 |
alone | +0.913 |
tank | +0.819 |
forth | +0.817 |
my | +0.799 |
Neg logit contributions | |
Her | -1.148 |
ves | -1.146 |
vows | -1.138 |
brist | -1.128 |
growth | -1.038 |
Token | L |
Token ID | 406 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
o | +0.086 |
alone | +0.081 |
forth | +0.072 |
afloat | +0.072 |
tank | +0.071 |
Neg logit contributions | |
vows | -0.119 |
Her | -0.119 |
ves | -0.118 |
brist | -0.116 |
blonde | -0.108 |
Token | ola |
Token ID | 5708 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
o | +0.260 |
alone | +0.244 |
forth | +0.225 |
tank | +0.222 |
afloat | +0.218 |
Neg logit contributions | |
ves | -0.232 |
Her | -0.230 |
vows | -0.229 |
brist | -0.224 |
blonde | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
o | +0.005 |
alone | +0.004 |
my | +0.004 |
tank | +0.004 |
forth | +0.003 |
Neg logit contributions | |
brist | -0.006 |
ves | -0.006 |
Her | -0.006 |
vows | -0.006 |
growth | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
o | +0.045 |
alone | +0.044 |
forth | +0.041 |
afloat | +0.039 |
tank | +0.039 |
Neg logit contributions | |
Her | -0.040 |
vows | -0.038 |
ves | -0.038 |
brist | -0.038 |
blonde | -0.035 |
Token | got |
Token ID | 1392 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
o | +0.120 |
alone | +0.105 |
tank | +0.098 |
forth | +0.097 |
afloat | +0.096 |
Neg logit contributions | |
Her | -0.157 |
ves | -0.157 |
brist | -0.154 |
vows | -0.154 |
blonde | -0.141 |
Token | a |
Token ID | 257 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
o | +0.075 |
alone | +0.063 |
tank | +0.060 |
forth | +0.059 |
afloat | +0.057 |
Neg logit contributions | |
Her | -0.118 |
brist | -0.116 |
ves | -0.114 |
vows | -0.113 |
blush | -0.106 |
Token | boo |
Token ID | 22513 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ves | +0.133 |
Her | +0.132 |
vows | +0.132 |
brist | +0.129 |
blonde | +0.118 |
Neg logit contributions | |
o | -0.119 |
alone | -0.110 |
forth | -0.099 |
tank | -0.098 |
afloat | -0.096 |
Token | - |
Token ID | 12 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
o | +0.411 |
alone | +0.378 |
tank | +0.364 |
afloat | +0.352 |
forth | +0.352 |
Neg logit contributions | |
ves | -0.331 |
Her | -0.330 |
brist | -0.329 |
vows | -0.312 |
ork | -0.282 |
Token | bo |
Token ID | 2127 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
o | +0.023 |
alone | +0.021 |
forth | +0.017 |
tank | +0.017 |
afloat | +0.016 |
Neg logit contributions | |
ves | -0.061 |
Her | -0.061 |
vows | -0.060 |
brist | -0.060 |
growth | -0.056 |
Token | o |
Token ID | 78 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
alone | +0.046 |
o | +0.039 |
forth | +0.035 |
afloat | +0.011 |
tank | +0.004 |
Neg logit contributions | |
ves | -1.254 |
Her | -1.237 |
vows | -1.211 |
brist | -1.201 |
ork | -1.167 |
Token | on |
Token ID | 319 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
o | +1.001 |
alone | +0.926 |
forth | +0.864 |
tank | +0.855 |
afloat | +0.847 |
Neg logit contributions | |
ves | -1.108 |
Her | -1.090 |
vows | -1.083 |
brist | -1.070 |
ork | -0.966 |
Token | her |
Token ID | 607 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
o | +0.307 |
alone | +0.296 |
forth | +0.264 |
tank | +0.263 |
my | +0.257 |
Neg logit contributions | |
ves | -0.294 |
vows | -0.291 |
Her | -0.285 |
brist | -0.280 |
blonde | -0.256 |
Token | knee |
Token ID | 10329 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
ves | +0.426 |
vows | +0.422 |
Her | +0.421 |
brist | +0.412 |
growth | +0.378 |
Neg logit contributions | |
o | -0.380 |
alone | -0.357 |
forth | -0.321 |
tank | -0.318 |
afloat | -0.309 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
o | +0.150 |
alone | +0.142 |
forth | +0.126 |
my | +0.123 |
tank | +0.123 |
Neg logit contributions | |
vows | -0.174 |
ves | -0.172 |
Her | -0.170 |
brist | -0.168 |
growth | -0.158 |
Token | Her |
Token ID | 2332 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
o | +0.058 |
alone | +0.055 |
tank | +0.049 |
forth | +0.049 |
my | +0.048 |
Neg logit contributions | |
ves | -0.046 |
vows | -0.045 |
Her | -0.044 |
brist | -0.044 |
growth | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
o | +0.280 |
alone | +0.273 |
my | +0.237 |
tank | +0.234 |
wreck | +0.229 |
Neg logit contributions | |
ves | -0.310 |
vows | -0.303 |
Her | -0.303 |
brist | -0.292 |
growth | -0.277 |
Token | big |
Token ID | 1263 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
ves | +0.110 |
Her | +0.109 |
vows | +0.109 |
brist | +0.107 |
growth | +0.098 |
Neg logit contributions | |
o | -0.108 |
alone | -0.101 |
forth | -0.092 |
tank | -0.091 |
afloat | -0.089 |
Token | boo |
Token ID | 22513 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
o | +0.089 |
alone | +0.079 |
forth | +0.072 |
afloat | +0.071 |
| | +0.070 |
Neg logit contributions | |
vows | -0.090 |
brist | -0.090 |
ves | -0.089 |
Her | -0.088 |
blonde | -0.082 |
Token | - |
Token ID | 12 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
o | +0.416 |
alone | +0.387 |
forth | +0.361 |
tank | +0.359 |
afloat | +0.355 |
Neg logit contributions | |
ves | -0.337 |
Her | -0.333 |
brist | -0.331 |
vows | -0.326 |
blonde | -0.286 |
Token | bo |
Token ID | 2127 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
o | +0.032 |
alone | +0.029 |
forth | +0.026 |
tank | +0.025 |
afloat | +0.024 |
Neg logit contributions | |
ves | -0.057 |
Her | -0.057 |
vows | -0.056 |
brist | -0.056 |
growth | -0.052 |
Token | o |
Token ID | 78 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
o | +0.153 |
alone | +0.135 |
forth | +0.115 |
afloat | +0.095 |
tank | +0.084 |
Neg logit contributions | |
ves | -1.147 |
Her | -1.132 |
vows | -1.120 |
brist | -1.106 |
blonde | -1.056 |
Token | on |
Token ID | 319 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
o | +1.046 |
alone | +0.963 |
forth | +0.896 |
tank | +0.875 |
afloat | +0.871 |
Neg logit contributions | |
ves | -1.075 |
Her | -1.059 |
vows | -1.056 |
brist | -1.040 |
blonde | -0.944 |
Token | his |
Token ID | 465 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
o | +0.164 |
alone | +0.149 |
tank | +0.120 |
forth | +0.117 |
my | +0.110 |
Neg logit contributions | |
ves | -0.456 |
vows | -0.455 |
Her | -0.449 |
brist | -0.444 |
blonde | -0.418 |
Token | knee |
Token ID | 10329 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
o | +0.583 |
alone | +0.549 |
forth | +0.495 |
tank | +0.492 |
afloat | +0.476 |
Neg logit contributions | |
ves | -0.627 |
vows | -0.622 |
Her | -0.620 |
brist | -0.608 |
blonde | -0.555 |
Token | . |
Token ID | 13 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
o | +0.153 |
alone | +0.144 |
forth | +0.125 |
my | +0.124 |
tank | +0.124 |
Neg logit contributions | |
vows | -0.184 |
ves | -0.182 |
Her | -0.181 |
brist | -0.179 |
growth | -0.169 |
Token | He |
Token ID | 679 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
o | +0.041 |
forth | +0.040 |
alone | +0.040 |
afloat | +0.038 |
wreck | +0.034 |
Neg logit contributions | |
Her | -0.060 |
Her | -0.058 |
brist | -0.056 |
blonde | -0.055 |
ves | -0.053 |
Token | sky |
Token ID | 6766 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
o | +0.348 |
alone | +0.314 |
forth | +0.298 |
afloat | +0.291 |
tank | +0.290 |
Neg logit contributions | |
brist | -0.213 |
vows | -0.213 |
Her | -0.211 |
ves | -0.210 |
growth | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
vows | +0.161 |
ves | +0.160 |
Her | +0.160 |
brist | +0.157 |
growth | +0.146 |
Neg logit contributions | |
o | -0.133 |
alone | -0.127 |
forth | -0.110 |
tank | -0.109 |
my | -0.108 |
Token | The |
Token ID | 383 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
o | +0.061 |
alone | +0.057 |
forth | +0.052 |
tank | +0.051 |
afloat | +0.050 |
Neg logit contributions | |
ves | -0.061 |
Her | -0.061 |
vows | -0.061 |
brist | -0.060 |
blonde | -0.055 |
Token | dove |
Token ID | 38862 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
o | +0.106 |
alone | +0.099 |
forth | +0.091 |
tank | +0.090 |
afloat | +0.088 |
Neg logit contributions | |
ves | -0.100 |
Her | -0.099 |
vows | -0.099 |
brist | -0.097 |
blonde | -0.088 |
Token | co |
Token ID | 763 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
Her | +0.144 |
vows | +0.143 |
ves | +0.143 |
brist | +0.142 |
growth | +0.131 |
Neg logit contributions | |
o | -0.134 |
alone | -0.128 |
forth | -0.114 |
tank | -0.111 |
my | -0.110 |
Token | o |
Token ID | 78 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
o | +0.112 |
alone | +0.099 |
forth | +0.088 |
tank | +0.086 |
my | +0.085 |
Neg logit contributions | |
vows | -0.158 |
ves | -0.158 |
Her | -0.156 |
brist | -0.155 |
growth | -0.144 |
Token | ed |
Token ID | 276 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
o | +1.056 |
alone | +0.962 |
forth | +0.841 |
tank | +0.834 |
my | +0.834 |
Neg logit contributions | |
Her | -1.134 |
vows | -1.102 |
ves | -1.101 |
brist | -1.093 |
blonde | -1.009 |
Token | softly |
Token ID | 26625 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
ves | +0.266 |
Her | +0.264 |
vows | +0.264 |
brist | +0.259 |
growth | +0.239 |
Neg logit contributions | |
o | -0.194 |
alone | -0.178 |
forth | -0.159 |
tank | -0.156 |
afloat | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ves | +0.177 |
Her | +0.170 |
vows | +0.170 |
brist | +0.165 |
growth | +0.157 |
Neg logit contributions | |
o | -0.123 |
alone | -0.116 |
forth | -0.102 |
tank | -0.099 |
afloat | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
o | +0.036 |
alone | +0.032 |
tank | +0.030 |
forth | +0.029 |
afloat | +0.029 |
Neg logit contributions | |
Her | -0.041 |
brist | -0.040 |
ves | -0.040 |
vows | -0.040 |
blonde | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
o | +0.080 |
alone | +0.073 |
tank | +0.068 |
afloat | +0.066 |
wreck | +0.066 |
Neg logit contributions | |
ves | -0.085 |
Her | -0.085 |
vows | -0.085 |
brist | -0.083 |
blonde | -0.076 |
Token | ." |
Token ID | 526 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
vows | +0.029 |
ves | +0.028 |
Her | +0.028 |
brist | +0.027 |
blonde | +0.025 |
Neg logit contributions | |
o | -0.024 |
| | -0.020 |
forth | -0.020 |
alone | -0.019 |
afloat | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
o | +0.351 |
alone | +0.327 |
forth | +0.305 |
afloat | +0.298 |
tank | +0.294 |
Neg logit contributions | |
Her | -0.437 |
ves | -0.423 |
vows | -0.418 |
brist | -0.411 |
blonde | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
forth | +0.274 |
o | +0.264 |
alone | +0.264 |
afloat | +0.258 |
tank | +0.249 |
Neg logit contributions | |
Her | -0.306 |
ves | -0.281 |
Her | -0.247 |
brist | -0.246 |
ork | -0.238 |
Token | The |
Token ID | 464 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
o | +0.318 |
alone | +0.304 |
forth | +0.284 |
tank | +0.281 |
afloat | +0.277 |
Neg logit contributions | |
Her | -0.248 |
ves | -0.239 |
vows | -0.226 |
brist | -0.225 |
blonde | -0.202 |
Token | hipp |
Token ID | 18568 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
vows | +0.126 |
ves | +0.126 |
Her | +0.125 |
brist | +0.124 |
blonde | +0.113 |
Neg logit contributions | |
o | -0.110 |
alone | -0.100 |
forth | -0.091 |
afloat | -0.089 |
tank | -0.088 |
Token | o |
Token ID | 78 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
alone | +0.110 |
afloat | +0.094 |
forth | +0.083 |
o | +0.043 |
polar | +0.040 |
Neg logit contributions | |
ves | -0.965 |
vows | -0.955 |
Her | -0.938 |
brist | -0.901 |
owers | -0.880 |
Token | was |
Token ID | 373 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
o | +1.006 |
alone | +0.936 |
forth | +0.848 |
tank | +0.833 |
afloat | +0.818 |
Neg logit contributions | |
ves | -1.120 |
vows | -1.113 |
Her | -1.109 |
brist | -1.090 |
growth | -0.995 |
Token | confused |
Token ID | 10416 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
o | +0.042 |
forth | +0.038 |
| | +0.036 |
alone | +0.035 |
afloat | +0.035 |
Neg logit contributions | |
Her | -0.056 |
ves | -0.056 |
brist | -0.054 |
vows | -0.054 |
blonde | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
o | +0.370 |
alone | +0.344 |
forth | +0.314 |
tank | +0.310 |
afloat | +0.304 |
Neg logit contributions | |
ves | -0.369 |
Her | -0.368 |
vows | -0.365 |
brist | -0.360 |
blonde | -0.327 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
o | +0.081 |
afloat | +0.068 |
| | +0.067 |
alone | +0.067 |
my | +0.066 |
Neg logit contributions | |
Her | -0.096 |
vows | -0.095 |
ves | -0.095 |
brist | -0.091 |
blonde | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
o | +0.207 |
alone | +0.190 |
tank | +0.165 |
my | +0.163 |
forth | +0.162 |
Neg logit contributions | |
vows | -0.271 |
ves | -0.271 |
brist | -0.270 |
Her | -0.268 |
growth | -0.250 |
Token | minutes |
Token ID | 2431 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
Her | +0.241 |
vows | +0.232 |
brist | +0.222 |
ves | +0.221 |
growth | +0.204 |
Neg logit contributions | |
alone | -0.243 |
o | -0.224 |
tank | -0.208 |
forth | -0.206 |
wreck | -0.199 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
vows | +0.116 |
Her | +0.114 |
ves | +0.113 |
brist | +0.112 |
blonde | +0.102 |
Neg logit contributions | |
o | -0.089 |
alone | -0.082 |
forth | -0.073 |
my | -0.072 |
tank | -0.069 |
Token | then |
Token ID | 788 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
o | +0.046 |
alone | +0.043 |
forth | +0.039 |
tank | +0.038 |
my | +0.037 |
Neg logit contributions | |
ves | -0.054 |
vows | -0.054 |
Her | -0.053 |
brist | -0.052 |
growth | -0.048 |
Token | t |
Token ID | 256 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
o | +0.044 |
alone | +0.041 |
forth | +0.037 |
tank | +0.035 |
my | +0.035 |
Neg logit contributions | |
ves | -0.057 |
vows | -0.057 |
Her | -0.057 |
brist | -0.056 |
growth | -0.054 |
Token | ipt |
Token ID | 10257 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
o | +0.050 |
alone | +0.041 |
my | +0.039 |
forth | +0.038 |
polar | +0.036 |
Neg logit contributions | |
ves | -0.064 |
vows | -0.064 |
brist | -0.062 |
Her | -0.060 |
blonde | -0.058 |
Token | o |
Token ID | 78 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
alone | +0.126 |
tank | +0.122 |
o | +0.121 |
afloat | +0.118 |
forth | +0.114 |
Neg logit contributions | |
Her | -0.220 |
ves | -0.206 |
vows | -0.202 |
brist | -0.200 |
Her | -0.188 |
Token | ed |
Token ID | 276 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
o | +1.269 |
alone | +1.173 |
forth | +1.070 |
tank | +1.056 |
my | +1.054 |
Neg logit contributions | |
Her | -0.890 |
ves | -0.883 |
vows | -0.877 |
brist | -0.873 |
growth | -0.787 |
Token | back |
Token ID | 736 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ves | +0.308 |
Her | +0.304 |
vows | +0.303 |
brist | +0.298 |
growth | +0.277 |
Neg logit contributions | |
o | -0.174 |
alone | -0.161 |
forth | -0.138 |
tank | -0.136 |
my | -0.131 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
o | +0.388 |
alone | +0.357 |
forth | +0.314 |
tank | +0.307 |
my | +0.298 |
Neg logit contributions | |
ves | -0.585 |
vows | -0.580 |
Her | -0.579 |
brist | -0.569 |
growth | -0.528 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Her | +0.032 |
vows | +0.032 |
ves | +0.032 |
brist | +0.032 |
growth | +0.029 |
Neg logit contributions | |
o | -0.022 |
alone | -0.020 |
forth | -0.018 |
tank | -0.018 |
afloat | -0.017 |
Token | table |
Token ID | 3084 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
o | +0.258 |
alone | +0.245 |
tank | +0.224 |
forth | +0.223 |
polar | +0.216 |
Neg logit contributions | |
ves | -0.242 |
Her | -0.239 |
vows | -0.235 |
brist | -0.231 |
growth | -0.209 |
Token | So |
Token ID | 1406 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ves | +0.554 |
vows | +0.550 |
Her | +0.549 |
brist | +0.540 |
growth | +0.496 |
Neg logit contributions | |
o | -0.472 |
alone | -0.436 |
forth | -0.395 |
tank | -0.388 |
my | -0.378 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ves | +0.047 |
vows | +0.047 |
Her | +0.047 |
brist | +0.046 |
growth | +0.042 |
Neg logit contributions | |
o | -0.049 |
alone | -0.046 |
forth | -0.042 |
tank | -0.041 |
my | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
o | +0.039 |
alone | +0.036 |
forth | +0.033 |
tank | +0.032 |
afloat | +0.032 |
Neg logit contributions | |
ves | -0.043 |
Her | -0.043 |
vows | -0.042 |
brist | -0.041 |
blonde | -0.038 |
Token | little |
Token ID | 1310 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
o | +0.238 |
alone | +0.220 |
forth | +0.199 |
tank | +0.196 |
afloat | +0.192 |
Neg logit contributions | |
ves | -0.271 |
Her | -0.270 |
vows | -0.269 |
brist | -0.265 |
blonde | -0.242 |
Token | hipp |
Token ID | 18568 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
brist | +0.013 |
vows | +0.013 |
ves | +0.013 |
Her | +0.013 |
ribbon | +0.012 |
Neg logit contributions | |
o | -0.009 |
alone | -0.008 |
afloat | -0.007 |
| | -0.007 |
forth | -0.007 |
Token | o |
Token ID | 78 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
alone | +0.084 |
forth | +0.061 |
afloat | +0.045 |
o | +0.024 |
polar | -0.004 |
Neg logit contributions | |
ves | -1.000 |
vows | -0.992 |
Her | -0.982 |
brist | -0.938 |
owers | -0.928 |
Token | went |
Token ID | 1816 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
o | +0.995 |
alone | +0.902 |
tank | +0.814 |
forth | +0.804 |
my | +0.786 |
Neg logit contributions | |
Her | -1.156 |
ves | -1.144 |
vows | -1.132 |
brist | -1.128 |
blonde | -1.038 |
Token | to |
Token ID | 284 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
o | +0.082 |
alone | +0.072 |
forth | +0.072 |
afloat | +0.067 |
| | +0.066 |
Neg logit contributions | |
Her | -0.094 |
ves | -0.093 |
vows | -0.090 |
brist | -0.086 |
ribbon | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
vows | +0.011 |
Her | +0.011 |
ves | +0.011 |
brist | +0.010 |
growth | +0.010 |
Neg logit contributions | |
o | -0.010 |
alone | -0.008 |
forth | -0.008 |
my | -0.008 |
afloat | -0.007 |
Token | river |
Token ID | 7850 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
o | +0.252 |
alone | +0.229 |
forth | +0.214 |
afloat | +0.206 |
my | +0.200 |
Neg logit contributions | |
vows | -0.275 |
ves | -0.262 |
Her | -0.260 |
brist | -0.258 |
growth | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
o | +0.351 |
alone | +0.322 |
forth | +0.307 |
polar | +0.292 |
afloat | +0.289 |
Neg logit contributions | |
ves | -0.341 |
Her | -0.333 |
vows | -0.331 |
brist | -0.324 |
growth | -0.296 |
Token | Ch |
Token ID | 609 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
o | +0.228 |
alone | +0.210 |
forth | +0.187 |
tank | +0.184 |
afloat | +0.179 |
Neg logit contributions | |
ves | -0.325 |
Her | -0.323 |
vows | -0.322 |
brist | -0.317 |
blonde | -0.293 |
Token | ir |
Token ID | 343 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
o | +0.366 |
alone | +0.355 |
forth | +0.344 |
afloat | +0.323 |
tank | +0.321 |
Neg logit contributions | |
Her | -0.240 |
ves | -0.240 |
vows | -0.233 |
brist | -0.228 |
growth | -0.208 |
Token | py |
Token ID | 9078 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ves | +0.185 |
Her | +0.184 |
vows | +0.184 |
brist | +0.181 |
blonde | +0.167 |
Neg logit contributions | |
o | -0.125 |
alone | -0.115 |
forth | -0.102 |
tank | -0.101 |
afloat | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
o | +0.301 |
alone | +0.275 |
my | +0.244 |
tank | +0.241 |
forth | +0.240 |
Neg logit contributions | |
ves | -0.334 |
vows | -0.334 |
brist | -0.325 |
Her | -0.325 |
growth | -0.300 |
Token | Bob |
Token ID | 5811 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
o | +0.062 |
alone | +0.057 |
forth | +0.051 |
tank | +0.050 |
afloat | +0.049 |
Neg logit contributions | |
ves | -0.082 |
vows | -0.081 |
Her | -0.081 |
brist | -0.080 |
blonde | -0.073 |
Token | o |
Token ID | 78 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
o | +0.023 |
alone | +0.023 |
forth | -0.011 |
afloat | -0.019 |
tank | -0.023 |
Neg logit contributions | |
Her | -0.798 |
ves | -0.797 |
vows | -0.791 |
brist | -0.788 |
blonde | -0.752 |
Token | said |
Token ID | 531 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
o | +0.975 |
alone | +0.858 |
tank | +0.780 |
my | +0.770 |
forth | +0.760 |
Neg logit contributions | |
Her | -1.181 |
ves | -1.175 |
vows | -1.173 |
brist | -1.158 |
growth | -1.093 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
o | +0.191 |
alone | +0.179 |
tank | +0.146 |
my | +0.141 |
forth | +0.136 |
Neg logit contributions | |
growth | -0.273 |
vows | -0.273 |
brist | -0.272 |
Her | -0.264 |
ves | -0.262 |
Token | " |
Token ID | 366 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
o | +0.051 |
alone | +0.047 |
tank | +0.043 |
forth | +0.042 |
my | +0.042 |
Neg logit contributions | |
vows | -0.043 |
ves | -0.043 |
Her | -0.042 |
brist | -0.042 |
growth | -0.039 |
Token | I |
Token ID | 40 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
Her | +0.089 |
ves | +0.087 |
vows | +0.085 |
brist | +0.085 |
blonde | +0.076 |
Neg logit contributions | |
o | -0.098 |
alone | -0.095 |
tank | -0.087 |
forth | -0.087 |
afloat | -0.086 |
Token | found |
Token ID | 1043 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
o | +0.046 |
alone | +0.043 |
forth | +0.042 |
afloat | +0.039 |
tank | +0.038 |
Neg logit contributions | |
ves | -0.057 |
vows | -0.057 |
Her | -0.056 |
brist | -0.055 |
blonde | -0.051 |
Token | put |
Token ID | 1234 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
o | +0.459 |
alone | +0.420 |
forth | +0.377 |
tank | +0.377 |
my | +0.372 |
Neg logit contributions | |
Her | -0.491 |
ves | -0.481 |
vows | -0.481 |
brist | -0.478 |
blonde | -0.443 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
o | +0.111 |
alone | +0.102 |
forth | +0.090 |
tank | +0.089 |
my | +0.086 |
Neg logit contributions | |
ves | -0.170 |
Her | -0.169 |
vows | -0.169 |
brist | -0.165 |
growth | -0.154 |
Token | leaves |
Token ID | 5667 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
o | +0.304 |
alone | +0.291 |
tank | +0.268 |
forth | +0.265 |
polar | +0.257 |
Neg logit contributions | |
Her | -0.274 |
ves | -0.271 |
vows | -0.265 |
brist | -0.258 |
growth | -0.239 |
Token | on |
Token ID | 319 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
vows | +0.143 |
ves | +0.141 |
Her | +0.139 |
brist | +0.138 |
growth | +0.131 |
Neg logit contributions | |
o | -0.072 |
alone | -0.068 |
forth | -0.057 |
tank | -0.055 |
afloat | -0.055 |
Token | Bob |
Token ID | 5811 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
o | +0.209 |
alone | +0.192 |
tank | +0.176 |
polar | +0.163 |
my | +0.159 |
Neg logit contributions | |
vows | -0.421 |
ves | -0.419 |
Her | -0.402 |
brist | -0.397 |
blush | -0.381 |
Token | o |
Token ID | 78 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
o | +0.365 |
alone | +0.323 |
forth | +0.290 |
my | +0.287 |
tank | +0.285 |
Neg logit contributions | |
ves | -0.508 |
vows | -0.506 |
Her | -0.499 |
brist | -0.492 |
growth | -0.457 |
Token | 's |
Token ID | 338 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
o | +0.916 |
alone | +0.827 |
tank | +0.721 |
my | +0.715 |
forth | +0.711 |
Neg logit contributions | |
Her | -1.255 |
vows | -1.239 |
ves | -1.226 |
brist | -1.206 |
growth | -1.148 |
Token | head |
Token ID | 1182 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
o | +0.210 |
alone | +0.209 |
tank | +0.190 |
forth | +0.185 |
polar | +0.180 |
Neg logit contributions | |
ves | -0.204 |
Her | -0.198 |
vows | -0.195 |
brist | -0.185 |
growth | -0.175 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
o | +0.230 |
alone | +0.212 |
my | +0.185 |
tank | +0.179 |
forth | +0.171 |
Neg logit contributions | |
ves | -0.353 |
vows | -0.348 |
Her | -0.346 |
growth | -0.339 |
brist | -0.336 |
Token | Now |
Token ID | 2735 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
o | +0.044 |
alone | +0.043 |
forth | +0.040 |
afloat | +0.037 |
tank | +0.037 |
Neg logit contributions | |
Her | -0.060 |
ves | -0.059 |
vows | -0.059 |
brist | -0.058 |
blonde | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
o | +0.046 |
alone | +0.042 |
forth | +0.038 |
tank | +0.038 |
afloat | +0.037 |
Neg logit contributions | |
ves | -0.057 |
vows | -0.057 |
Her | -0.057 |
brist | -0.055 |
blonde | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
o | +0.053 |
alone | +0.052 |
tank | +0.045 |
my | +0.045 |
polar | +0.043 |
Neg logit contributions | |
ves | -0.051 |
vows | -0.050 |
Her | -0.048 |
brist | -0.048 |
growth | -0.044 |
Token | purple |
Token ID | 14032 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
vows | +0.127 |
brist | +0.125 |
ves | +0.124 |
Her | +0.124 |
ribbon | +0.116 |
Neg logit contributions | |
o | -0.146 |
alone | -0.131 |
forth | -0.121 |
afloat | -0.120 |
| | -0.120 |
Token | bird |
Token ID | 6512 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
ves | +0.086 |
Her | +0.085 |
vows | +0.083 |
brist | +0.081 |
growth | +0.077 |
Neg logit contributions | |
o | -0.073 |
alone | -0.069 |
tank | -0.065 |
forth | -0.062 |
polar | -0.061 |
Token | named |
Token ID | 3706 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
o | +0.078 |
alone | +0.072 |
forth | +0.069 |
afloat | +0.069 |
tank | +0.067 |
Neg logit contributions | |
ves | -0.086 |
Her | -0.085 |
vows | -0.081 |
brist | -0.081 |
blonde | -0.074 |
Token | Bob |
Token ID | 5811 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
o | +0.214 |
alone | +0.195 |
forth | +0.174 |
tank | +0.169 |
afloat | +0.165 |
Neg logit contributions | |
ves | -0.345 |
Her | -0.344 |
vows | -0.342 |
brist | -0.338 |
blonde | -0.314 |
Token | o |
Token ID | 78 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
forth | +0.431 |
alone | +0.423 |
afloat | +0.408 |
o | +0.404 |
wreck | +0.401 |
Neg logit contributions | |
Her | -0.378 |
ves | -0.374 |
vows | -0.357 |
brist | -0.334 |
Her | -0.328 |
Token | . |
Token ID | 13 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
o | +1.061 |
alone | +1.000 |
forth | +0.930 |
tank | +0.900 |
afloat | +0.897 |
Neg logit contributions | |
ves | -1.038 |
Her | -1.033 |
vows | -1.024 |
brist | -0.997 |
blonde | -0.907 |
Token | Bob |
Token ID | 5811 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
alone | +0.050 |
o | +0.049 |
forth | +0.049 |
afloat | +0.045 |
wreck | +0.043 |
Neg logit contributions | |
Her | -0.065 |
vows | -0.063 |
ves | -0.062 |
Her | -0.062 |
blonde | -0.061 |
Token | o |
Token ID | 78 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
forth | +0.083 |
afloat | +0.081 |
alone | +0.080 |
wreck | +0.052 |
tank | +0.035 |
Neg logit contributions | |
Her | -0.680 |
ves | -0.667 |
brist | -0.661 |
vows | -0.657 |
Her | -0.646 |
Token | loved |
Token ID | 6151 |
Feature activation | +7.32e-03 |
Pos logit contributions | |
o | +1.050 |
alone | +0.986 |
forth | +0.908 |
afloat | +0.889 |
tank | +0.888 |
Neg logit contributions | |
ves | -1.018 |
Her | -1.010 |
vows | -1.009 |
brist | -0.985 |
blonde | -0.894 |
Token | to |
Token ID | 284 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
o | +0.015 |
alone | +0.014 |
forth | +0.013 |
tank | +0.012 |
afloat | +0.012 |
Neg logit contributions | |
ves | -0.013 |
vows | -0.013 |
Her | -0.013 |
brist | -0.012 |
blonde | -0.011 |
Token | ever |
Token ID | 1683 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
o | +0.027 |
alone | +0.027 |
forth | +0.024 |
my | +0.023 |
tank | +0.023 |
Neg logit contributions | |
ves | -0.028 |
vows | -0.028 |
Her | -0.028 |
brist | -0.027 |
growth | -0.025 |
Token | before |
Token ID | 878 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
ves | +0.040 |
brist | +0.040 |
Her | +0.040 |
vows | +0.039 |
blonde | +0.037 |
Neg logit contributions | |
o | -0.047 |
tank | -0.042 |
alone | -0.042 |
polar | -0.041 |
afloat | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
vows | +0.050 |
ves | +0.047 |
brist | +0.046 |
Her | +0.045 |
blush | +0.043 |
Neg logit contributions | |
alone | -0.028 |
o | -0.025 |
forth | -0.021 |
my | -0.020 |
afloat | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
ves | +0.131 |
vows | +0.127 |
brist | +0.121 |
Her | +0.118 |
ribbon | +0.114 |
Neg logit contributions | |
o | -0.105 |
alone | -0.094 |
my | -0.085 |
tank | -0.081 |
| | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
o | +0.068 |
alone | +0.061 |
tank | +0.053 |
my | +0.052 |
forth | +0.052 |
Neg logit contributions | |
vows | -0.101 |
brist | -0.099 |
ves | -0.099 |
Her | -0.098 |
blonde | -0.093 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
o | +0.081 |
alone | +0.072 |
my | +0.068 |
| | +0.067 |
forth | +0.064 |
Neg logit contributions | |
vows | -0.086 |
brist | -0.082 |
blonde | -0.081 |
rings | -0.076 |
blush | -0.075 |
Token | mum |
Token ID | 25682 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ves | +0.851 |
Her | +0.821 |
vows | +0.792 |
brist | +0.782 |
growth | +0.719 |
Neg logit contributions | |
o | -1.313 |
alone | -1.267 |
forth | -1.193 |
tank | -1.174 |
afloat | -1.143 |
Token | was |
Token ID | 373 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
ves | +0.455 |
vows | +0.451 |
Her | +0.450 |
brist | +0.442 |
blonde | +0.401 |
Neg logit contributions | |
o | -0.433 |
alone | -0.409 |
forth | -0.369 |
afloat | -0.367 |
tank | -0.366 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Her | +0.162 |
ves | +0.157 |
vows | +0.157 |
brist | +0.155 |
blonde | +0.145 |
Neg logit contributions | |
o | -0.107 |
alone | -0.093 |
forth | -0.087 |
tank | -0.086 |
afloat | -0.083 |
Token | that |
Token ID | 326 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
o | +0.277 |
alone | +0.263 |
forth | +0.229 |
my | +0.225 |
tank | +0.218 |
Neg logit contributions | |
ves | -0.329 |
vows | -0.320 |
Her | -0.306 |
brist | -0.305 |
growth | -0.298 |
Token | Daisy |
Token ID | 40355 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
vows | +0.343 |
ves | +0.342 |
brist | +0.331 |
Her | +0.331 |
growth | +0.301 |
Neg logit contributions | |
o | -0.374 |
alone | -0.364 |
forth | -0.330 |
my | -0.322 |
tank | -0.313 |
Token | it |
Token ID | 340 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
vows | +0.054 |
ves | +0.053 |
Her | +0.053 |
brist | +0.052 |
growth | +0.049 |
Neg logit contributions | |
o | -0.039 |
alone | -0.039 |
tank | -0.034 |
forth | -0.034 |
my | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
vows | +0.197 |
ves | +0.192 |
brist | +0.190 |
Her | +0.187 |
growth | +0.183 |
Neg logit contributions | |
alone | -0.118 |
o | -0.118 |
my | -0.097 |
tank | -0.095 |
forth | -0.093 |
Token | |
Token ID | 220 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
ves | +0.141 |
brist | +0.139 |
vows | +0.137 |
blonde | +0.130 |
growth | +0.127 |
Neg logit contributions | |
o | -0.104 |
my | -0.079 |
alone | -0.079 |
tank | -0.073 |
forth | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
o | +0.067 |
alone | +0.059 |
my | +0.050 |
tank | +0.050 |
forth | +0.050 |
Neg logit contributions | |
vows | -0.111 |
ves | -0.109 |
brist | -0.108 |
Her | -0.108 |
growth | -0.101 |
Token |
|
Token ID | 198 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
o | +0.056 |
alone | +0.047 |
my | +0.040 |
tank | +0.038 |
| | +0.037 |
Neg logit contributions | |
vows | -0.107 |
brist | -0.107 |
ves | -0.104 |
Her | -0.101 |
blonde | -0.099 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
o | +0.081 |
my | +0.068 |
forth | +0.068 |
alone | +0.066 |
ny | +0.066 |
Neg logit contributions | |
brist | -0.068 |
vows | -0.067 |
icing | -0.066 |
der | -0.065 |
blonde | -0.064 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ves | +1.189 |
Her | +1.130 |
vows | +1.119 |
growth | +1.112 |
brist | +1.097 |
Neg logit contributions | |
o | -1.020 |
alone | -0.936 |
my | -0.882 |
forth | -0.855 |
tank | -0.851 |
Token | showed |
Token ID | 3751 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
ves | +0.276 |
Her | +0.272 |
vows | +0.272 |
brist | +0.266 |
growth | +0.258 |
Neg logit contributions | |
o | -0.205 |
alone | -0.170 |
my | -0.168 |
forth | -0.160 |
tank | -0.156 |
Token | her |
Token ID | 607 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
vows | +0.128 |
ves | +0.127 |
brist | +0.121 |
blonde | +0.118 |
Her | +0.117 |
Neg logit contributions | |
o | -0.152 |
alone | -0.136 |
my | -0.133 |
forth | -0.121 |
ny | -0.121 |
Token | how |
Token ID | 703 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ves | +0.761 |
vows | +0.746 |
brist | +0.708 |
owers | +0.701 |
Her | +0.694 |
Neg logit contributions | |
alone | -0.439 |
o | -0.418 |
my | -0.372 |
tank | -0.359 |
down | -0.317 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ves | +0.326 |
vows | +0.325 |
brist | +0.317 |
growth | +0.302 |
Her | +0.301 |
Neg logit contributions | |
o | -0.244 |
alone | -0.234 |
tank | -0.187 |
my | -0.185 |
forth | -0.179 |
Token | her |
Token ID | 607 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ves | +0.189 |
vows | +0.179 |
brist | +0.178 |
Her | +0.171 |
blonde | +0.159 |
Neg logit contributions | |
alone | -0.204 |
o | -0.200 |
tank | -0.177 |
forth | -0.176 |
my | -0.175 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ves | +0.620 |
Her | +0.616 |
vows | +0.616 |
brist | +0.604 |
blonde | +0.553 |
Neg logit contributions | |
o | -0.552 |
alone | -0.511 |
forth | -0.462 |
tank | -0.456 |
afloat | -0.445 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
Her | +0.214 |
brist | +0.197 |
vows | +0.196 |
ves | +0.194 |
Her | +0.186 |
Neg logit contributions | |
o | -0.232 |
alone | -0.218 |
afloat | -0.210 |
wreck | -0.208 |
polar | -0.206 |
Token |
|
Token ID | 198 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
ves | +0.167 |
vows | +0.161 |
brist | +0.159 |
growth | +0.154 |
comb | +0.150 |
Neg logit contributions | |
o | -0.073 |
my | -0.053 |
alone | -0.053 |
Tim | -0.046 |
tank | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
o | +0.059 |
alone | +0.051 |
tank | +0.043 |
my | +0.043 |
forth | +0.041 |
Neg logit contributions | |
vows | -0.102 |
brist | -0.101 |
ves | -0.100 |
Her | -0.098 |
blonde | -0.095 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
o | +0.061 |
alone | +0.055 |
my | +0.051 |
forth | +0.047 |
| | +0.045 |
Neg logit contributions | |
vows | -0.097 |
brist | -0.094 |
blonde | -0.091 |
growth | -0.090 |
der | -0.089 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ves | +1.120 |
Her | +1.087 |
vows | +1.067 |
brist | +1.042 |
growth | +1.020 |
Neg logit contributions | |
o | -1.058 |
alone | -1.011 |
tank | -0.921 |
forth | -0.917 |
my | -0.901 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
ves | +0.274 |
vows | +0.272 |
Her | +0.270 |
brist | +0.266 |
growth | +0.256 |
Neg logit contributions | |
o | -0.211 |
alone | -0.176 |
my | -0.174 |
forth | -0.164 |
tank | -0.160 |
Token | when |
Token ID | 618 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
ves | +0.074 |
vows | +0.071 |
Her | +0.070 |
brist | +0.070 |
growth | +0.065 |
Neg logit contributions | |
o | -0.055 |
alone | -0.052 |
forth | -0.046 |
tank | -0.045 |
my | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
vows | +0.109 |
brist | +0.108 |
growth | +0.107 |
ves | +0.107 |
Her | +0.094 |
Neg logit contributions | |
alone | -0.123 |
o | -0.115 |
my | -0.110 |
forth | -0.110 |
Tim | -0.106 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
vows | +0.829 |
ves | +0.819 |
brist | +0.817 |
Her | +0.815 |
blonde | +0.754 |
Neg logit contributions | |
o | -0.514 |
alone | -0.444 |
my | -0.399 |
forth | -0.396 |
tank | -0.386 |
Token | it |
Token ID | 340 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
o | +0.145 |
alone | +0.144 |
forth | +0.123 |
my | +0.121 |
tank | +0.119 |
Neg logit contributions | |
ves | -0.198 |
vows | -0.197 |
brist | -0.196 |
Her | -0.195 |
blonde | -0.182 |
Token | back |
Token ID | 736 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ves | +0.179 |
Her | +0.179 |
vows | +0.178 |
brist | +0.174 |
blonde | +0.160 |
Neg logit contributions | |
o | -0.131 |
alone | -0.120 |
forth | -0.108 |
tank | -0.106 |
afloat | -0.104 |
Token | ." |
Token ID | 526 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
o | +0.266 |
alone | +0.242 |
forth | +0.228 |
tank | +0.224 |
afloat | +0.224 |
Neg logit contributions | |
ves | -0.339 |
Her | -0.338 |
vows | -0.335 |
brist | -0.325 |
ork | -0.298 |
Token |
|
Token ID | 198 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
o | +0.150 |
alone | +0.139 |
my | +0.117 |
tank | +0.106 |
forth | +0.102 |
Neg logit contributions | |
vows | -0.274 |
ves | -0.271 |
brist | -0.253 |
growth | -0.244 |
blonde | -0.239 |
Token |
|
Token ID | 198 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
o | +0.072 |
alone | +0.066 |
forth | +0.062 |
tank | +0.060 |
afloat | +0.059 |
Neg logit contributions | |
Her | -0.096 |
ves | -0.093 |
brist | -0.090 |
vows | -0.089 |
growth | -0.082 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
o | +0.133 |
alone | +0.130 |
my | +0.121 |
forth | +0.121 |
tank | +0.116 |
Neg logit contributions | |
vows | -0.035 |
ves | -0.029 |
brist | -0.026 |
growth | -0.024 |
blonde | -0.022 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ves | +1.013 |
vows | +0.989 |
Her | +0.986 |
brist | +0.969 |
growth | +0.900 |
Neg logit contributions | |
o | -1.151 |
alone | -1.093 |
forth | -0.991 |
tank | -0.988 |
my | -0.972 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
ves | +0.264 |
vows | +0.264 |
Her | +0.262 |
brist | +0.257 |
growth | +0.241 |
Neg logit contributions | |
o | -0.217 |
alone | -0.196 |
forth | -0.176 |
my | -0.175 |
tank | -0.175 |
Token | and |
Token ID | 290 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
Her | +0.061 |
vows | +0.059 |
brist | +0.059 |
ves | +0.058 |
blonde | +0.052 |
Neg logit contributions | |
o | -0.064 |
alone | -0.058 |
forth | -0.054 |
tank | -0.054 |
afloat | -0.053 |
Token | hugged |
Token ID | 41130 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
ves | +0.088 |
vows | +0.087 |
Her | +0.087 |
brist | +0.085 |
blonde | +0.079 |
Neg logit contributions | |
o | -0.067 |
alone | -0.061 |
forth | -0.055 |
tank | -0.054 |
my | -0.053 |
Token | her |
Token ID | 607 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ves | +0.107 |
vows | +0.106 |
brist | +0.099 |
Her | +0.097 |
blonde | +0.092 |
Neg logit contributions | |
o | -0.117 |
alone | -0.117 |
my | -0.105 |
forth | -0.103 |
tank | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
ves | +0.424 |
Her | +0.422 |
vows | +0.420 |
brist | +0.412 |
growth | +0.386 |
Neg logit contributions | |
o | -0.249 |
alone | -0.227 |
forth | -0.197 |
tank | -0.194 |
my | -0.188 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ves | +0.083 |
Her | +0.083 |
vows | +0.082 |
brist | +0.081 |
growth | +0.074 |
Neg logit contributions | |
o | -0.074 |
alone | -0.069 |
forth | -0.062 |
tank | -0.062 |
afloat | -0.060 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
o | +0.190 |
alone | +0.182 |
forth | +0.151 |
my | +0.142 |
tank | +0.141 |
Neg logit contributions | |
ves | -0.379 |
Her | -0.376 |
vows | -0.374 |
brist | -0.367 |
growth | -0.354 |
Token |
|
Token ID | 198 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
o | +0.175 |
alone | +0.168 |
my | +0.142 |
forth | +0.136 |
tank | +0.131 |
Neg logit contributions | |
vows | -0.261 |
ves | -0.255 |
brist | -0.239 |
growth | -0.236 |
blonde | -0.229 |
Token |
|
Token ID | 198 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
o | +0.066 |
alone | +0.060 |
forth | +0.055 |
tank | +0.053 |
afloat | +0.052 |
Neg logit contributions | |
ves | -0.092 |
Her | -0.092 |
vows | -0.091 |
brist | -0.090 |
growth | -0.083 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.071 |
alone | +0.070 |
forth | +0.066 |
my | +0.062 |
| | +0.057 |
Neg logit contributions | |
vows | -0.086 |
growth | -0.079 |
blonde | -0.077 |
brist | -0.076 |
ves | -0.074 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ves | +1.020 |
Her | +1.010 |
vows | +0.992 |
brist | +0.981 |
growth | +0.911 |
Neg logit contributions | |
o | -1.134 |
alone | -1.078 |
tank | -0.984 |
forth | -0.976 |
polar | -0.945 |
Token | is |
Token ID | 318 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ves | +0.264 |
Her | +0.263 |
vows | +0.259 |
brist | +0.255 |
blonde | +0.237 |
Neg logit contributions | |
o | -0.223 |
alone | -0.204 |
forth | -0.186 |
tank | -0.184 |
my | -0.181 |
Token | surprised |
Token ID | 6655 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
Her | +0.031 |
ves | +0.029 |
vows | +0.029 |
brist | +0.029 |
blonde | +0.027 |
Neg logit contributions | |
o | -0.021 |
alone | -0.017 |
tank | -0.017 |
forth | -0.017 |
polar | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
o | +0.129 |
alone | +0.120 |
forth | +0.108 |
my | +0.106 |
tank | +0.105 |
Neg logit contributions | |
ves | -0.148 |
vows | -0.147 |
Her | -0.144 |
brist | -0.143 |
growth | -0.133 |
Token | She |
Token ID | 1375 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ves | +0.110 |
vows | +0.107 |
Her | +0.102 |
brist | +0.100 |
growth | +0.094 |
Neg logit contributions | |
o | -0.154 |
alone | -0.147 |
tank | -0.132 |
my | -0.131 |
forth | -0.130 |
Token | lovely |
Token ID | 14081 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
o | +0.111 |
alone | +0.092 |
forth | +0.089 |
my | +0.089 |
| | +0.088 |
Neg logit contributions | |
vows | -0.103 |
ves | -0.088 |
ribbon | -0.085 |
Her | -0.081 |
brist | -0.080 |
Token | seal |
Token ID | 13810 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
vows | +0.230 |
ves | +0.212 |
ribbon | +0.194 |
Her | +0.187 |
brist | +0.186 |
Neg logit contributions | |
o | -0.224 |
alone | -0.191 |
forth | -0.184 |
afloat | -0.180 |
my | -0.178 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
o | +0.129 |
afloat | +0.117 |
ior | +0.113 |
| | +0.113 |
polar | +0.112 |
Neg logit contributions | |
ves | -0.177 |
vows | -0.177 |
Her | -0.173 |
ork | -0.155 |
veil | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
o | +0.409 |
my | +0.383 |
alone | +0.375 |
tank | +0.347 |
forth | +0.345 |
Neg logit contributions | |
ves | -0.265 |
vows | -0.239 |
growth | -0.228 |
brist | -0.227 |
comb | -0.211 |
Token |
|
Token ID | 198 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
o | +0.066 |
alone | +0.061 |
forth | +0.054 |
tank | +0.053 |
afloat | +0.052 |
Neg logit contributions | |
ves | -0.099 |
Her | -0.098 |
vows | -0.098 |
brist | -0.096 |
blonde | -0.089 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.119 |
alone | +0.112 |
my | +0.109 |
forth | +0.105 |
tank | +0.101 |
Neg logit contributions | |
growth | -0.045 |
ves | -0.044 |
vows | -0.043 |
brist | -0.043 |
der | -0.042 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
vows | +0.872 |
Her | +0.865 |
ves | +0.860 |
brist | +0.837 |
blonde | +0.741 |
Neg logit contributions | |
o | -1.288 |
alone | -1.214 |
forth | -1.125 |
afloat | -1.112 |
tank | -1.096 |
Token | said |
Token ID | 531 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
Her | +0.232 |
ves | +0.229 |
vows | +0.228 |
brist | +0.226 |
blonde | +0.203 |
Neg logit contributions | |
o | -0.224 |
alone | -0.220 |
afloat | -0.201 |
forth | -0.195 |
tank | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
o | +0.030 |
alone | +0.028 |
tank | +0.022 |
my | +0.022 |
forth | +0.020 |
Neg logit contributions | |
growth | -0.067 |
brist | -0.063 |
vows | -0.062 |
meanings | -0.060 |
ves | -0.060 |
Token | " |
Token ID | 366 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ves | +0.129 |
vows | +0.128 |
brist | +0.123 |
growth | +0.121 |
Her | +0.121 |
Neg logit contributions | |
o | -0.130 |
alone | -0.118 |
tank | -0.107 |
forth | -0.106 |
my | -0.105 |
Token | Sure |
Token ID | 19457 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ves | +0.272 |
vows | +0.271 |
brist | +0.263 |
Her | +0.261 |
growth | +0.244 |
Neg logit contributions | |
o | -0.242 |
alone | -0.220 |
forth | -0.201 |
my | -0.196 |
tank | -0.194 |
Token | touch |
Token ID | 3638 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
o | +0.132 |
alone | +0.114 |
tank | +0.106 |
my | +0.103 |
polar | +0.101 |
Neg logit contributions | |
ves | -0.173 |
vows | -0.170 |
brist | -0.166 |
Her | -0.166 |
blonde | -0.155 |
Token | it |
Token ID | 340 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
ves | +0.201 |
Her | +0.200 |
vows | +0.194 |
brist | +0.193 |
growth | +0.175 |
Neg logit contributions | |
o | -0.227 |
alone | -0.212 |
forth | -0.196 |
afloat | -0.194 |
tank | -0.192 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Her | +0.204 |
ves | +0.203 |
vows | +0.200 |
brist | +0.197 |
growth | +0.182 |
Neg logit contributions | |
o | -0.093 |
alone | -0.080 |
forth | -0.070 |
afloat | -0.068 |
tank | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
o | +0.399 |
alone | +0.362 |
my | +0.355 |
forth | +0.329 |
tank | +0.317 |
Neg logit contributions | |
vows | -0.301 |
ves | -0.291 |
brist | -0.261 |
growth | -0.248 |
comb | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
o | +0.069 |
alone | +0.064 |
forth | +0.058 |
tank | +0.057 |
afloat | +0.056 |
Neg logit contributions | |
Her | -0.100 |
ves | -0.100 |
vows | -0.098 |
brist | -0.097 |
growth | -0.089 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.137 |
alone | +0.125 |
my | +0.125 |
forth | +0.121 |
tank | +0.115 |
Neg logit contributions | |
vows | -0.036 |
growth | -0.032 |
brist | -0.029 |
ves | -0.029 |
owers | -0.027 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Her | +0.858 |
vows | +0.850 |
ves | +0.844 |
brist | +0.824 |
blonde | +0.730 |
Neg logit contributions | |
o | -1.288 |
alone | -1.213 |
forth | -1.128 |
afloat | -1.126 |
tank | -1.102 |
Token | said |
Token ID | 531 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
vows | +0.290 |
ves | +0.289 |
Her | +0.283 |
brist | +0.278 |
growth | +0.273 |
Neg logit contributions | |
o | -0.192 |
alone | -0.161 |
my | -0.154 |
forth | -0.150 |
tank | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
o | +0.032 |
alone | +0.029 |
my | +0.023 |
tank | +0.022 |
forth | +0.021 |
Neg logit contributions | |
growth | -0.071 |
vows | -0.068 |
brist | -0.067 |
ves | -0.065 |
meanings | -0.065 |
Token | " |
Token ID | 366 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
vows | +0.133 |
ves | +0.132 |
growth | +0.125 |
brist | +0.125 |
Her | +0.122 |
Neg logit contributions | |
o | -0.121 |
alone | -0.109 |
tank | -0.097 |
my | -0.096 |
forth | -0.095 |
Token | No |
Token ID | 2949 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
vows | +0.278 |
ves | +0.274 |
brist | +0.262 |
Her | +0.255 |
growth | +0.249 |
Neg logit contributions | |
o | -0.244 |
alone | -0.220 |
forth | -0.200 |
my | -0.196 |
tank | -0.189 |
Token | go |
Token ID | 467 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
o | +0.156 |
alone | +0.145 |
tank | +0.131 |
forth | +0.130 |
my | +0.127 |
Neg logit contributions | |
ves | -0.179 |
vows | -0.175 |
Her | -0.175 |
brist | -0.174 |
blonde | -0.158 |
Token | there |
Token ID | 612 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Her | +0.104 |
ves | +0.102 |
vows | +0.102 |
brist | +0.096 |
ribbon | +0.095 |
Neg logit contributions | |
o | -0.122 |
alone | -0.116 |
igator | -0.111 |
afloat | -0.106 |
forth | -0.106 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
o | +0.211 |
alone | +0.188 |
forth | +0.172 |
tank | +0.167 |
afloat | +0.165 |
Neg logit contributions | |
Her | -0.334 |
vows | -0.333 |
ves | -0.332 |
brist | -0.324 |
blonde | -0.303 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
o | +0.438 |
alone | +0.410 |
my | +0.408 |
Tim | +0.396 |
forth | +0.379 |
Neg logit contributions | |
ves | -0.246 |
vows | -0.229 |
growth | -0.200 |
brist | -0.188 |
comb | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
o | +0.068 |
alone | +0.063 |
forth | +0.056 |
tank | +0.055 |
afloat | +0.054 |
Neg logit contributions | |
Her | -0.100 |
ves | -0.100 |
vows | -0.098 |
brist | -0.097 |
blonde | -0.089 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.104 |
alone | +0.098 |
my | +0.094 |
forth | +0.090 |
tank | +0.085 |
Neg logit contributions | |
vows | -0.062 |
growth | -0.060 |
brist | -0.059 |
ves | -0.058 |
owers | -0.054 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ves | +0.943 |
Her | +0.936 |
vows | +0.935 |
brist | +0.914 |
blonde | +0.819 |
Neg logit contributions | |
o | -1.213 |
alone | -1.138 |
forth | -1.048 |
tank | -1.036 |
afloat | -1.017 |
Token | replied |
Token ID | 8712 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
ves | +0.258 |
vows | +0.256 |
Her | +0.256 |
brist | +0.251 |
growth | +0.232 |
Neg logit contributions | |
o | -0.207 |
alone | -0.189 |
forth | -0.171 |
tank | -0.168 |
my | -0.165 |
Token | , |
Token ID | 11 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
growth | +0.235 |
vows | +0.220 |
meanings | +0.212 |
ribbon | +0.209 |
ves | +0.209 |
Neg logit contributions | |
alone | -0.089 |
o | -0.088 |
down | -0.062 |
my | -0.059 |
tank | -0.059 |
Token | " |
Token ID | 366 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ves | +0.135 |
vows | +0.134 |
growth | +0.130 |
brist | +0.125 |
Her | +0.123 |
Neg logit contributions | |
o | -0.120 |
alone | -0.110 |
my | -0.097 |
tank | -0.097 |
forth | -0.095 |
Token | No |
Token ID | 2949 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
vows | +0.293 |
ves | +0.291 |
brist | +0.279 |
growth | +0.268 |
Her | +0.265 |
Neg logit contributions | |
o | -0.224 |
alone | -0.193 |
my | -0.177 |
forth | -0.176 |
tank | -0.163 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
o | +0.088 |
forth | +0.077 |
afloat | +0.077 |
alone | +0.077 |
tank | +0.074 |
Neg logit contributions | |
Her | -0.103 |
ves | -0.100 |
vows | -0.099 |
brist | -0.099 |
blonde | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
o | +0.235 |
alone | +0.233 |
tank | +0.184 |
my | +0.182 |
forth | +0.178 |
Neg logit contributions | |
vows | -0.406 |
ves | -0.398 |
Her | -0.383 |
brist | -0.377 |
growth | -0.367 |
Token | |
Token ID | 220 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
ves | +0.092 |
vows | +0.090 |
brist | +0.083 |
Her | +0.082 |
growth | +0.075 |
Neg logit contributions | |
o | -0.132 |
alone | -0.126 |
my | -0.117 |
tank | -0.112 |
forth | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
o | +0.081 |
alone | +0.075 |
forth | +0.074 |
tank | +0.070 |
polar | +0.070 |
Neg logit contributions | |
Her | -0.102 |
ves | -0.099 |
brist | -0.093 |
vows | -0.093 |
Her | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
o | +0.072 |
alone | +0.067 |
forth | +0.063 |
tank | +0.061 |
afloat | +0.060 |
Neg logit contributions | |
Her | -0.099 |
ves | -0.097 |
vows | -0.093 |
brist | -0.093 |
blonde | -0.087 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.087 |
alone | +0.082 |
my | +0.076 |
| | +0.068 |
forth | +0.066 |
Neg logit contributions | |
vows | -0.095 |
brist | -0.084 |
ves | -0.084 |
growth | -0.081 |
owers | -0.076 |
Token | teacher |
Token ID | 4701 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ves | +1.057 |
Her | +1.006 |
vows | +1.004 |
brist | +0.971 |
growth | +0.920 |
Neg logit contributions | |
o | -1.124 |
alone | -1.079 |
forth | -0.973 |
tank | -0.969 |
my | -0.951 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
ves | +0.615 |
vows | +0.612 |
brist | +0.603 |
growth | +0.599 |
Her | +0.598 |
Neg logit contributions | |
o | -0.387 |
alone | -0.344 |
my | -0.325 |
forth | -0.289 |
tank | -0.280 |
Token | this |
Token ID | 428 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
o | +0.123 |
alone | +0.122 |
my | +0.116 |
forth | +0.100 |
Tim | +0.099 |
Neg logit contributions | |
vows | -0.133 |
ves | -0.127 |
brist | -0.116 |
comb | -0.111 |
ork | -0.109 |
Token | and |
Token ID | 290 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
ves | +0.084 |
vows | +0.083 |
Her | +0.083 |
brist | +0.080 |
growth | +0.076 |
Neg logit contributions | |
o | -0.067 |
alone | -0.065 |
tank | -0.056 |
forth | -0.056 |
my | -0.056 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
growth | +0.102 |
vows | +0.102 |
ves | +0.102 |
brist | +0.100 |
ork | +0.097 |
Neg logit contributions | |
o | -0.045 |
alone | -0.041 |
my | -0.034 |
forth | -0.031 |
tank | -0.030 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
vows | +0.817 |
ves | +0.812 |
Her | +0.795 |
brist | +0.793 |
growth | +0.756 |
Neg logit contributions | |
o | -0.495 |
alone | -0.453 |
forth | -0.402 |
tank | -0.380 |
my | -0.377 |
Token | . |
Token ID | 13 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
alone | +0.055 |
o | +0.053 |
forth | +0.046 |
my | +0.045 |
tank | +0.042 |
Neg logit contributions | |
vows | -0.080 |
ves | -0.078 |
brist | -0.075 |
growth | -0.074 |
Her | -0.072 |
Token | |
Token ID | 220 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
ves | +0.107 |
vows | +0.101 |
brist | +0.100 |
ribbon | +0.090 |
growth | +0.090 |
Neg logit contributions | |
o | -0.131 |
alone | -0.117 |
my | -0.110 |
tank | -0.106 |
Tim | -0.105 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
o | +0.072 |
alone | +0.066 |
forth | +0.058 |
tank | +0.057 |
afloat | +0.055 |
Neg logit contributions | |
ves | -0.111 |
vows | -0.110 |
Her | -0.110 |
brist | -0.108 |
blonde | -0.100 |
Token |
|
Token ID | 198 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
o | +0.057 |
alone | +0.044 |
my | +0.039 |
tank | +0.036 |
| | +0.034 |
Neg logit contributions | |
brist | -0.119 |
vows | -0.119 |
ves | -0.115 |
blonde | -0.112 |
growth | -0.110 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.112 |
alone | +0.098 |
my | +0.093 |
forth | +0.089 |
tank | +0.089 |
Neg logit contributions | |
brist | -0.060 |
vows | -0.056 |
growth | -0.054 |
blonde | -0.054 |
der | -0.053 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ves | +1.040 |
Her | +1.020 |
vows | +1.006 |
brist | +0.992 |
growth | +0.933 |
Neg logit contributions | |
o | -1.132 |
alone | -1.064 |
tank | -0.976 |
forth | -0.969 |
my | -0.947 |
Token | laughed |
Token ID | 13818 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
ves | +0.275 |
vows | +0.273 |
Her | +0.266 |
growth | +0.263 |
brist | +0.261 |
Neg logit contributions | |
o | -0.202 |
my | -0.167 |
alone | -0.165 |
forth | -0.157 |
tank | -0.149 |
Token | and |
Token ID | 290 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
alone | +0.030 |
o | +0.030 |
forth | +0.025 |
my | +0.025 |
tank | +0.024 |
Neg logit contributions | |
ves | -0.052 |
vows | -0.051 |
brist | -0.048 |
growth | -0.047 |
Her | -0.047 |
Token | replied |
Token ID | 8712 |
Feature activation | -8.23e-02 |
Pos logit contributions | |
ves | +0.095 |
vows | +0.094 |
Her | +0.091 |
brist | +0.090 |
growth | +0.089 |
Neg logit contributions | |
o | -0.055 |
alone | -0.048 |
forth | -0.045 |
my | -0.041 |
tank | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
growth | +0.226 |
vows | +0.216 |
ves | +0.206 |
Her | +0.203 |
meanings | +0.199 |
Neg logit contributions | |
alone | -0.092 |
o | -0.091 |
down | -0.068 |
my | -0.063 |
forth | -0.062 |
Token | dull |
Token ID | 19222 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
o | +0.095 |
alone | +0.085 |
forth | +0.080 |
afloat | +0.078 |
| | +0.075 |
Neg logit contributions | |
vows | -0.100 |
brist | -0.096 |
ves | -0.096 |
Her | -0.095 |
blonde | -0.089 |
Token | ones |
Token ID | 3392 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
vows | +0.086 |
ves | +0.086 |
brist | +0.084 |
Her | +0.084 |
blonde | +0.077 |
Neg logit contributions | |
o | -0.065 |
alone | -0.061 |
forth | -0.055 |
afloat | -0.054 |
tank | -0.051 |
Token | ." |
Token ID | 526 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ves | +0.332 |
vows | +0.328 |
Her | +0.327 |
brist | +0.320 |
blonde | +0.292 |
Neg logit contributions | |
o | -0.301 |
alone | -0.276 |
forth | -0.256 |
tank | -0.250 |
afloat | -0.248 |
Token |
|
Token ID | 198 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
o | +0.134 |
alone | +0.118 |
my | +0.097 |
tank | +0.091 |
forth | +0.085 |
Neg logit contributions | |
vows | -0.294 |
ves | -0.290 |
brist | -0.281 |
Her | -0.262 |
ribbon | -0.261 |
Token |
|
Token ID | 198 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
o | +0.069 |
alone | +0.065 |
forth | +0.060 |
tank | +0.058 |
afloat | +0.057 |
Neg logit contributions | |
Her | -0.094 |
ves | -0.093 |
vows | -0.089 |
brist | -0.089 |
growth | -0.082 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.130 |
alone | +0.122 |
my | +0.114 |
forth | +0.114 |
tank | +0.112 |
Neg logit contributions | |
vows | -0.036 |
brist | -0.033 |
ves | -0.030 |
blonde | -0.028 |
growth | -0.025 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ves | +1.045 |
Her | +1.036 |
brist | +1.009 |
vows | +1.005 |
growth | +0.959 |
Neg logit contributions | |
o | -1.113 |
alone | -1.046 |
tank | -0.962 |
polar | -0.939 |
forth | -0.937 |
Token | and |
Token ID | 290 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
vows | +0.277 |
ves | +0.277 |
Her | +0.273 |
brist | +0.267 |
growth | +0.258 |
Neg logit contributions | |
o | -0.209 |
alone | -0.177 |
my | -0.173 |
tank | -0.160 |
forth | -0.159 |
Token | dad |
Token ID | 9955 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
ves | +0.082 |
vows | +0.080 |
brist | +0.078 |
Her | +0.078 |
growth | +0.072 |
Neg logit contributions | |
o | -0.072 |
alone | -0.068 |
forth | -0.062 |
my | -0.060 |
tank | -0.060 |
Token | hugged |
Token ID | 41130 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
ves | +0.146 |
Her | +0.142 |
vows | +0.140 |
brist | +0.140 |
ork | +0.132 |
Neg logit contributions | |
o | -0.108 |
alone | -0.097 |
my | -0.093 |
forth | -0.089 |
tank | -0.087 |
Token | her |
Token ID | 607 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ves | +0.092 |
vows | +0.091 |
brist | +0.085 |
Her | +0.079 |
blonde | +0.078 |
Neg logit contributions | |
o | -0.131 |
alone | -0.129 |
my | -0.119 |
forth | -0.117 |
tank | -0.112 |
Token | big |
Token ID | 1263 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
alone | +0.102 |
o | +0.094 |
tank | +0.085 |
polar | +0.082 |
my | +0.082 |
Neg logit contributions | |
ves | -0.126 |
vows | -0.120 |
Her | -0.112 |
ork | -0.108 |
owers | -0.106 |
Token | eyes |
Token ID | 2951 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ves | +0.081 |
Her | +0.076 |
vows | +0.075 |
brist | +0.067 |
growth | +0.062 |
Neg logit contributions | |
o | -0.153 |
alone | -0.151 |
tank | -0.139 |
forth | -0.139 |
my | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
ves | +0.833 |
vows | +0.821 |
Her | +0.780 |
brist | +0.764 |
growth | +0.761 |
Neg logit contributions | |
alone | -0.513 |
o | -0.499 |
my | -0.421 |
forth | -0.394 |
tank | -0.394 |
Token | |
Token ID | 220 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
ves | +0.137 |
vows | +0.133 |
brist | +0.126 |
ribbon | +0.120 |
Her | +0.120 |
Neg logit contributions | |
o | -0.098 |
alone | -0.090 |
tank | -0.079 |
my | -0.079 |
forth | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
o | +0.075 |
alone | +0.068 |
forth | +0.061 |
tank | +0.060 |
afloat | +0.058 |
Neg logit contributions | |
ves | -0.111 |
Her | -0.111 |
vows | -0.110 |
brist | -0.109 |
blonde | -0.101 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.059 |
alone | +0.050 |
my | +0.043 |
tank | +0.042 |
forth | +0.039 |
Neg logit contributions | |
vows | -0.116 |
brist | -0.112 |
ves | -0.112 |
blonde | -0.106 |
Her | -0.104 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Her | +0.862 |
vows | +0.860 |
ves | +0.856 |
brist | +0.846 |
blonde | +0.746 |
Neg logit contributions | |
o | -1.283 |
alone | -1.195 |
forth | -1.123 |
afloat | -1.106 |
tank | -1.094 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
ves | +0.273 |
vows | +0.272 |
Her | +0.268 |
brist | +0.264 |
growth | +0.249 |
Neg logit contributions | |
o | -0.192 |
alone | -0.170 |
forth | -0.154 |
my | -0.152 |
tank | -0.149 |
Token | and |
Token ID | 290 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
ves | +0.065 |
vows | +0.064 |
Her | +0.063 |
brist | +0.062 |
growth | +0.058 |
Neg logit contributions | |
o | -0.052 |
alone | -0.049 |
forth | -0.044 |
tank | -0.043 |
my | -0.042 |
Token | hugged |
Token ID | 41130 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
ves | +0.083 |
vows | +0.083 |
Her | +0.081 |
brist | +0.080 |
growth | +0.076 |
Neg logit contributions | |
o | -0.061 |
alone | -0.054 |
forth | -0.050 |
tank | -0.047 |
my | -0.047 |
Token | her |
Token ID | 607 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ves | +0.098 |
vows | +0.097 |
brist | +0.090 |
Her | +0.089 |
ork | +0.082 |
Neg logit contributions | |
o | -0.122 |
alone | -0.119 |
forth | -0.109 |
my | -0.107 |
tank | -0.104 |
Token | exclaimed |
Token ID | 33552 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
o | +0.153 |
alone | +0.137 |
forth | +0.120 |
my | +0.117 |
tank | +0.116 |
Neg logit contributions | |
vows | -0.218 |
ves | -0.215 |
brist | -0.210 |
Her | -0.209 |
growth | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
ves | +0.226 |
vows | +0.225 |
Her | +0.223 |
brist | +0.219 |
growth | +0.201 |
Neg logit contributions | |
o | -0.213 |
alone | -0.199 |
forth | -0.179 |
tank | -0.177 |
afloat | -0.173 |
Token | |
Token ID | 220 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
ves | +0.129 |
vows | +0.120 |
brist | +0.116 |
growth | +0.110 |
Her | +0.109 |
Neg logit contributions | |
o | -0.121 |
alone | -0.115 |
tank | -0.104 |
my | -0.102 |
forth | -0.099 |
Token |
|
Token ID | 198 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
o | +0.083 |
alone | +0.078 |
forth | +0.076 |
tank | +0.073 |
polar | +0.072 |
Neg logit contributions | |
Her | -0.106 |
ves | -0.104 |
brist | -0.097 |
vows | -0.097 |
Her | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
o | +0.071 |
alone | +0.065 |
forth | +0.058 |
tank | +0.057 |
afloat | +0.056 |
Neg logit contributions | |
Her | -0.103 |
ves | -0.103 |
vows | -0.101 |
brist | -0.099 |
blonde | -0.092 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.091 |
alone | +0.089 |
forth | +0.081 |
my | +0.079 |
tank | +0.079 |
Neg logit contributions | |
vows | -0.074 |
ves | -0.073 |
brist | -0.072 |
growth | -0.070 |
blonde | -0.065 |
Token | dad |
Token ID | 9955 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
ves | +1.024 |
Her | +1.009 |
vows | +0.992 |
brist | +0.979 |
growth | +0.906 |
Neg logit contributions | |
o | -1.144 |
alone | -1.072 |
tank | -0.981 |
forth | -0.979 |
polar | -0.953 |
Token | said |
Token ID | 531 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
ves | +0.133 |
vows | +0.133 |
Her | +0.132 |
brist | +0.130 |
growth | +0.122 |
Neg logit contributions | |
o | -0.113 |
alone | -0.100 |
forth | -0.092 |
my | -0.091 |
tank | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
o | +0.041 |
alone | +0.038 |
tank | +0.033 |
polar | +0.031 |
forth | +0.031 |
Neg logit contributions | |
brist | -0.054 |
vows | -0.054 |
ves | -0.054 |
Her | -0.053 |
growth | -0.053 |
Token | " |
Token ID | 366 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Her | +0.102 |
ves | +0.102 |
vows | +0.101 |
brist | +0.099 |
blonde | +0.088 |
Neg logit contributions | |
o | -0.146 |
alone | -0.137 |
forth | -0.128 |
tank | -0.125 |
afloat | -0.124 |
Token | You |
Token ID | 1639 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
Her | +0.247 |
ves | +0.240 |
brist | +0.236 |
vows | +0.236 |
blonde | +0.213 |
Neg logit contributions | |
o | -0.257 |
alone | -0.244 |
tank | -0.222 |
forth | -0.221 |
afloat | -0.218 |
Token | lot |
Token ID | 1256 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
vows | +0.244 |
ves | +0.240 |
Her | +0.233 |
brist | +0.226 |
growth | +0.205 |
Neg logit contributions | |
o | -0.376 |
alone | -0.366 |
tank | -0.333 |
forth | -0.332 |
my | -0.327 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
vows | +0.523 |
ves | +0.521 |
Her | +0.515 |
brist | +0.506 |
blonde | +0.468 |
Neg logit contributions | |
o | -0.480 |
alone | -0.452 |
forth | -0.399 |
tank | -0.397 |
my | -0.391 |
Token | |
Token ID | 220 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
ves | +0.138 |
vows | +0.137 |
Her | +0.135 |
brist | +0.134 |
growth | +0.124 |
Neg logit contributions | |
o | -0.101 |
alone | -0.093 |
forth | -0.082 |
tank | -0.080 |
my | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
o | +0.081 |
alone | +0.077 |
forth | +0.075 |
polar | +0.072 |
tank | +0.072 |
Neg logit contributions | |
Her | -0.103 |
ves | -0.101 |
brist | -0.095 |
vows | -0.094 |
Her | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
o | +0.078 |
alone | +0.074 |
forth | +0.071 |
tank | +0.068 |
afloat | +0.068 |
Neg logit contributions | |
Her | -0.100 |
ves | -0.097 |
vows | -0.091 |
brist | -0.091 |
Her | -0.086 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
alone | +0.116 |
o | +0.116 |
my | +0.106 |
forth | +0.102 |
| | +0.098 |
Neg logit contributions | |
vows | -0.066 |
growth | -0.052 |
ves | -0.052 |
brist | -0.051 |
owers | -0.047 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Her | +0.916 |
ves | +0.914 |
vows | +0.907 |
brist | +0.896 |
blonde | +0.795 |
Neg logit contributions | |
o | -1.230 |
alone | -1.147 |
forth | -1.060 |
tank | -1.048 |
afloat | -1.041 |
Token | came |
Token ID | 1625 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
Her | +0.368 |
brist | +0.350 |
ves | +0.347 |
vows | +0.333 |
blush | +0.330 |
Neg logit contributions | |
o | -0.081 |
afloat | -0.078 |
alone | -0.075 |
tank | -0.065 |
| | -0.056 |
Token | outside |
Token ID | 2354 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
Her | +0.127 |
brist | +0.112 |
Her | +0.103 |
ves | +0.102 |
vows | +0.099 |
Neg logit contributions | |
o | -0.124 |
igator | -0.118 |
afloat | -0.116 |
tank | -0.113 |
wreck | -0.111 |
Token | and |
Token ID | 290 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
o | +0.095 |
alone | +0.089 |
forth | +0.080 |
tank | +0.079 |
my | +0.076 |
Neg logit contributions | |
ves | -0.109 |
vows | -0.109 |
Her | -0.108 |
brist | -0.106 |
blonde | -0.098 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
Her | +0.081 |
ves | +0.074 |
brist | +0.073 |
vows | +0.069 |
Her | +0.068 |
Neg logit contributions | |
o | -0.065 |
afloat | -0.062 |
alone | -0.061 |
tank | -0.059 |
| | -0.056 |
Token | glowing |
Token ID | 21377 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
o | +0.024 |
alone | +0.022 |
forth | +0.020 |
tank | +0.020 |
afloat | +0.019 |
Neg logit contributions | |
ves | -0.032 |
Her | -0.031 |
vows | -0.031 |
brist | -0.031 |
blonde | -0.029 |
Token | red |
Token ID | 2266 |
Feature activation | -6.00e-03 |
Pos logit contributions | |
Her | +0.079 |
ves | +0.078 |
vows | +0.075 |
brist | +0.075 |
growth | +0.072 |
Neg logit contributions | |
o | -0.045 |
alone | -0.043 |
forth | -0.036 |
tank | -0.036 |
my | -0.035 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ves | +0.016 |
Her | +0.016 |
vows | +0.015 |
brist | +0.015 |
growth | +0.015 |
Neg logit contributions | |
o | -0.007 |
alone | -0.006 |
my | -0.006 |
forth | -0.005 |
tank | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
o | +0.134 |
alone | +0.105 |
my | +0.087 |
tank | +0.084 |
polar | +0.074 |
Neg logit contributions | |
vows | -0.325 |
ves | -0.317 |
brist | -0.306 |
ribbon | -0.289 |
blonde | -0.285 |
Token |
|
Token ID | 198 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
o | +0.062 |
alone | +0.055 |
tank | +0.047 |
forth | +0.047 |
my | +0.046 |
Neg logit contributions | |
vows | -0.101 |
ves | -0.100 |
brist | -0.100 |
Her | -0.099 |
blonde | -0.093 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.079 |
alone | +0.065 |
my | +0.060 |
forth | +0.060 |
tank | +0.059 |
Neg logit contributions | |
vows | -0.089 |
brist | -0.085 |
ves | -0.084 |
blonde | -0.082 |
blush | -0.080 |
Token | mother |
Token ID | 2802 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ves | +0.875 |
vows | +0.821 |
Her | +0.820 |
brist | +0.773 |
growth | +0.736 |
Neg logit contributions | |
o | -1.324 |
alone | -1.217 |
forth | -1.180 |
my | -1.162 |
polar | -1.157 |
Token | smiled |
Token ID | 13541 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
ves | +0.550 |
vows | +0.549 |
Her | +0.538 |
brist | +0.525 |
growth | +0.502 |
Neg logit contributions | |
o | -0.437 |
alone | -0.382 |
my | -0.359 |
forth | -0.355 |
tank | -0.340 |
Token | and |
Token ID | 290 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
ves | +0.071 |
vows | +0.069 |
Her | +0.067 |
brist | +0.067 |
growth | +0.063 |
Neg logit contributions | |
o | -0.052 |
alone | -0.049 |
forth | -0.043 |
tank | -0.042 |
my | -0.042 |
Token | nodded |
Token ID | 14464 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ves | +0.094 |
vows | +0.093 |
Her | +0.091 |
brist | +0.091 |
growth | +0.087 |
Neg logit contributions | |
o | -0.056 |
alone | -0.048 |
forth | -0.044 |
my | -0.042 |
tank | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
ves | +0.368 |
vows | +0.348 |
brist | +0.335 |
growth | +0.332 |
ork | +0.326 |
Neg logit contributions | |
alone | -0.243 |
o | -0.240 |
forth | -0.208 |
my | -0.203 |
tank | -0.194 |
Token | large |
Token ID | 1588 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
alone | +0.105 |
o | +0.105 |
forth | +0.094 |
tank | +0.091 |
my | +0.089 |
Neg logit contributions | |
Her | -0.100 |
ves | -0.100 |
vows | -0.100 |
brist | -0.097 |
growth | -0.092 |
Token | swing |
Token ID | 9628 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Her | +0.152 |
ves | +0.152 |
vows | +0.150 |
brist | +0.146 |
growth | +0.137 |
Neg logit contributions | |
o | -0.116 |
alone | -0.113 |
forth | -0.101 |
tank | -0.097 |
my | -0.096 |
Token | ." |
Token ID | 526 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ves | +0.284 |
Her | +0.282 |
vows | +0.280 |
brist | +0.271 |
ribbon | +0.251 |
Neg logit contributions | |
o | -0.207 |
alone | -0.186 |
afloat | -0.174 |
forth | -0.172 |
polar | -0.171 |
Token |
|
Token ID | 198 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
o | +0.162 |
alone | +0.148 |
my | +0.125 |
tank | +0.125 |
forth | +0.123 |
Neg logit contributions | |
ves | -0.258 |
vows | -0.257 |
brist | -0.248 |
Her | -0.243 |
growth | -0.233 |
Token |
|
Token ID | 198 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
o | +0.071 |
alone | +0.065 |
forth | +0.059 |
tank | +0.057 |
afloat | +0.056 |
Neg logit contributions | |
Her | -0.101 |
ves | -0.101 |
vows | -0.099 |
brist | -0.098 |
growth | -0.090 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.122 |
alone | +0.119 |
forth | +0.110 |
my | +0.110 |
tank | +0.105 |
Neg logit contributions | |
vows | -0.053 |
brist | -0.047 |
ves | -0.047 |
growth | -0.044 |
blonde | -0.041 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ves | +1.004 |
Her | +0.991 |
vows | +0.987 |
brist | +0.970 |
growth | +0.902 |
Neg logit contributions | |
o | -1.154 |
alone | -1.085 |
forth | -0.992 |
tank | -0.986 |
my | -0.965 |
Token | hugged |
Token ID | 41130 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
vows | +0.271 |
ves | +0.270 |
Her | +0.269 |
brist | +0.264 |
growth | +0.253 |
Neg logit contributions | |
o | -0.204 |
alone | -0.178 |
my | -0.164 |
forth | -0.161 |
tank | -0.158 |
Token | her |
Token ID | 607 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ves | +0.076 |
vows | +0.075 |
Her | +0.074 |
brist | +0.072 |
blonde | +0.063 |
Neg logit contributions | |
o | -0.144 |
alone | -0.138 |
forth | -0.128 |
tank | -0.127 |
my | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
Her | +0.572 |
brist | +0.564 |
vows | +0.564 |
ves | +0.559 |
ribbon | +0.507 |
Neg logit contributions | |
o | -0.590 |
alone | -0.526 |
forth | -0.484 |
tank | -0.481 |
afloat | -0.480 |
Token | said |
Token ID | 531 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
ves | +0.091 |
vows | +0.091 |
Her | +0.090 |
brist | +0.089 |
growth | +0.084 |
Neg logit contributions | |
o | -0.057 |
alone | -0.052 |
forth | -0.047 |
tank | -0.044 |
my | -0.044 |
Token | ground |
Token ID | 2323 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
o | +0.109 |
alone | +0.102 |
forth | +0.093 |
tank | +0.092 |
afloat | +0.090 |
Neg logit contributions | |
ves | -0.093 |
Her | -0.092 |
vows | -0.092 |
brist | -0.090 |
blonde | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
vows | +0.289 |
Her | +0.287 |
ves | +0.285 |
brist | +0.281 |
growth | +0.261 |
Neg logit contributions | |
o | -0.237 |
alone | -0.225 |
tank | -0.196 |
forth | -0.193 |
my | -0.190 |
Token | |
Token ID | 220 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
ves | +0.129 |
vows | +0.123 |
brist | +0.122 |
Her | +0.122 |
growth | +0.110 |
Neg logit contributions | |
o | -0.100 |
alone | -0.098 |
tank | -0.089 |
my | -0.083 |
| | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
o | +0.078 |
alone | +0.073 |
forth | +0.069 |
tank | +0.065 |
polar | +0.064 |
Neg logit contributions | |
ves | -0.105 |
Her | -0.105 |
vows | -0.101 |
brist | -0.100 |
growth | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
o | +0.069 |
alone | +0.063 |
forth | +0.057 |
tank | +0.055 |
afloat | +0.054 |
Neg logit contributions | |
ves | -0.099 |
Her | -0.099 |
vows | -0.097 |
brist | -0.095 |
blonde | -0.088 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
alone | +0.082 |
o | +0.081 |
my | +0.072 |
tank | +0.071 |
late | +0.071 |
Neg logit contributions | |
vows | -0.080 |
brist | -0.077 |
ves | -0.076 |
growth | -0.073 |
owers | -0.070 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
Her | +1.364 |
ves | +1.358 |
vows | +1.341 |
brist | +1.311 |
growth | +1.255 |
Neg logit contributions | |
o | -0.808 |
alone | -0.740 |
tank | -0.651 |
forth | -0.634 |
polar | -0.625 |
Token | gathered |
Token ID | 9272 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
o | +0.047 |
alone | +0.043 |
forth | +0.039 |
my | +0.039 |
tank | +0.038 |
Neg logit contributions | |
ves | -0.054 |
Her | -0.054 |
vows | -0.054 |
brist | -0.053 |
growth | -0.049 |
Token | around |
Token ID | 1088 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ves | +0.315 |
Her | +0.310 |
vows | +0.306 |
brist | +0.298 |
growth | +0.279 |
Neg logit contributions | |
o | -0.210 |
alone | -0.202 |
forth | -0.176 |
tank | -0.175 |
my | -0.167 |
Token | the |
Token ID | 262 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
alone | +0.178 |
o | +0.167 |
tank | +0.144 |
forth | +0.143 |
my | +0.133 |
Neg logit contributions | |
ves | -0.389 |
vows | -0.385 |
Her | -0.379 |
brist | -0.367 |
growth | -0.358 |
Token | crack |
Token ID | 8469 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
o | +0.110 |
alone | +0.103 |
forth | +0.094 |
tank | +0.093 |
afloat | +0.092 |
Neg logit contributions | |
ves | -0.091 |
Her | -0.090 |
vows | -0.090 |
brist | -0.088 |
blonde | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
o | +0.065 |
tank | +0.056 |
afloat | +0.056 |
alone | +0.055 |
| | +0.055 |
Neg logit contributions | |
Her | -0.077 |
brist | -0.075 |
ves | -0.073 |
vows | -0.073 |
blush | -0.069 |
Token | cup |
Token ID | 6508 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
o | +0.100 |
alone | +0.097 |
tank | +0.087 |
my | +0.087 |
polar | +0.082 |
Neg logit contributions | |
ves | -0.109 |
Her | -0.108 |
vows | -0.108 |
growth | -0.099 |
brist | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
vows | +0.365 |
ves | +0.365 |
Her | +0.350 |
brist | +0.347 |
blonde | +0.333 |
Neg logit contributions | |
o | -0.241 |
alone | -0.230 |
my | -0.192 |
tank | -0.189 |
forth | -0.188 |
Token |
|
Token ID | 198 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
ves | +0.130 |
vows | +0.130 |
brist | +0.124 |
Her | +0.121 |
growth | +0.118 |
Neg logit contributions | |
o | -0.095 |
alone | -0.086 |
my | -0.077 |
forth | -0.076 |
tank | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
o | +0.079 |
alone | +0.076 |
forth | +0.073 |
afloat | +0.071 |
tank | +0.071 |
Neg logit contributions | |
Her | -0.098 |
ves | -0.096 |
vows | -0.088 |
brist | -0.088 |
Her | -0.084 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.103 |
alone | +0.101 |
my | +0.096 |
forth | +0.093 |
ny | +0.085 |
Neg logit contributions | |
vows | -0.078 |
growth | -0.070 |
ves | -0.064 |
brist | -0.063 |
owers | -0.062 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ves | +1.010 |
vows | +0.996 |
Her | +0.988 |
brist | +0.969 |
growth | +0.896 |
Neg logit contributions | |
o | -1.156 |
alone | -1.078 |
forth | -0.986 |
tank | -0.982 |
my | -0.965 |
Token | noticed |
Token ID | 6810 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
Her | +0.250 |
ves | +0.249 |
vows | +0.244 |
brist | +0.243 |
blonde | +0.221 |
Neg logit contributions | |
o | -0.205 |
alone | -0.193 |
afloat | -0.174 |
tank | -0.172 |
forth | -0.170 |
Token | that |
Token ID | 326 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
vows | +0.175 |
ves | +0.159 |
brist | +0.146 |
blonde | +0.144 |
growth | +0.142 |
Neg logit contributions | |
o | -0.138 |
alone | -0.133 |
my | -0.128 |
forth | -0.116 |
tank | -0.107 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
vows | +0.466 |
ves | +0.461 |
Her | +0.450 |
brist | +0.446 |
growth | +0.428 |
Neg logit contributions | |
o | -0.247 |
alone | -0.237 |
forth | -0.199 |
my | -0.194 |
tank | -0.190 |
Token | was |
Token ID | 373 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
o | +0.154 |
alone | +0.143 |
my | +0.128 |
forth | +0.123 |
tank | +0.119 |
Neg logit contributions | |
vows | -0.218 |
Her | -0.212 |
ves | -0.210 |
brist | -0.205 |
growth | -0.202 |
Token | it |
Token ID | 340 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
o | +0.088 |
alone | +0.086 |
forth | +0.076 |
my | +0.072 |
tank | +0.071 |
Neg logit contributions | |
vows | -0.128 |
ves | -0.121 |
brist | -0.120 |
Her | -0.117 |
growth | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
ves | +0.157 |
vows | +0.157 |
Her | +0.156 |
brist | +0.154 |
growth | +0.142 |
Neg logit contributions | |
o | -0.139 |
alone | -0.131 |
forth | -0.117 |
tank | -0.115 |
my | -0.113 |
Token | |
Token ID | 220 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
ves | +0.107 |
vows | +0.105 |
brist | +0.102 |
growth | +0.096 |
Her | +0.096 |
Neg logit contributions | |
o | -0.126 |
alone | -0.113 |
my | -0.107 |
tank | -0.105 |
forth | -0.103 |
Token |
|
Token ID | 198 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
o | +0.080 |
alone | +0.077 |
forth | +0.075 |
tank | +0.071 |
afloat | +0.071 |
Neg logit contributions | |
Her | -0.104 |
ves | -0.102 |
vows | -0.096 |
brist | -0.094 |
Her | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
o | +0.074 |
alone | +0.071 |
forth | +0.065 |
afloat | +0.063 |
tank | +0.063 |
Neg logit contributions | |
Her | -0.100 |
ves | -0.098 |
vows | -0.095 |
brist | -0.092 |
ork | -0.086 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.090 |
my | +0.081 |
alone | +0.079 |
forth | +0.074 |
ny | +0.071 |
Neg logit contributions | |
growth | -0.088 |
vows | -0.085 |
ves | -0.081 |
brist | -0.081 |
der | -0.079 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ves | +1.013 |
vows | +0.997 |
Her | +0.989 |
brist | +0.976 |
growth | +0.909 |
Neg logit contributions | |
o | -1.150 |
alone | -1.074 |
forth | -0.984 |
tank | -0.979 |
my | -0.966 |
Token | said |
Token ID | 531 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
ves | +0.273 |
vows | +0.272 |
Her | +0.270 |
brist | +0.267 |
growth | +0.251 |
Neg logit contributions | |
o | -0.193 |
alone | -0.174 |
forth | -0.156 |
tank | -0.152 |
my | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
o | +0.031 |
alone | +0.028 |
Tim | +0.024 |
Nem | +0.024 |
my | +0.021 |
Neg logit contributions | |
growth | -0.070 |
brist | -0.063 |
vows | -0.063 |
meanings | -0.062 |
owers | -0.060 |
Token | " |
Token ID | 366 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
vows | +0.139 |
growth | +0.136 |
ves | +0.136 |
brist | +0.129 |
Her | +0.126 |
Neg logit contributions | |
o | -0.117 |
alone | -0.102 |
my | -0.093 |
tank | -0.090 |
forth | -0.088 |
Token | Sure |
Token ID | 19457 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
vows | +0.254 |
ves | +0.253 |
brist | +0.239 |
Her | +0.236 |
growth | +0.226 |
Neg logit contributions | |
o | -0.262 |
alone | -0.241 |
forth | -0.222 |
my | -0.221 |
tank | -0.210 |
Token | question |
Token ID | 1808 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
o | +0.002 |
alone | +0.002 |
forth | +0.002 |
tank | +0.002 |
polar | +0.002 |
Neg logit contributions | |
Her | -0.002 |
ves | -0.002 |
brist | -0.002 |
vows | -0.002 |
growth | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
brist | +0.391 |
growth | +0.381 |
vows | +0.381 |
ves | +0.373 |
Her | +0.364 |
Neg logit contributions | |
o | -0.254 |
alone | -0.239 |
my | -0.213 |
tank | -0.178 |
forth | -0.177 |
Token | |
Token ID | 220 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
ves | +0.105 |
vows | +0.098 |
brist | +0.094 |
growth | +0.087 |
ribbon | +0.085 |
Neg logit contributions | |
o | -0.128 |
alone | -0.112 |
my | -0.106 |
tank | -0.103 |
Tim | -0.099 |
Token |
|
Token ID | 198 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
o | +0.073 |
alone | +0.067 |
forth | +0.060 |
tank | +0.059 |
afloat | +0.057 |
Neg logit contributions | |
ves | -0.110 |
Her | -0.109 |
vows | -0.109 |
brist | -0.107 |
blonde | -0.099 |
Token |
|
Token ID | 198 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
o | +0.064 |
alone | +0.055 |
my | +0.048 |
tank | +0.046 |
forth | +0.045 |
Neg logit contributions | |
vows | -0.114 |
brist | -0.112 |
ves | -0.111 |
Her | -0.107 |
blonde | -0.104 |
Token | Her |
Token ID | 9360 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
o | +0.115 |
alone | +0.105 |
my | +0.102 |
forth | +0.096 |
late | +0.092 |
Neg logit contributions | |
vows | -0.061 |
brist | -0.055 |
der | -0.054 |
growth | -0.053 |
ves | -0.052 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ves | +1.174 |
Her | +1.134 |
vows | +1.110 |
brist | +1.107 |
growth | +1.101 |
Neg logit contributions | |
o | -1.027 |
alone | -0.938 |
tank | -0.869 |
my | -0.860 |
forth | -0.847 |
Token | explained |
Token ID | 4893 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
vows | +0.272 |
ves | +0.271 |
Her | +0.267 |
brist | +0.266 |
growth | +0.253 |
Neg logit contributions | |
o | -0.200 |
alone | -0.174 |
my | -0.164 |
forth | -0.160 |
tank | -0.154 |
Token | that |
Token ID | 326 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
vows | +0.258 |
growth | +0.257 |
ves | +0.246 |
brist | +0.242 |
blonde | +0.236 |
Neg logit contributions | |
alone | -0.149 |
o | -0.143 |
my | -0.125 |
by | -0.122 |
mad | -0.115 |
Token | ge |
Token ID | 4903 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
vows | +0.434 |
Her | +0.430 |
brist | +0.422 |
ves | +0.422 |
growth | +0.401 |
Neg logit contributions | |
o | -0.278 |
alone | -0.267 |
my | -0.226 |
forth | -0.220 |
tank | -0.220 |
Token | ese |
Token ID | 2771 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
o | +0.103 |
alone | +0.095 |
forth | +0.084 |
tank | +0.083 |
afloat | +0.080 |
Neg logit contributions | |
ves | -0.153 |
Her | -0.152 |
vows | -0.151 |
brist | -0.149 |
blonde | -0.138 |
Token | excited |
Token ID | 6568 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
o | +0.119 |
forth | +0.099 |
afloat | +0.098 |
tank | +0.098 |
alone | +0.097 |
Neg logit contributions | |
Her | -0.156 |
vows | -0.151 |
brist | -0.148 |
ves | -0.148 |
blonde | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
o | +0.078 |
alone | +0.074 |
my | +0.065 |
forth | +0.065 |
tank | +0.061 |
Neg logit contributions | |
vows | -0.102 |
ves | -0.102 |
Her | -0.100 |
brist | -0.099 |
growth | -0.094 |
Token | but |
Token ID | 475 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
vows | +0.106 |
ves | +0.106 |
Her | +0.102 |
brist | +0.101 |
growth | +0.099 |
Neg logit contributions | |
o | -0.053 |
alone | -0.051 |
forth | -0.043 |
my | -0.042 |
tank | -0.039 |
Token | then |
Token ID | 788 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
o | +0.152 |
alone | +0.145 |
forth | +0.136 |
tank | +0.133 |
my | +0.133 |
Neg logit contributions | |
ves | -0.067 |
vows | -0.066 |
Her | -0.065 |
brist | -0.064 |
growth | -0.055 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ves | +0.065 |
growth | +0.062 |
vows | +0.061 |
brist | +0.059 |
ork | +0.059 |
Neg logit contributions | |
alone | -0.075 |
forth | -0.074 |
o | -0.073 |
my | -0.070 |
Tim | -0.065 |
Token | my |
Token ID | 1820 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
Her | +0.031 |
brist | +0.030 |
ves | +0.030 |
blush | +0.029 |
vows | +0.029 |
Neg logit contributions | |
alone | -0.009 |
afloat | -0.009 |
tank | -0.007 |
| | -0.007 |
wreck | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
o | +0.606 |
alone | +0.543 |
forth | +0.487 |
tank | +0.477 |
my | +0.476 |
Neg logit contributions | |
Her | -0.849 |
vows | -0.849 |
ves | -0.847 |
brist | -0.839 |
growth | -0.787 |
Token | there |
Token ID | 612 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
alone | +0.066 |
o | +0.058 |
Tim | +0.054 |
mad | +0.052 |
tired | +0.051 |
Neg logit contributions | |
growth | -0.116 |
brist | -0.101 |
vows | -0.098 |
owers | -0.098 |
ribbon | -0.096 |
Token | was |
Token ID | 373 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
o | +0.168 |
alone | +0.161 |
my | +0.147 |
Tim | +0.121 |
boy | +0.121 |
Neg logit contributions | |
growth | -0.475 |
brist | -0.453 |
Her | -0.439 |
vows | -0.427 |
quet | -0.416 |
Token | going |
Token ID | 1016 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
ves | +0.110 |
growth | +0.108 |
brist | +0.105 |
vows | +0.104 |
Her | +0.102 |
Neg logit contributions | |
o | -0.079 |
alone | -0.070 |
my | -0.068 |
Tim | -0.060 |
late | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
o | +0.082 |
alone | +0.075 |
tank | +0.070 |
polar | +0.070 |
afloat | +0.070 |
Neg logit contributions | |
Her | -0.072 |
ves | -0.072 |
vows | -0.071 |
brist | -0.069 |
blonde | -0.062 |
Token | you |
Token ID | 345 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
o | +0.283 |
alone | +0.259 |
afloat | +0.247 |
forth | +0.230 |
polar | +0.229 |
Neg logit contributions | |
Her | -0.401 |
ves | -0.389 |
vows | -0.373 |
brist | -0.360 |
Her | -0.348 |
Token | let |
Token ID | 1309 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
o | +0.437 |
alone | +0.405 |
forth | +0.369 |
tank | +0.363 |
afloat | +0.358 |
Neg logit contributions | |
Her | -0.436 |
ves | -0.435 |
vows | -0.432 |
brist | -0.424 |
blonde | -0.384 |
Token | her |
Token ID | 607 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
o | +0.173 |
alone | +0.160 |
afloat | +0.152 |
tank | +0.139 |
forth | +0.138 |
Neg logit contributions | |
Her | -0.239 |
ves | -0.237 |
vows | -0.234 |
brist | -0.223 |
Her | -0.211 |
Token | hold |
Token ID | 1745 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
vows | +0.418 |
Her | +0.417 |
ves | +0.417 |
brist | +0.392 |
blush | +0.375 |
Neg logit contributions | |
o | -0.385 |
alone | -0.353 |
forth | -0.327 |
afloat | -0.326 |
| | -0.319 |
Token | your |
Token ID | 534 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Her | +0.049 |
ves | +0.048 |
brist | +0.047 |
vows | +0.047 |
ribbon | +0.045 |
Neg logit contributions | |
o | -0.029 |
alone | -0.027 |
afloat | -0.026 |
forth | -0.025 |
wreck | -0.024 |
Token | bear |
Token ID | 6842 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
o | +0.398 |
alone | +0.336 |
| | +0.325 |
afloat | +0.314 |
forth | +0.313 |
Neg logit contributions | |
vows | -0.507 |
brist | -0.501 |
ves | -0.495 |
ribbon | -0.489 |
Her | -0.471 |
Token | for |
Token ID | 329 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
o | +0.505 |
polar | +0.454 |
alone | +0.453 |
| | +0.450 |
forth | +0.442 |
Neg logit contributions | |
Her | -0.617 |
ves | -0.609 |
vows | -0.575 |
brist | -0.568 |
ribbon | -0.560 |
Token | a |
Token ID | 257 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
o | +0.265 |
alone | +0.248 |
forth | +0.220 |
tank | +0.213 |
polar | +0.207 |
Neg logit contributions | |
vows | -0.405 |
ves | -0.402 |
Her | -0.396 |
brist | -0.392 |
blonde | -0.366 |
Token | little |
Token ID | 1310 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
vows | +0.136 |
ves | +0.135 |
Her | +0.131 |
brist | +0.130 |
ribbon | +0.128 |
Neg logit contributions | |
o | -0.177 |
alone | -0.165 |
forth | -0.159 |
afloat | -0.149 |
my | -0.143 |
Token | while |
Token ID | 981 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
brist | +0.038 |
ribbon | +0.037 |
vows | +0.036 |
Her | +0.035 |
ves | +0.035 |
Neg logit contributions | |
o | -0.052 |
alone | -0.046 |
| | -0.044 |
forth | -0.043 |
afloat | -0.043 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ves | +0.089 |
Her | +0.089 |
vows | +0.088 |
brist | +0.086 |
blonde | +0.081 |
Neg logit contributions | |
o | -0.053 |
alone | -0.047 |
forth | -0.042 |
afloat | -0.041 |
tank | -0.041 |
Token | stranger |
Token ID | 16195 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
o | +0.166 |
alone | +0.162 |
forth | +0.144 |
tank | +0.143 |
afloat | +0.137 |
Neg logit contributions | |
ves | -0.185 |
Her | -0.183 |
vows | -0.182 |
brist | -0.180 |
growth | -0.163 |
Token | 's |
Token ID | 338 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
ves | +0.054 |
vows | +0.054 |
Her | +0.053 |
brist | +0.052 |
blonde | +0.048 |
Neg logit contributions | |
o | -0.051 |
alone | -0.048 |
forth | -0.043 |
tank | -0.043 |
afloat | -0.043 |
Token | car |
Token ID | 1097 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
o | +0.093 |
alone | +0.088 |
forth | +0.079 |
tank | +0.079 |
afloat | +0.075 |
Neg logit contributions | |
Her | -0.107 |
ves | -0.107 |
vows | -0.105 |
brist | -0.104 |
growth | -0.096 |
Token | was |
Token ID | 373 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
o | +0.201 |
alone | +0.188 |
forth | +0.168 |
tank | +0.167 |
my | +0.162 |
Neg logit contributions | |
Her | -0.227 |
vows | -0.225 |
ves | -0.225 |
brist | -0.223 |
growth | -0.205 |
Token | even |
Token ID | 772 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
ves | +0.067 |
Her | +0.066 |
brist | +0.064 |
vows | +0.064 |
blonde | +0.062 |
Neg logit contributions | |
o | -0.040 |
forth | -0.034 |
| | -0.032 |
alone | -0.032 |
tank | -0.032 |
Token | faster |
Token ID | 5443 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
ves | +0.077 |
Her | +0.076 |
brist | +0.074 |
ribbon | +0.070 |
blonde | +0.070 |
Neg logit contributions | |
o | -0.078 |
| | -0.071 |
tank | -0.063 |
polar | -0.060 |
alone | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
o | +0.570 |
alone | +0.519 |
forth | +0.479 |
tank | +0.479 |
polar | +0.468 |
Neg logit contributions | |
ves | -0.579 |
Her | -0.568 |
vows | -0.567 |
brist | -0.558 |
blonde | -0.507 |
Token | The |
Token ID | 383 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
Her | +0.062 |
ves | +0.060 |
Her | +0.059 |
brist | +0.059 |
vows | +0.056 |
Neg logit contributions | |
o | -0.037 |
forth | -0.036 |
alone | -0.036 |
afloat | -0.033 |
polar | -0.031 |
Token | stranger |
Token ID | 16195 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
ves | +0.017 |
vows | +0.017 |
Her | +0.017 |
brist | +0.016 |
blonde | +0.015 |
Neg logit contributions | |
o | -0.017 |
alone | -0.016 |
forth | -0.014 |
tank | -0.014 |
afloat | -0.014 |
Token | won |
Token ID | 1839 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ves | +0.061 |
vows | +0.060 |
Her | +0.060 |
brist | +0.058 |
blonde | +0.054 |
Neg logit contributions | |
o | -0.056 |
alone | -0.052 |
forth | -0.047 |
afloat | -0.046 |
tank | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
o | +0.242 |
alone | +0.226 |
forth | +0.199 |
tank | +0.197 |
afloat | +0.193 |
Neg logit contributions | |
vows | -0.292 |
Her | -0.288 |
ves | -0.287 |
brist | -0.284 |
blonde | -0.265 |
Token | of |
Token ID | 286 |
Feature activation | -6.28e-03 |
Pos logit contributions | |
Her | +0.120 |
ves | +0.120 |
vows | +0.117 |
brist | +0.116 |
growth | +0.105 |
Neg logit contributions | |
o | -0.135 |
alone | -0.126 |
forth | -0.117 |
tank | -0.116 |
afloat | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Her | +0.011 |
growth | +0.011 |
brist | +0.011 |
ves | +0.010 |
ribbon | +0.010 |
Neg logit contributions | |
o | -0.012 |
afloat | -0.010 |
forth | -0.010 |
alone | -0.010 |
ny | -0.009 |
Token | cliff |
Token ID | 19516 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
o | +0.257 |
forth | +0.223 |
alone | +0.223 |
afloat | +0.215 |
| | +0.208 |
Neg logit contributions | |
brist | -0.243 |
vows | -0.238 |
ves | -0.236 |
Her | -0.235 |
ork | -0.226 |
Token | and |
Token ID | 290 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
o | +0.034 |
alone | +0.030 |
polar | +0.030 |
forth | +0.029 |
afloat | +0.029 |
Neg logit contributions | |
ves | -0.031 |
Her | -0.030 |
vows | -0.029 |
brist | -0.028 |
ork | -0.026 |
Token | looked |
Token ID | 3114 |
Feature activation | +5.07e-03 |
Pos logit contributions | |
o | +0.080 |
alone | +0.073 |
afloat | +0.071 |
tank | +0.068 |
polar | +0.067 |
Neg logit contributions | |
vows | -0.072 |
ves | -0.072 |
Her | -0.071 |
brist | -0.069 |
blush | -0.064 |
Token | down |
Token ID | 866 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
o | +0.009 |
| | +0.008 |
polar | +0.007 |
forth | +0.007 |
wreck | +0.007 |
Neg logit contributions | |
vows | -0.010 |
Her | -0.009 |
brist | -0.009 |
ves | -0.009 |
blush | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
o | +0.588 |
alone | +0.577 |
forth | +0.490 |
tank | +0.489 |
afloat | +0.475 |
Neg logit contributions | |
ves | -0.776 |
vows | -0.769 |
Her | -0.755 |
brist | -0.754 |
growth | -0.702 |
Token | He |
Token ID | 679 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
o | +0.012 |
alone | +0.011 |
forth | +0.010 |
tank | +0.009 |
afloat | +0.009 |
Neg logit contributions | |
ves | -0.026 |
Her | -0.026 |
vows | -0.026 |
brist | -0.025 |
blonde | -0.024 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
o | +0.446 |
alone | +0.420 |
forth | +0.376 |
afloat | +0.375 |
tank | +0.372 |
Neg logit contributions | |
ves | -0.605 |
Her | -0.595 |
vows | -0.593 |
brist | -0.583 |
blonde | -0.541 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
o | +0.258 |
alone | +0.243 |
tank | +0.218 |
forth | +0.218 |
my | +0.212 |
Neg logit contributions | |
ves | -0.246 |
vows | -0.245 |
Her | -0.243 |
brist | -0.238 |
blonde | -0.216 |
Token | in |
Token ID | 287 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
o | +0.283 |
alone | +0.258 |
forth | +0.239 |
tank | +0.238 |
afloat | +0.235 |
Neg logit contributions | |
Her | -0.340 |
ves | -0.336 |
brist | -0.324 |
vows | -0.323 |
blonde | -0.300 |
Token | in |
Token ID | 287 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Her | +0.142 |
vows | +0.141 |
ves | +0.140 |
brist | +0.137 |
growth | +0.127 |
Neg logit contributions | |
o | -0.109 |
alone | -0.104 |
forth | -0.092 |
tank | -0.090 |
my | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
o | +0.150 |
alone | +0.137 |
forth | +0.121 |
tank | +0.119 |
afloat | +0.115 |
Neg logit contributions | |
ves | -0.233 |
vows | -0.232 |
Her | -0.231 |
brist | -0.227 |
blonde | -0.211 |
Token | sky |
Token ID | 6766 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
o | +0.152 |
alone | +0.144 |
forth | +0.132 |
tank | +0.130 |
my | +0.128 |
Neg logit contributions | |
ves | -0.120 |
vows | -0.119 |
Her | -0.119 |
brist | -0.115 |
blonde | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
ves | +0.333 |
vows | +0.332 |
Her | +0.332 |
brist | +0.324 |
growth | +0.299 |
Neg logit contributions | |
o | -0.291 |
alone | -0.271 |
forth | -0.240 |
tank | -0.238 |
my | -0.236 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Her | +0.113 |
ves | +0.113 |
vows | +0.112 |
brist | +0.111 |
blonde | +0.105 |
Neg logit contributions | |
o | -0.030 |
alone | -0.026 |
forth | -0.020 |
tank | -0.019 |
afloat | -0.018 |
Token | my |
Token ID | 1820 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
afloat | +0.259 |
alone | +0.225 |
polar | +0.199 |
tank | +0.196 |
wreck | +0.186 |
Neg logit contributions | |
Her | -0.761 |
brist | -0.756 |
Her | -0.708 |
vows | -0.699 |
blush | -0.690 |
Token | didn |
Token ID | 1422 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
o | +0.648 |
alone | +0.574 |
my | +0.525 |
forth | +0.522 |
tank | +0.505 |
Neg logit contributions | |
vows | -0.827 |
ves | -0.826 |
Her | -0.804 |
brist | -0.801 |
growth | -0.778 |
Token | 't |
Token ID | 470 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
o | +0.048 |
alone | +0.044 |
tank | +0.040 |
wreck | +0.040 |
| | +0.039 |
Neg logit contributions | |
vows | -0.050 |
brist | -0.048 |
blonde | -0.047 |
ves | -0.046 |
Her | -0.046 |
Token | really |
Token ID | 1107 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
Her | +0.293 |
ves | +0.286 |
brist | +0.285 |
vows | +0.284 |
blonde | +0.260 |
Neg logit contributions | |
o | -0.242 |
alone | -0.221 |
forth | -0.206 |
tank | -0.203 |
afloat | -0.198 |
Token | understand |
Token ID | 1833 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
o | +0.093 |
alone | +0.084 |
forth | +0.080 |
tank | +0.079 |
afloat | +0.077 |
Neg logit contributions | |
ves | -0.079 |
Her | -0.078 |
vows | -0.077 |
brist | -0.076 |
blonde | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
ves | +0.390 |
vows | +0.390 |
Her | +0.387 |
brist | +0.380 |
growth | +0.350 |
Neg logit contributions | |
o | -0.321 |
alone | -0.299 |
forth | -0.268 |
tank | -0.264 |
my | -0.257 |
Token | Look |
Token ID | 8567 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
vows | +0.140 |
ves | +0.140 |
brist | +0.134 |
Her | +0.131 |
ork | +0.126 |
Neg logit contributions | |
o | -0.105 |
alone | -0.092 |
forth | -0.086 |
my | -0.084 |
tank | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ves | +0.061 |
vows | +0.061 |
Her | +0.060 |
brist | +0.058 |
blush | +0.052 |
Neg logit contributions | |
o | -0.070 |
alone | -0.066 |
afloat | -0.061 |
tank | -0.061 |
polar | -0.060 |
Token | Ben |
Token ID | 3932 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
ves | +0.083 |
Her | +0.083 |
vows | +0.083 |
brist | +0.081 |
blonde | +0.075 |
Neg logit contributions | |
o | -0.066 |
alone | -0.061 |
forth | -0.054 |
tank | -0.054 |
afloat | -0.052 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
alone | +0.175 |
| | +0.174 |
o | +0.173 |
afloat | +0.168 |
forth | +0.166 |
Neg logit contributions | |
ves | -0.114 |
brist | -0.109 |
Her | -0.104 |
vows | -0.102 |
ribbon | -0.096 |
Token | Mia |
Token ID | 32189 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
o | +0.161 |
alone | +0.157 |
tank | +0.127 |
polar | +0.120 |
boy | +0.115 |
Neg logit contributions | |
brist | -0.343 |
vows | -0.342 |
ves | -0.339 |
Her | -0.333 |
growth | -0.317 |
Token | says |
Token ID | 1139 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
o | +0.061 |
alone | +0.055 |
afloat | +0.053 |
forth | +0.053 |
tank | +0.051 |
Neg logit contributions | |
Her | -0.077 |
ves | -0.076 |
brist | -0.076 |
vows | -0.075 |
Her | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
o | +0.158 |
alone | +0.150 |
forth | +0.129 |
tank | +0.129 |
afloat | +0.124 |
Neg logit contributions | |
vows | -0.196 |
ves | -0.195 |
brist | -0.191 |
Her | -0.191 |
growth | -0.181 |
Token | " |
Token ID | 366 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
vows | +0.091 |
ves | +0.089 |
brist | +0.080 |
ork | +0.075 |
ribbon | +0.075 |
Neg logit contributions | |
o | -0.086 |
alone | -0.082 |
tank | -0.072 |
down | -0.067 |
boy | -0.066 |
Token | The |
Token ID | 464 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
vows | +0.211 |
ves | +0.208 |
brist | +0.201 |
Her | +0.199 |
blonde | +0.183 |
Neg logit contributions | |
o | -0.218 |
alone | -0.203 |
tank | -0.180 |
forth | -0.180 |
my | -0.177 |
Token | tree |
Token ID | 5509 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
ves | +0.276 |
vows | +0.275 |
Her | +0.270 |
brist | +0.256 |
growth | +0.250 |
Neg logit contributions | |
o | -0.250 |
alone | -0.247 |
forth | -0.219 |
my | -0.214 |
tank | -0.213 |
Token | has |
Token ID | 468 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ves | +0.088 |
vows | +0.087 |
Her | +0.086 |
brist | +0.085 |
blonde | +0.078 |
Neg logit contributions | |
o | -0.070 |
alone | -0.064 |
forth | -0.058 |
tank | -0.057 |
afloat | -0.057 |
Token | une |
Token ID | 1726 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ves | +0.151 |
vows | +0.148 |
Her | +0.147 |
blonde | +0.131 |
ribbon | +0.123 |
Neg logit contributions | |
o | -0.195 |
my | -0.157 |
alone | -0.152 |
tank | -0.145 |
polar | -0.143 |
Token | was |
Token ID | 373 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Her | +0.442 |
vows | +0.442 |
brist | +0.436 |
ves | +0.431 |
growth | +0.401 |
Neg logit contributions | |
o | -0.386 |
alone | -0.352 |
forth | -0.316 |
tank | -0.314 |
my | -0.309 |
Token | excited |
Token ID | 6568 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
Her | +0.057 |
ves | +0.056 |
vows | +0.055 |
brist | +0.055 |
blonde | +0.053 |
Neg logit contributions | |
o | -0.044 |
alone | -0.038 |
forth | -0.037 |
tank | -0.036 |
| | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
o | +0.117 |
alone | +0.109 |
forth | +0.098 |
my | +0.095 |
tank | +0.094 |
Neg logit contributions | |
ves | -0.145 |
vows | -0.144 |
Her | -0.143 |
brist | -0.141 |
growth | -0.131 |
Token | It |
Token ID | 632 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Her | +0.036 |
ves | +0.035 |
vows | +0.035 |
brist | +0.035 |
growth | +0.032 |
Neg logit contributions | |
o | -0.038 |
alone | -0.036 |
forth | -0.034 |
afloat | -0.032 |
polar | -0.032 |
Token | had |
Token ID | 550 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
ves | +0.302 |
vows | +0.300 |
Her | +0.300 |
brist | +0.294 |
blonde | +0.268 |
Neg logit contributions | |
o | -0.292 |
alone | -0.272 |
forth | -0.248 |
tank | -0.244 |
afloat | -0.240 |
Token | never |
Token ID | 1239 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
o | +0.112 |
alone | +0.110 |
my | +0.092 |
polar | +0.091 |
tank | +0.090 |
Neg logit contributions | |
brist | -0.149 |
Her | -0.148 |
ves | -0.145 |
vows | -0.141 |
blush | -0.137 |
Token | been |
Token ID | 587 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ves | +0.083 |
Her | +0.083 |
vows | +0.082 |
brist | +0.081 |
blonde | +0.075 |
Neg logit contributions | |
o | -0.072 |
alone | -0.066 |
tank | -0.061 |
forth | -0.061 |
afloat | -0.059 |
Token | on |
Token ID | 319 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ves | +0.034 |
vows | +0.034 |
Her | +0.034 |
brist | +0.033 |
blonde | +0.031 |
Neg logit contributions | |
o | -0.029 |
alone | -0.027 |
forth | -0.025 |
tank | -0.024 |
afloat | -0.024 |
Token | an |
Token ID | 281 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
alone | +0.154 |
o | +0.145 |
tank | +0.126 |
polar | +0.122 |
wreck | +0.119 |
Neg logit contributions | |
Her | -0.238 |
ves | -0.235 |
vows | -0.231 |
brist | -0.228 |
blush | -0.212 |
Token | adventure |
Token ID | 8855 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ves | +0.353 |
Her | +0.352 |
vows | +0.351 |
brist | +0.346 |
blonde | +0.316 |
Neg logit contributions | |
o | -0.314 |
alone | -0.288 |
forth | -0.262 |
tank | -0.259 |
afloat | -0.253 |
Token | ily |
Token ID | 813 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
o | +0.100 |
alone | +0.094 |
my | +0.087 |
forth | +0.085 |
tank | +0.084 |
Neg logit contributions | |
vows | -0.064 |
ves | -0.064 |
Her | -0.061 |
brist | -0.061 |
blonde | -0.055 |
Token | stopped |
Token ID | 5025 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
ves | +0.298 |
Her | +0.290 |
vows | +0.286 |
brist | +0.279 |
growth | +0.269 |
Neg logit contributions | |
o | -0.236 |
alone | -0.209 |
my | -0.199 |
forth | -0.189 |
tank | -0.187 |
Token | weeping |
Token ID | 45705 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Her | +0.050 |
brist | +0.048 |
vows | +0.046 |
ves | +0.045 |
Her | +0.044 |
Neg logit contributions | |
o | -0.040 |
alone | -0.035 |
afloat | -0.033 |
tank | -0.033 |
forth | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
alone | +0.235 |
o | +0.231 |
forth | +0.205 |
tank | +0.193 |
my | +0.191 |
Neg logit contributions | |
ves | -0.335 |
vows | -0.330 |
Her | -0.320 |
brist | -0.316 |
growth | -0.299 |
Token | waited |
Token ID | 13488 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
o | +0.065 |
alone | +0.061 |
forth | +0.055 |
tank | +0.053 |
my | +0.052 |
Neg logit contributions | |
ves | -0.082 |
vows | -0.080 |
Her | -0.080 |
brist | -0.079 |
growth | -0.073 |
Token | for |
Token ID | 329 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ves | +0.056 |
vows | +0.055 |
Her | +0.054 |
brist | +0.053 |
growth | +0.053 |
Neg logit contributions | |
alone | -0.032 |
o | -0.029 |
tank | -0.025 |
forth | -0.024 |
afloat | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
alone | +0.198 |
o | +0.198 |
forth | +0.177 |
tank | +0.173 |
polar | +0.168 |
Neg logit contributions | |
vows | -0.428 |
ves | -0.422 |
Her | -0.409 |
brist | -0.396 |
owers | -0.382 |
Token | gum |
Token ID | 27142 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
o | +0.264 |
alone | +0.246 |
forth | +0.226 |
tank | +0.222 |
afloat | +0.220 |
Neg logit contributions | |
ves | -0.203 |
vows | -0.201 |
Her | -0.201 |
brist | -0.200 |
blonde | -0.178 |
Token | to |
Token ID | 284 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
brist | +0.062 |
ves | +0.062 |
Her | +0.061 |
vows | +0.061 |
growth | +0.058 |
Neg logit contributions | |
o | -0.045 |
alone | -0.044 |
tank | -0.036 |
my | -0.036 |
forth | -0.035 |
Token | come |
Token ID | 1282 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ves | +0.051 |
vows | +0.051 |
Her | +0.051 |
brist | +0.050 |
blonde | +0.045 |
Neg logit contributions | |
o | -0.048 |
alone | -0.046 |
forth | -0.042 |
tank | -0.041 |
afloat | -0.040 |
Token | out |
Token ID | 503 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
o | +0.025 |
alone | +0.023 |
forth | +0.021 |
tank | +0.020 |
wreck | +0.020 |
Neg logit contributions | |
Her | -0.038 |
vows | -0.037 |
ves | -0.037 |
brist | -0.037 |
blonde | -0.034 |
Token | record |
Token ID | 1700 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
o | +0.065 |
alone | +0.065 |
tank | +0.055 |
forth | +0.054 |
my | +0.053 |
Neg logit contributions | |
vows | -0.096 |
ves | -0.094 |
brist | -0.093 |
Her | -0.092 |
growth | -0.086 |
Token | a |
Token ID | 257 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
o | +0.030 |
alone | +0.030 |
forth | +0.026 |
tank | +0.025 |
my | +0.025 |
Neg logit contributions | |
vows | -0.038 |
Her | -0.037 |
ves | -0.037 |
brist | -0.037 |
growth | -0.035 |
Token | song |
Token ID | 3496 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
ves | +0.096 |
vows | +0.095 |
Her | +0.094 |
brist | +0.093 |
blonde | +0.084 |
Neg logit contributions | |
o | -0.113 |
alone | -0.105 |
forth | -0.097 |
tank | -0.095 |
afloat | -0.094 |
Token | together |
Token ID | 1978 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
brist | +0.172 |
Her | +0.171 |
vows | +0.171 |
ves | +0.170 |
growth | +0.164 |
Neg logit contributions | |
o | -0.123 |
alone | -0.118 |
forth | -0.098 |
tank | -0.098 |
my | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
alone | +0.283 |
o | +0.280 |
forth | +0.237 |
tank | +0.232 |
my | +0.229 |
Neg logit contributions | |
Her | -0.422 |
brist | -0.419 |
ves | -0.416 |
vows | -0.410 |
growth | -0.390 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
o | +0.061 |
alone | +0.058 |
forth | +0.054 |
afloat | +0.052 |
tank | +0.052 |
Neg logit contributions | |
Her | -0.061 |
ves | -0.060 |
vows | -0.060 |
brist | -0.059 |
blonde | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
o | +0.225 |
alone | +0.217 |
forth | +0.210 |
afloat | +0.198 |
tank | +0.196 |
Neg logit contributions | |
Her | -0.289 |
ves | -0.284 |
vows | -0.265 |
brist | -0.263 |
growth | -0.248 |
Token | The |
Token ID | 464 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
o | +0.295 |
alone | +0.276 |
forth | +0.254 |
tank | +0.251 |
my | +0.248 |
Neg logit contributions | |
vows | -0.214 |
ves | -0.213 |
brist | -0.208 |
Her | -0.208 |
blonde | -0.185 |
Token | man |
Token ID | 582 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ves | +0.127 |
Her | +0.127 |
vows | +0.126 |
brist | +0.123 |
growth | +0.113 |
Neg logit contributions | |
o | -0.122 |
alone | -0.115 |
forth | -0.105 |
tank | -0.104 |
my | -0.100 |
Token | was |
Token ID | 373 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
o | +0.203 |
alone | +0.188 |
forth | +0.169 |
tank | +0.168 |
my | +0.164 |
Neg logit contributions | |
Her | -0.231 |
ves | -0.231 |
vows | -0.229 |
brist | -0.227 |
growth | -0.208 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
o | +0.032 |
forth | +0.027 |
alone | +0.027 |
tank | +0.026 |
| | +0.025 |
Neg logit contributions | |
Her | -0.041 |
vows | -0.040 |
ves | -0.039 |
brist | -0.039 |
blonde | -0.037 |
Token | bar |
Token ID | 5657 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
o | +0.082 |
alone | +0.075 |
forth | +0.067 |
tank | +0.067 |
my | +0.065 |
Neg logit contributions | |
vows | -0.097 |
ves | -0.096 |
Her | -0.096 |
brist | -0.094 |
blonde | -0.087 |
Token | row |
Token ID | 808 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
o | +0.378 |
alone | +0.356 |
forth | +0.323 |
tank | +0.318 |
afloat | +0.311 |
Neg logit contributions | |
ves | -0.393 |
Her | -0.388 |
vows | -0.384 |
brist | -0.379 |
growth | -0.344 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
o | +0.065 |
alone | +0.062 |
tank | +0.054 |
afloat | +0.053 |
forth | +0.052 |
Neg logit contributions | |
Her | -0.080 |
vows | -0.080 |
ves | -0.078 |
brist | -0.078 |
growth | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
o | +0.003 |
alone | +0.003 |
forth | +0.003 |
afloat | +0.002 |
tank | +0.002 |
Neg logit contributions | |
Her | -0.003 |
vows | -0.003 |
ves | -0.003 |
brist | -0.003 |
blonde | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
o | +0.176 |
alone | +0.171 |
forth | +0.163 |
tank | +0.151 |
afloat | +0.150 |
Neg logit contributions | |
ves | -0.232 |
Her | -0.231 |
vows | -0.219 |
brist | -0.215 |
ork | -0.202 |
Token | John |
Token ID | 7554 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
o | +0.234 |
alone | +0.219 |
forth | +0.201 |
tank | +0.200 |
my | +0.196 |
Neg logit contributions | |
ves | -0.172 |
vows | -0.172 |
Her | -0.169 |
brist | -0.168 |
blonde | -0.149 |
Token | : |
Token ID | 25 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
o | +0.192 |
alone | +0.172 |
forth | +0.157 |
my | +0.155 |
tank | +0.154 |
Neg logit contributions | |
Her | -0.213 |
ves | -0.212 |
vows | -0.212 |
brist | -0.207 |
growth | -0.190 |
Token | " |
Token ID | 366 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
Her | +0.300 |
vows | +0.298 |
ves | +0.295 |
brist | +0.291 |
blonde | +0.266 |
Neg logit contributions | |
o | -0.429 |
alone | -0.403 |
forth | -0.375 |
afloat | -0.372 |
tank | -0.368 |
Token | What |
Token ID | 2061 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
Her | +0.122 |
brist | +0.119 |
vows | +0.118 |
ves | +0.118 |
blonde | +0.107 |
Neg logit contributions | |
o | -0.154 |
alone | -0.148 |
tank | -0.135 |
forth | -0.134 |
afloat | -0.131 |
Token | we |
Token ID | 356 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
o | +0.051 |
alone | +0.045 |
tank | +0.041 |
my | +0.041 |
wreck | +0.038 |
Neg logit contributions | |
Her | -0.064 |
brist | -0.062 |
vows | -0.062 |
ves | -0.061 |
growth | -0.058 |
Token | doing |
Token ID | 1804 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
o | +0.281 |
alone | +0.244 |
polar | +0.233 |
| | +0.227 |
afloat | +0.223 |
Neg logit contributions | |
brist | -0.258 |
vows | -0.248 |
Her | -0.240 |
ves | -0.239 |
ribbon | -0.234 |
Token | it |
Token ID | 340 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
o | +0.122 |
alone | +0.116 |
forth | +0.111 |
my | +0.104 |
tank | +0.102 |
Neg logit contributions | |
Her | -0.131 |
ves | -0.130 |
vows | -0.127 |
brist | -0.123 |
growth | -0.120 |
Token | broke |
Token ID | 6265 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
o | +0.033 |
alone | +0.032 |
my | +0.028 |
forth | +0.028 |
tank | +0.026 |
Neg logit contributions | |
Her | -0.048 |
growth | -0.046 |
ves | -0.046 |
vows | -0.045 |
brist | -0.044 |
Token | into |
Token ID | 656 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
o | +0.072 |
alone | +0.067 |
forth | +0.060 |
my | +0.059 |
tank | +0.057 |
Neg logit contributions | |
ves | -0.094 |
vows | -0.094 |
Her | -0.092 |
brist | -0.089 |
growth | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
alone | +0.247 |
o | +0.232 |
tank | +0.204 |
my | +0.201 |
wreck | +0.198 |
Neg logit contributions | |
vows | -0.315 |
ves | -0.305 |
Her | -0.284 |
owers | -0.275 |
brist | -0.267 |
Token | million |
Token ID | 1510 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ves | +0.150 |
Her | +0.149 |
vows | +0.149 |
brist | +0.147 |
blonde | +0.134 |
Neg logit contributions | |
o | -0.122 |
alone | -0.112 |
forth | -0.101 |
tank | -0.099 |
afloat | -0.097 |
Token | pieces |
Token ID | 5207 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
alone | +0.208 |
o | +0.202 |
forth | +0.181 |
wreck | +0.180 |
tank | +0.178 |
Neg logit contributions | |
vows | -0.226 |
ves | -0.224 |
Her | -0.224 |
brist | -0.202 |
growth | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
vows | +0.102 |
Her | +0.101 |
ves | +0.099 |
brist | +0.099 |
growth | +0.093 |
Neg logit contributions | |
o | -0.077 |
alone | -0.076 |
tank | -0.063 |
forth | -0.062 |
my | -0.062 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
o | +0.041 |
alone | +0.038 |
forth | +0.035 |
tank | +0.034 |
afloat | +0.034 |
Neg logit contributions | |
Her | -0.044 |
ves | -0.043 |
vows | -0.043 |
brist | -0.042 |
blonde | -0.039 |
Token | 's |
Token ID | 338 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
o | +0.312 |
alone | +0.287 |
my | +0.261 |
forth | +0.255 |
tank | +0.249 |
Neg logit contributions | |
ves | -0.396 |
vows | -0.389 |
Her | -0.385 |
brist | -0.372 |
growth | -0.361 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
o | +0.175 |
alone | +0.173 |
tank | +0.158 |
forth | +0.151 |
wreck | +0.150 |
Neg logit contributions | |
Her | -0.195 |
ves | -0.193 |
vows | -0.185 |
brist | -0.181 |
growth | -0.181 |
Token | was |
Token ID | 373 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ves | +0.084 |
vows | +0.083 |
Her | +0.083 |
brist | +0.081 |
growth | +0.078 |
Neg logit contributions | |
o | -0.062 |
alone | -0.056 |
my | -0.052 |
forth | -0.051 |
tank | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
alone | +0.319 |
o | +0.317 |
tank | +0.265 |
afloat | +0.263 |
forth | +0.263 |
Neg logit contributions | |
vows | -0.434 |
ves | -0.433 |
Her | -0.426 |
brist | -0.420 |
growth | -0.398 |
Token | From |
Token ID | 3574 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
ves | +0.084 |
Her | +0.084 |
vows | +0.083 |
brist | +0.082 |
blonde | +0.074 |
Neg logit contributions | |
o | -0.087 |
alone | -0.081 |
forth | -0.074 |
tank | -0.073 |
afloat | -0.072 |
Token | then |
Token ID | 788 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
ves | +0.077 |
Her | +0.077 |
brist | +0.073 |
vows | +0.071 |
ribbon | +0.065 |
Neg logit contributions | |
o | -0.144 |
| | -0.130 |
alone | -0.127 |
tank | -0.124 |
polar | -0.124 |
Token | on |
Token ID | 319 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
ves | +0.105 |
Her | +0.104 |
vows | +0.103 |
brist | +0.101 |
blonde | +0.093 |
Neg logit contributions | |
o | -0.066 |
alone | -0.060 |
tank | -0.053 |
forth | -0.052 |
afloat | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
o | +0.125 |
alone | +0.120 |
forth | +0.108 |
tank | +0.105 |
my | +0.099 |
Neg logit contributions | |
vows | -0.160 |
Her | -0.158 |
brist | -0.158 |
ves | -0.156 |
growth | -0.146 |
Token | it |
Token ID | 340 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
ves | +0.107 |
Her | +0.106 |
vows | +0.103 |
brist | +0.102 |
blonde | +0.095 |
Neg logit contributions | |
o | -0.090 |
alone | -0.078 |
polar | -0.072 |
tank | -0.072 |
afloat | -0.071 |
Token | was |
Token ID | 373 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
ves | +0.119 |
vows | +0.116 |
Her | +0.115 |
brist | +0.112 |
growth | +0.101 |
Neg logit contributions | |
o | -0.131 |
alone | -0.121 |
afloat | -0.114 |
forth | -0.114 |
tank | -0.112 |
Token | much |
Token ID | 881 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
ves | +0.109 |
Her | +0.108 |
vows | +0.107 |
brist | +0.105 |
blonde | +0.096 |
Neg logit contributions | |
o | -0.102 |
alone | -0.095 |
forth | -0.087 |
tank | -0.086 |
afloat | -0.084 |
Token | quieter |
Token ID | 43880 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
Her | +0.178 |
ves | +0.178 |
brist | +0.176 |
vows | +0.172 |
blonde | +0.157 |
Neg logit contributions | |
o | -0.192 |
alone | -0.170 |
| | -0.159 |
tank | -0.156 |
forth | -0.153 |
Token | and |
Token ID | 290 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
o | +0.084 |
alone | +0.077 |
forth | +0.070 |
tank | +0.069 |
afloat | +0.067 |
Neg logit contributions | |
ves | -0.101 |
Her | -0.100 |
vows | -0.100 |
brist | -0.098 |
blonde | -0.090 |
Token | people |
Token ID | 661 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
ves | +0.048 |
vows | +0.047 |
Her | +0.046 |
brist | +0.045 |
blonde | +0.041 |
Neg logit contributions | |
o | -0.048 |
alone | -0.043 |
tank | -0.041 |
afloat | -0.040 |
polar | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
o | +0.291 |
alone | +0.273 |
tank | +0.247 |
my | +0.244 |
forth | +0.243 |
Neg logit contributions | |
vows | -0.228 |
ves | -0.225 |
brist | -0.221 |
Her | -0.219 |
blonde | -0.195 |
Token | time |
Token ID | 640 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
ves | +0.289 |
Her | +0.284 |
vows | +0.280 |
brist | +0.276 |
blonde | +0.253 |
Neg logit contributions | |
o | -0.329 |
alone | -0.312 |
forth | -0.292 |
tank | -0.284 |
afloat | -0.281 |
Token | , |
Token ID | 11 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
ves | +0.096 |
Her | +0.095 |
vows | +0.083 |
brist | +0.081 |
Her | +0.081 |
Neg logit contributions | |
o | -0.154 |
forth | -0.152 |
alone | -0.149 |
afloat | -0.146 |
polar | -0.143 |
Token | there |
Token ID | 612 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Her | +0.111 |
ves | +0.104 |
Her | +0.096 |
blonde | +0.095 |
brist | +0.092 |
Neg logit contributions | |
o | -0.113 |
forth | -0.106 |
polar | -0.106 |
ior | -0.103 |
afloat | -0.102 |
Token | was |
Token ID | 373 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
o | +0.310 |
alone | +0.298 |
forth | +0.287 |
afloat | +0.281 |
tank | +0.269 |
Neg logit contributions | |
ves | -0.239 |
Her | -0.235 |
vows | -0.227 |
brist | -0.221 |
growth | -0.202 |
Token | a |
Token ID | 257 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ves | +0.112 |
vows | +0.112 |
Her | +0.110 |
brist | +0.108 |
blonde | +0.096 |
Neg logit contributions | |
o | -0.152 |
alone | -0.143 |
tank | -0.130 |
forth | -0.130 |
my | -0.127 |
Token | spot |
Token ID | 4136 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
Her | +0.229 |
brist | +0.223 |
ves | +0.221 |
vows | +0.220 |
ribbon | +0.205 |
Neg logit contributions | |
o | -0.384 |
alone | -0.352 |
afloat | -0.347 |
| | -0.345 |
forth | -0.342 |
Token | . |
Token ID | 13 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
ves | +0.077 |
Her | +0.076 |
vows | +0.076 |
brist | +0.074 |
blonde | +0.068 |
Neg logit contributions | |
o | -0.056 |
alone | -0.052 |
forth | -0.048 |
afloat | -0.046 |
tank | -0.046 |
Token | It |
Token ID | 632 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ves | +0.119 |
vows | +0.117 |
Her | +0.114 |
brist | +0.111 |
ork | +0.099 |
Neg logit contributions | |
o | -0.122 |
alone | -0.113 |
tank | -0.103 |
my | -0.100 |
polar | -0.098 |
Token | seemed |
Token ID | 3947 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ves | +0.352 |
Her | +0.350 |
vows | +0.344 |
brist | +0.340 |
blonde | +0.306 |
Neg logit contributions | |
o | -0.395 |
alone | -0.369 |
forth | -0.355 |
afloat | -0.346 |
tank | -0.336 |
Token | very |
Token ID | 845 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
ves | +0.321 |
vows | +0.321 |
Her | +0.320 |
brist | +0.316 |
blonde | +0.291 |
Neg logit contributions | |
o | -0.277 |
alone | -0.249 |
forth | -0.235 |
tank | -0.226 |
my | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
o | +0.189 |
alone | +0.173 |
forth | +0.160 |
tank | +0.156 |
afloat | +0.156 |
Neg logit contributions | |
Her | -0.195 |
ves | -0.193 |
vows | -0.192 |
brist | -0.190 |
blonde | -0.173 |
Token | She |
Token ID | 1375 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ves | +0.103 |
vows | +0.091 |
Her | +0.081 |
brist | +0.081 |
ribbon | +0.080 |
Neg logit contributions | |
o | -0.104 |
alone | -0.102 |
my | -0.090 |
tank | -0.089 |
ny | -0.081 |
Token | was |
Token ID | 373 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
ves | +0.557 |
Her | +0.553 |
vows | +0.553 |
brist | +0.544 |
growth | +0.501 |
Neg logit contributions | |
o | -0.421 |
alone | -0.387 |
forth | -0.345 |
tank | -0.341 |
my | -0.330 |
Token | only |
Token ID | 691 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Her | +0.130 |
brist | +0.126 |
vows | +0.126 |
ves | +0.124 |
blonde | +0.119 |
Neg logit contributions | |
o | -0.097 |
forth | -0.083 |
alone | -0.083 |
afloat | -0.081 |
tank | -0.078 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
Her | +0.166 |
vows | +0.165 |
brist | +0.165 |
ves | +0.164 |
blonde | +0.147 |
Neg logit contributions | |
o | -0.260 |
alone | -0.243 |
forth | -0.228 |
tank | -0.225 |
afloat | -0.223 |
Token | years |
Token ID | 812 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
vows | +0.141 |
Her | +0.141 |
ves | +0.141 |
brist | +0.138 |
growth | +0.127 |
Neg logit contributions | |
o | -0.135 |
alone | -0.127 |
forth | -0.114 |
tank | -0.112 |
my | -0.110 |
Token | old |
Token ID | 1468 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ves | +0.115 |
Her | +0.115 |
vows | +0.115 |
brist | +0.113 |
blonde | +0.104 |
Neg logit contributions | |
o | -0.093 |
alone | -0.085 |
forth | -0.077 |
tank | -0.076 |
afloat | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
o | +0.025 |
alone | +0.024 |
tank | +0.021 |
forth | +0.021 |
my | +0.021 |
Neg logit contributions | |
ves | -0.036 |
Her | -0.035 |
vows | -0.035 |
brist | -0.034 |
growth | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
ves | +0.058 |
vows | +0.058 |
Her | +0.057 |
brist | +0.056 |
growth | +0.054 |
Neg logit contributions | |
o | -0.053 |
alone | -0.052 |
tank | -0.045 |
forth | -0.044 |
my | -0.044 |
Token | very |
Token ID | 845 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
Her | +0.136 |
ves | +0.135 |
vows | +0.135 |
brist | +0.134 |
blonde | +0.124 |
Neg logit contributions | |
o | -0.099 |
alone | -0.089 |
forth | -0.082 |
tank | -0.080 |
afloat | -0.079 |
Token | upset |
Token ID | 9247 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
o | +0.088 |
forth | +0.079 |
afloat | +0.077 |
| | +0.072 |
tank | +0.071 |
Neg logit contributions | |
Her | -0.122 |
vows | -0.119 |
brist | -0.117 |
ves | -0.116 |
blonde | -0.113 |
Token | even |
Token ID | 772 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
ves | +0.027 |
Her | +0.027 |
vows | +0.026 |
brist | +0.026 |
blonde | +0.024 |
Neg logit contributions | |
o | -0.021 |
alone | -0.018 |
forth | -0.018 |
| | -0.017 |
tank | -0.017 |
Token | stronger |
Token ID | 7387 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Her | +0.116 |
brist | +0.108 |
ves | +0.105 |
ribbon | +0.098 |
words | +0.097 |
Neg logit contributions | |
o | -0.165 |
| | -0.151 |
tank | -0.139 |
polar | -0.138 |
wreck | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
o | +0.322 |
alone | +0.287 |
polar | +0.285 |
tank | +0.280 |
| | +0.278 |
Neg logit contributions | |
ves | -0.262 |
Her | -0.253 |
vows | -0.252 |
brist | -0.248 |
ribbon | -0.224 |
Token | So |
Token ID | 1406 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
Her | +0.098 |
ves | +0.095 |
brist | +0.093 |
vows | +0.092 |
blonde | +0.087 |
Neg logit contributions | |
o | -0.098 |
alone | -0.093 |
forth | -0.088 |
afloat | -0.086 |
polar | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
ves | +0.189 |
vows | +0.189 |
Her | +0.188 |
brist | +0.185 |
growth | +0.169 |
Neg logit contributions | |
o | -0.165 |
alone | -0.154 |
forth | -0.141 |
tank | -0.137 |
my | -0.133 |
Token | each |
Token ID | 1123 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
vows | +0.140 |
ves | +0.137 |
Her | +0.136 |
brist | +0.135 |
growth | +0.125 |
Neg logit contributions | |
o | -0.073 |
alone | -0.070 |
forth | -0.061 |
tank | -0.058 |
afloat | -0.054 |
Token | day |
Token ID | 1110 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Her | +0.295 |
ves | +0.292 |
brist | +0.279 |
vows | +0.277 |
growth | +0.265 |
Neg logit contributions | |
o | -0.242 |
alone | -0.208 |
afloat | -0.201 |
forth | -0.193 |
tank | -0.193 |
Token | it |
Token ID | 340 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
o | +0.185 |
alone | +0.166 |
tank | +0.141 |
forth | +0.130 |
afloat | +0.130 |
Neg logit contributions | |
vows | -0.330 |
Her | -0.322 |
brist | -0.320 |
ves | -0.308 |
growth | -0.304 |
Token | would |
Token ID | 561 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ves | +0.143 |
Her | +0.143 |
vows | +0.143 |
brist | +0.140 |
blonde | +0.128 |
Neg logit contributions | |
o | -0.140 |
alone | -0.130 |
forth | -0.118 |
tank | -0.117 |
my | -0.113 |
Token | go |
Token ID | 467 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
ves | +0.282 |
vows | +0.277 |
Her | +0.275 |
brist | +0.275 |
growth | +0.254 |
Neg logit contributions | |
o | -0.211 |
alone | -0.207 |
tank | -0.182 |
forth | -0.178 |
wreck | -0.172 |
Token | for |
Token ID | 329 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
Her | +0.102 |
ves | +0.100 |
brist | +0.093 |
ork | +0.089 |
ribbon | +0.089 |
Neg logit contributions | |
o | -0.113 |
polar | -0.102 |
alone | -0.099 |
forth | -0.099 |
igator | -0.098 |
Token | and |
Token ID | 290 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
alone | +0.010 |
o | +0.009 |
forth | +0.008 |
afloat | +0.007 |
tank | +0.007 |
Neg logit contributions | |
vows | -0.016 |
ves | -0.016 |
Her | -0.016 |
brist | -0.016 |
growth | -0.015 |
Token | slept |
Token ID | 21256 |
Feature activation | +6.10e-03 |
Pos logit contributions | |
ves | +0.076 |
Her | +0.075 |
vows | +0.075 |
brist | +0.074 |
blonde | +0.068 |
Neg logit contributions | |
o | -0.067 |
alone | -0.063 |
forth | -0.057 |
tank | -0.056 |
my | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
alone | +0.009 |
o | +0.008 |
forth | +0.007 |
afloat | +0.007 |
tank | +0.007 |
Neg logit contributions | |
vows | -0.014 |
Her | -0.014 |
ves | -0.014 |
brist | -0.014 |
growth | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ves | +0.132 |
vows | +0.128 |
brist | +0.116 |
Her | +0.113 |
ribbon | +0.112 |
Neg logit contributions | |
o | -0.108 |
alone | -0.105 |
my | -0.093 |
| | -0.088 |
tank | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
o | +0.067 |
alone | +0.062 |
forth | +0.057 |
tank | +0.055 |
afloat | +0.054 |
Neg logit contributions | |
ves | -0.096 |
Her | -0.096 |
vows | -0.094 |
brist | -0.092 |
growth | -0.086 |
Token | Finally |
Token ID | 11158 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
o | +0.079 |
alone | +0.079 |
| | +0.070 |
my | +0.068 |
late | +0.065 |
Neg logit contributions | |
vows | -0.085 |
brist | -0.079 |
blush | -0.073 |
blonde | -0.073 |
ves | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
vows | +0.979 |
brist | +0.968 |
ves | +0.964 |
meanings | +0.940 |
Her | +0.930 |
Neg logit contributions | |
alone | -0.376 |
o | -0.326 |
forth | -0.310 |
my | -0.272 |
Tim | -0.257 |
Token | when |
Token ID | 618 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
vows | +0.166 |
ves | +0.165 |
brist | +0.158 |
Her | +0.153 |
growth | +0.146 |
Neg logit contributions | |
alone | -0.091 |
o | -0.083 |
forth | -0.079 |
my | -0.068 |
down | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
vows | +0.131 |
ves | +0.129 |
brist | +0.126 |
Her | +0.124 |
growth | +0.115 |
Neg logit contributions | |
alone | -0.092 |
o | -0.087 |
forth | -0.083 |
my | -0.073 |
tank | -0.071 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
alone | +0.085 |
o | +0.083 |
forth | +0.075 |
tank | +0.075 |
polar | +0.073 |
Neg logit contributions | |
ves | -0.090 |
Her | -0.090 |
vows | -0.088 |
brist | -0.088 |
blonde | -0.080 |
Token | rose |
Token ID | 8278 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Her | +0.253 |
ves | +0.252 |
brist | +0.251 |
vows | +0.250 |
blonde | +0.235 |
Neg logit contributions | |
o | -0.221 |
alone | -0.202 |
forth | -0.191 |
my | -0.183 |
tank | -0.180 |
Token | walking |
Token ID | 6155 |
Feature activation | -9.27e-03 |
Pos logit contributions | |
Her | +0.140 |
ves | +0.137 |
vows | +0.137 |
brist | +0.137 |
blonde | +0.127 |
Neg logit contributions | |
o | -0.112 |
alone | -0.102 |
forth | -0.094 |
tank | -0.092 |
afloat | -0.091 |
Token | around |
Token ID | 1088 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Her | +0.021 |
brist | +0.020 |
vows | +0.020 |
ves | +0.020 |
blonde | +0.019 |
Neg logit contributions | |
o | -0.014 |
alone | -0.012 |
afloat | -0.011 |
tank | -0.011 |
polar | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
o | +0.233 |
alone | +0.222 |
forth | +0.192 |
tank | +0.187 |
my | +0.183 |
Neg logit contributions | |
ves | -0.349 |
vows | -0.346 |
Her | -0.338 |
brist | -0.334 |
blonde | -0.309 |
Token | garden |
Token ID | 11376 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ves | +0.674 |
vows | +0.671 |
Her | +0.655 |
brist | +0.650 |
growth | +0.607 |
Neg logit contributions | |
o | -0.500 |
alone | -0.470 |
forth | -0.409 |
tank | -0.407 |
my | -0.394 |
Token | when |
Token ID | 618 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
vows | +0.528 |
ves | +0.503 |
growth | +0.477 |
brist | +0.475 |
meanings | +0.459 |
Neg logit contributions | |
alone | -0.251 |
o | -0.232 |
my | -0.183 |
tank | -0.176 |
forth | -0.166 |
Token | she |
Token ID | 673 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
vows | +0.083 |
ves | +0.079 |
brist | +0.078 |
Her | +0.068 |
ribbon | +0.068 |
Neg logit contributions | |
alone | -0.133 |
o | -0.127 |
forth | -0.119 |
my | -0.114 |
tank | -0.108 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
ves | +0.817 |
vows | +0.816 |
Her | +0.810 |
brist | +0.803 |
growth | +0.742 |
Neg logit contributions | |
o | -0.490 |
alone | -0.441 |
forth | -0.382 |
tank | -0.375 |
my | -0.369 |
Token | an |
Token ID | 281 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
alone | +0.095 |
o | +0.089 |
my | +0.082 |
Tim | +0.078 |
polar | +0.077 |
Neg logit contributions | |
vows | -0.165 |
ves | -0.160 |
ork | -0.146 |
ues | -0.142 |
brist | -0.140 |
Token | amazing |
Token ID | 4998 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Her | +0.431 |
ves | +0.429 |
vows | +0.427 |
brist | +0.425 |
blonde | +0.387 |
Neg logit contributions | |
o | -0.384 |
alone | -0.346 |
forth | -0.317 |
tank | -0.311 |
afloat | -0.307 |
Token | symbol |
Token ID | 6194 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
Her | +0.204 |
ves | +0.204 |
vows | +0.199 |
brist | +0.192 |
growth | +0.180 |
Neg logit contributions | |
o | -0.239 |
alone | -0.229 |
forth | -0.212 |
tank | -0.212 |
wreck | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
vows | +0.187 |
Her | +0.183 |
brist | +0.181 |
growth | +0.175 |
ves | +0.172 |
Neg logit contributions | |
o | -0.099 |
alone | -0.098 |
tank | -0.077 |
forth | -0.076 |
my | -0.074 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
o | +0.212 |
alone | +0.193 |
tank | +0.167 |
my | +0.167 |
forth | +0.165 |
Neg logit contributions | |
Her | -0.284 |
brist | -0.276 |
vows | -0.276 |
ves | -0.276 |
blonde | -0.253 |
Token | it |
Token ID | 340 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
o | +0.117 |
alone | +0.115 |
tank | +0.103 |
wreck | +0.098 |
forth | +0.098 |
Neg logit contributions | |
Her | -0.138 |
ves | -0.134 |
vows | -0.134 |
brist | -0.132 |
blonde | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
vows | +0.174 |
Her | +0.173 |
brist | +0.171 |
ves | +0.170 |
growth | +0.156 |
Neg logit contributions | |
o | -0.127 |
alone | -0.124 |
my | -0.106 |
tank | -0.104 |
forth | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
Her | +0.116 |
brist | +0.111 |
Her | +0.111 |
ves | +0.110 |
vows | +0.110 |
Neg logit contributions | |
forth | -0.113 |
o | -0.109 |
alone | -0.109 |
afloat | -0.103 |
polar | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
o | +0.073 |
forth | +0.073 |
alone | +0.072 |
afloat | +0.065 |
tank | +0.064 |
Neg logit contributions | |
ves | -0.087 |
Her | -0.086 |
vows | -0.078 |
brist | -0.077 |
ork | -0.075 |
Token | To |
Token ID | 2514 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
o | +0.096 |
alone | +0.090 |
forth | +0.083 |
tank | +0.083 |
afloat | +0.081 |
Neg logit contributions | |
ves | -0.064 |
vows | -0.064 |
Her | -0.064 |
brist | -0.062 |
blonde | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
ves | +0.751 |
Her | +0.747 |
vows | +0.746 |
brist | +0.736 |
blonde | +0.687 |
Neg logit contributions | |
o | -0.365 |
alone | -0.328 |
forth | -0.280 |
tank | -0.275 |
afloat | -0.264 |
Token | little |
Token ID | 1310 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
alone | +0.092 |
o | +0.091 |
forth | +0.081 |
tank | +0.081 |
my | +0.079 |
Neg logit contributions | |
ves | -0.099 |
vows | -0.097 |
Her | -0.097 |
brist | -0.093 |
growth | -0.085 |
Token | boy |
Token ID | 2933 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
brist | +0.219 |
ribbon | +0.213 |
blonde | +0.207 |
words | +0.201 |
growth | +0.199 |
Neg logit contributions | |
o | -0.147 |
| | -0.109 |
afloat | -0.105 |
ll | -0.105 |
polar | -0.097 |
Token | 's |
Token ID | 338 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
o | +0.528 |
alone | +0.489 |
forth | +0.442 |
tank | +0.436 |
afloat | +0.426 |
Neg logit contributions | |
ves | -0.601 |
Her | -0.598 |
vows | -0.597 |
brist | -0.586 |
blonde | -0.536 |
Token | amaz |
Token ID | 40642 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
o | +0.028 |
alone | +0.028 |
tank | +0.026 |
forth | +0.025 |
wreck | +0.025 |
Neg logit contributions | |
ves | -0.024 |
Her | -0.023 |
vows | -0.022 |
brist | -0.022 |
blonde | -0.019 |
Token | house |
Token ID | 2156 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ves | +0.100 |
vows | +0.099 |
Her | +0.098 |
brist | +0.095 |
growth | +0.091 |
Neg logit contributions | |
o | -0.073 |
alone | -0.072 |
forth | -0.064 |
my | -0.063 |
tank | -0.062 |
Token | together |
Token ID | 1978 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
o | +0.036 |
alone | +0.033 |
forth | +0.030 |
tank | +0.030 |
my | +0.029 |
Neg logit contributions | |
ves | -0.040 |
Her | -0.039 |
vows | -0.039 |
brist | -0.039 |
growth | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
alone | +0.149 |
o | +0.146 |
tank | +0.121 |
forth | +0.119 |
my | +0.116 |
Neg logit contributions | |
brist | -0.235 |
vows | -0.232 |
Her | -0.231 |
ves | -0.227 |
growth | -0.214 |
Token | He |
Token ID | 679 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Her | +0.099 |
ves | +0.095 |
Her | +0.091 |
brist | +0.090 |
vows | +0.090 |
Neg logit contributions | |
o | -0.070 |
forth | -0.070 |
alone | -0.070 |
afloat | -0.068 |
polar | -0.063 |
Token | asked |
Token ID | 1965 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
o | +0.371 |
alone | +0.330 |
tank | +0.296 |
my | +0.295 |
forth | +0.292 |
Neg logit contributions | |
Her | -0.477 |
brist | -0.468 |
ves | -0.467 |
vows | -0.462 |
growth | -0.442 |
Token | her |
Token ID | 607 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
o | +0.070 |
alone | +0.067 |
my | +0.058 |
forth | +0.056 |
tank | +0.055 |
Neg logit contributions | |
vows | -0.110 |
ves | -0.110 |
brist | -0.110 |
Her | -0.107 |
growth | -0.101 |
Token | if |
Token ID | 611 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
brist | +0.721 |
ves | +0.711 |
vows | +0.706 |
Her | +0.698 |
growth | +0.682 |
Neg logit contributions | |
o | -0.416 |
alone | -0.372 |
my | -0.327 |
tank | -0.320 |
forth | -0.295 |
Token | she |
Token ID | 673 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
o | +0.148 |
alone | +0.140 |
forth | +0.125 |
my | +0.123 |
tank | +0.121 |
Neg logit contributions | |
brist | -0.136 |
vows | -0.135 |
ves | -0.134 |
Her | -0.130 |
growth | -0.123 |
Token | wanted |
Token ID | 2227 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
ves | +0.725 |
Her | +0.722 |
vows | +0.714 |
brist | +0.713 |
growth | +0.660 |
Neg logit contributions | |
o | -0.551 |
alone | -0.488 |
my | -0.439 |
tank | -0.425 |
forth | -0.419 |
Token | to |
Token ID | 284 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
ves | +0.022 |
brist | +0.022 |
vows | +0.021 |
Her | +0.021 |
owers | +0.021 |
Neg logit contributions | |
alone | -0.010 |
o | -0.009 |
his | -0.008 |
my | -0.008 |
tank | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ves | +0.226 |
brist | +0.218 |
vows | +0.213 |
Her | +0.202 |
owers | +0.197 |
Neg logit contributions | |
alone | -0.113 |
o | -0.112 |
my | -0.098 |
wreck | -0.097 |
forth | -0.093 |
Token | very |
Token ID | 845 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
Her | +0.159 |
ves | +0.153 |
vows | +0.152 |
brist | +0.150 |
blonde | +0.140 |
Neg logit contributions | |
o | -0.093 |
forth | -0.079 |
alone | -0.077 |
tank | -0.075 |
polar | -0.071 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
o | +0.073 |
forth | +0.063 |
tank | +0.059 |
my | +0.059 |
alone | +0.058 |
Neg logit contributions | |
Her | -0.118 |
vows | -0.111 |
ves | -0.110 |
brist | -0.108 |
Her | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
alone | +0.156 |
o | +0.152 |
my | +0.125 |
forth | +0.124 |
tank | +0.117 |
Neg logit contributions | |
vows | -0.260 |
ves | -0.249 |
Her | -0.246 |
brist | -0.239 |
growth | -0.239 |
Token | Even |
Token ID | 3412 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ves | +0.116 |
vows | +0.103 |
brist | +0.093 |
growth | +0.093 |
Her | +0.092 |
Neg logit contributions | |
o | -0.133 |
alone | -0.130 |
my | -0.119 |
tank | -0.111 |
| | -0.106 |
Token | though |
Token ID | 996 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Her | +0.516 |
brist | +0.506 |
ves | +0.503 |
vows | +0.496 |
blonde | +0.471 |
Neg logit contributions | |
o | -0.398 |
alone | -0.342 |
tank | -0.323 |
afloat | -0.309 |
forth | -0.308 |
Token | she |
Token ID | 673 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
alone | +0.246 |
o | +0.221 |
forth | +0.210 |
my | +0.200 |
Tim | +0.195 |
Neg logit contributions | |
vows | -0.248 |
brist | -0.244 |
ves | -0.234 |
Her | -0.232 |
growth | -0.226 |
Token | had |
Token ID | 550 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ves | +0.630 |
vows | +0.625 |
Her | +0.619 |
brist | +0.614 |
blonde | +0.556 |
Neg logit contributions | |
o | -0.656 |
alone | -0.619 |
forth | -0.571 |
tank | -0.563 |
afloat | -0.560 |
Token | had |
Token ID | 550 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
alone | +0.047 |
o | +0.045 |
my | +0.037 |
forth | +0.035 |
afloat | +0.035 |
Neg logit contributions | |
ves | -0.069 |
Her | -0.069 |
vows | -0.068 |
brist | -0.066 |
owers | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
alone | +0.046 |
o | +0.044 |
my | +0.036 |
wreck | +0.034 |
tank | +0.034 |
Neg logit contributions | |
Her | -0.068 |
ves | -0.068 |
vows | -0.066 |
brist | -0.066 |
owers | -0.064 |
Token | lovely |
Token ID | 14081 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Her | +0.340 |
ves | +0.340 |
vows | +0.330 |
brist | +0.324 |
growth | +0.309 |
Neg logit contributions | |
o | -0.288 |
alone | -0.274 |
tank | -0.253 |
wreck | -0.242 |
afloat | -0.241 |
Token | bath |
Token ID | 7837 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
Her | +0.269 |
ves | +0.264 |
vows | +0.255 |
growth | +0.247 |
brist | +0.247 |
Neg logit contributions | |
o | -0.175 |
alone | -0.168 |
tank | -0.159 |
polar | -0.150 |
wreck | -0.145 |