Token | to |
Token ID | 284 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
around | +0.218 |
down | +0.197 |
air | +0.194 |
cy | +0.192 |
et | +0.186 |
Neg logit contributions | |
ves | -0.175 |
vern | -0.175 |
ades | -0.153 |
keys | -0.153 |
mercy | -0.151 |
Token | take |
Token ID | 1011 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
ves | +0.190 |
vern | +0.182 |
ades | +0.179 |
keys | +0.173 |
mercy | +0.158 |
Neg logit contributions | |
around | -0.132 |
air | -0.122 |
down | -0.117 |
| | -0.116 |
cy | -0.111 |
Token | them |
Token ID | 606 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
ves | +0.156 |
vern | +0.152 |
backup | +0.138 |
ades | +0.137 |
mercy | +0.135 |
Neg logit contributions | |
around | -0.181 |
cy | -0.171 |
air | -0.166 |
rated | -0.165 |
et | -0.163 |
Token | to |
Token ID | 284 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ves | +0.250 |
vern | +0.244 |
ades | +0.226 |
keys | +0.222 |
mercy | +0.222 |
Neg logit contributions | |
around | -0.182 |
down | -0.158 |
cy | -0.155 |
air | -0.153 |
et | -0.147 |
Token | the |
Token ID | 262 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
ves | +0.203 |
vern | +0.196 |
ades | +0.191 |
keys | +0.188 |
mercy | +0.175 |
Neg logit contributions | |
around | -0.123 |
air | -0.110 |
down | -0.108 |
| | -0.102 |
cy | -0.100 |
Token | charity |
Token ID | 11016 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
around | +0.196 |
air | +0.185 |
cy | +0.174 |
down | +0.174 |
et | +0.161 |
Neg logit contributions | |
ves | -0.260 |
vern | -0.246 |
keys | -0.232 |
ades | -0.230 |
mercy | -0.209 |
Token | shop |
Token ID | 6128 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ves | +0.851 |
vern | +0.833 |
ades | +0.760 |
backup | +0.757 |
mercy | +0.734 |
Neg logit contributions | |
around | -0.964 |
cy | -0.904 |
rated | -0.893 |
air | -0.884 |
| | -0.877 |
Token | , |
Token ID | 11 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
ves | +0.253 |
vern | +0.251 |
ades | +0.230 |
mercy | +0.226 |
keys | +0.223 |
Neg logit contributions | |
around | -0.172 |
cy | -0.153 |
down | -0.149 |
air | -0.149 |
et | -0.142 |
Token | where |
Token ID | 810 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
ves | +0.062 |
vern | +0.062 |
ades | +0.057 |
keys | +0.055 |
mercy | +0.055 |
Neg logit contributions | |
around | -0.042 |
down | -0.036 |
air | -0.036 |
cy | -0.035 |
et | -0.034 |
Token | other |
Token ID | 584 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
vern | +0.246 |
ves | +0.240 |
ades | +0.213 |
mercy | +0.202 |
backup | +0.201 |
Neg logit contributions | |
around | -0.423 |
air | -0.385 |
down | -0.384 |
cy | -0.383 |
et | -0.366 |
Token | children |
Token ID | 1751 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
vern | +0.082 |
ves | +0.081 |
ades | +0.073 |
mercy | +0.071 |
backup | +0.070 |
Neg logit contributions | |
around | -0.067 |
air | -0.061 |
cy | -0.058 |
down | -0.058 |
et | -0.054 |
Token | know |
Token ID | 760 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
vern | +0.429 |
mercy | +0.410 |
ves | +0.396 |
backup | +0.385 |
forgiveness | +0.378 |
Neg logit contributions | |
around | -0.424 |
cy | -0.420 |
amp | -0.412 |
ening | -0.392 |
down | -0.390 |
Token | the |
Token ID | 262 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
vern | +0.084 |
ves | +0.081 |
ades | +0.074 |
backup | +0.072 |
mercy | +0.070 |
Neg logit contributions | |
around | -0.108 |
air | -0.097 |
down | -0.095 |
cy | -0.092 |
et | -0.092 |
Token | box |
Token ID | 3091 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
around | +0.248 |
air | +0.231 |
cy | +0.224 |
down | +0.223 |
et | +0.215 |
Neg logit contributions | |
ves | -0.196 |
vern | -0.189 |
ades | -0.171 |
keys | -0.169 |
mercy | -0.165 |
Token | was |
Token ID | 373 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
around | +0.010 |
cy | +0.009 |
air | +0.009 |
down | +0.008 |
et | +0.008 |
Neg logit contributions | |
ves | -0.013 |
vern | -0.013 |
ades | -0.012 |
mercy | -0.012 |
backup | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ves | +0.101 |
vern | +0.099 |
ades | +0.090 |
mercy | +0.088 |
backup | +0.087 |
Neg logit contributions | |
around | -0.102 |
cy | -0.093 |
air | -0.092 |
down | -0.091 |
et | -0.089 |
Token | charity |
Token ID | 11016 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
around | +0.095 |
air | +0.086 |
down | +0.084 |
cy | +0.080 |
et | +0.079 |
Neg logit contributions | |
vern | -0.103 |
ves | -0.102 |
ades | -0.093 |
mercy | -0.091 |
keys | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
ves | +1.043 |
vern | +1.027 |
ades | +0.937 |
mercy | +0.926 |
backup | +0.922 |
Neg logit contributions | |
around | -0.801 |
cy | -0.746 |
air | -0.727 |
down | -0.716 |
| | -0.706 |
Token | They |
Token ID | 1119 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
around | +0.013 |
et | +0.012 |
rated | +0.012 |
cy | +0.011 |
ening | +0.011 |
Neg logit contributions | |
ves | -0.021 |
vern | -0.020 |
backup | -0.019 |
ades | -0.019 |
forgiveness | -0.019 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
around | +0.080 |
cy | +0.071 |
air | +0.071 |
down | +0.068 |
et | +0.068 |
Neg logit contributions | |
ves | -0.115 |
vern | -0.115 |
ades | -0.106 |
backup | -0.103 |
mercy | -0.102 |
Token | it |
Token ID | 340 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
around | +0.074 |
air | +0.065 |
down | +0.064 |
et | +0.061 |
cy | +0.061 |
Neg logit contributions | |
vern | -0.073 |
ves | -0.071 |
ades | -0.067 |
mercy | -0.065 |
keys | -0.064 |
Token | was |
Token ID | 373 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
around | +0.254 |
air | +0.243 |
cy | +0.240 |
down | +0.237 |
| | +0.233 |
Neg logit contributions | |
ves | -0.246 |
vern | -0.225 |
ades | -0.208 |
mercy | -0.204 |
forgiveness | -0.204 |
Token | She |
Token ID | 1375 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
rated | +0.014 |
around | +0.014 |
cy | +0.014 |
et | +0.014 |
ening | +0.013 |
Neg logit contributions | |
ves | -0.024 |
vern | -0.023 |
backup | -0.022 |
His | -0.021 |
ades | -0.021 |
Token | drove |
Token ID | 10357 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
around | +0.240 |
cy | +0.203 |
air | +0.201 |
et | +0.199 |
down | +0.186 |
Neg logit contributions | |
vern | -0.416 |
ves | -0.370 |
ades | -0.360 |
backup | -0.357 |
keys | -0.353 |
Token | away |
Token ID | 1497 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
ves | +0.185 |
vern | +0.169 |
backup | +0.165 |
mercy | +0.156 |
ades | +0.155 |
Neg logit contributions | |
cy | -0.187 |
| | -0.183 |
rated | -0.180 |
air | -0.175 |
amp | -0.174 |
Token | to |
Token ID | 284 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
around | +0.215 |
cy | +0.194 |
air | +0.191 |
down | +0.186 |
et | +0.184 |
Neg logit contributions | |
ves | -0.296 |
vern | -0.292 |
ades | -0.268 |
mercy | -0.264 |
backup | -0.262 |
Token | the |
Token ID | 262 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
ves | +0.177 |
vern | +0.175 |
ades | +0.159 |
mercy | +0.158 |
backup | +0.156 |
Neg logit contributions | |
around | -0.141 |
cy | -0.128 |
air | -0.126 |
down | -0.124 |
et | -0.121 |
Token | charity |
Token ID | 11016 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
around | +0.199 |
air | +0.179 |
cy | +0.179 |
down | +0.175 |
et | +0.170 |
Neg logit contributions | |
ves | -0.247 |
vern | -0.243 |
ades | -0.222 |
mercy | -0.216 |
keys | -0.216 |
Token | shop |
Token ID | 6128 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ves | +0.884 |
vern | +0.864 |
backup | +0.793 |
ades | +0.791 |
forgiveness | +0.764 |
Neg logit contributions | |
around | -0.904 |
rated | -0.872 |
cy | -0.863 |
| | -0.852 |
air | -0.823 |
Token | . |
Token ID | 13 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ves | +0.251 |
vern | +0.249 |
ades | +0.229 |
mercy | +0.225 |
backup | +0.223 |
Neg logit contributions | |
around | -0.166 |
cy | -0.147 |
air | -0.146 |
down | -0.143 |
et | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
around | +0.017 |
rated | +0.017 |
et | +0.017 |
ening | +0.016 |
cy | +0.016 |
Neg logit contributions | |
ves | -0.018 |
vern | -0.018 |
backup | -0.017 |
His | -0.016 |
forgiveness | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
vern | +0.047 |
ves | +0.046 |
mercy | +0.043 |
ades | +0.043 |
keys | +0.042 |
Neg logit contributions | |
around | -0.036 |
air | -0.031 |
cy | -0.031 |
down | -0.031 |
| | -0.030 |
Token | L |
Token ID | 43 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
vern | +0.039 |
mercy | +0.038 |
forgiveness | +0.036 |
ves | +0.036 |
keys | +0.035 |
Neg logit contributions | |
around | -0.044 |
air | -0.039 |
amp | -0.039 |
| | -0.039 |
cy | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
around | +0.013 |
cy | +0.012 |
air | +0.012 |
down | +0.012 |
et | +0.011 |
Neg logit contributions | |
ves | -0.016 |
vern | -0.016 |
ades | -0.014 |
backup | -0.014 |
mercy | -0.014 |
Token | It |
Token ID | 632 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
around | +0.017 |
et | +0.016 |
cy | +0.016 |
rated | +0.015 |
ening | +0.015 |
Neg logit contributions | |
vern | -0.023 |
ves | -0.023 |
backup | -0.022 |
forgiveness | -0.021 |
mercy | -0.021 |
Token | belongs |
Token ID | 14448 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
around | +0.430 |
cy | +0.389 |
air | +0.383 |
down | +0.377 |
et | +0.370 |
Neg logit contributions | |
ves | -0.586 |
vern | -0.567 |
ades | -0.521 |
keys | -0.519 |
mercy | -0.517 |
Token | to |
Token ID | 284 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ves | +0.023 |
vern | +0.023 |
ades | +0.020 |
mercy | +0.020 |
keys | +0.020 |
Neg logit contributions | |
around | -0.028 |
cy | -0.025 |
down | -0.025 |
air | -0.025 |
et | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
vern | +0.172 |
ves | +0.169 |
ades | +0.157 |
mercy | +0.147 |
backup | +0.146 |
Neg logit contributions | |
around | -0.148 |
air | -0.134 |
down | -0.130 |
cy | -0.126 |
et | -0.124 |
Token | charity |
Token ID | 11016 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
around | +0.211 |
cy | +0.192 |
air | +0.191 |
down | +0.187 |
et | +0.183 |
Neg logit contributions | |
ves | -0.232 |
vern | -0.229 |
ades | -0.209 |
mercy | -0.204 |
backup | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
ves | +0.905 |
vern | +0.885 |
ades | +0.808 |
keys | +0.793 |
mercy | +0.786 |
Neg logit contributions | |
around | -0.926 |
cy | -0.870 |
air | -0.846 |
et | -0.835 |
down | -0.835 |
Token | We |
Token ID | 775 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
around | +0.015 |
cy | +0.014 |
et | +0.014 |
rated | +0.013 |
air | +0.013 |
Neg logit contributions | |
ves | -0.024 |
vern | -0.024 |
backup | -0.022 |
forgiveness | -0.022 |
mercy | -0.022 |
Token | provide |
Token ID | 2148 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
ves | +0.027 |
vern | +0.027 |
mercy | +0.025 |
keys | +0.025 |
backup | +0.024 |
Neg logit contributions | |
around | -0.022 |
air | -0.020 |
down | -0.020 |
ening | -0.020 |
et | -0.020 |
Token | clothes |
Token ID | 8242 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
vern | +0.416 |
ves | +0.411 |
ades | +0.385 |
keys | +0.365 |
mercy | +0.356 |
Neg logit contributions | |
around | -0.351 |
air | -0.309 |
down | -0.303 |
cy | -0.285 |
et | -0.277 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ves | +0.455 |
vern | +0.452 |
mercy | +0.416 |
ades | +0.416 |
backup | +0.412 |
Neg logit contributions | |
around | -0.299 |
down | -0.252 |
cy | -0.247 |
air | -0.243 |
et | -0.229 |
Token | . |
Token ID | 13 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
ves | +0.347 |
vern | +0.343 |
ades | +0.315 |
mercy | +0.310 |
backup | +0.308 |
Neg logit contributions | |
around | -0.251 |
cy | -0.230 |
air | -0.225 |
down | -0.217 |
et | -0.216 |
Token | They |
Token ID | 1119 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
around | +0.017 |
cy | +0.015 |
air | +0.015 |
down | +0.015 |
et | +0.014 |
Neg logit contributions | |
ves | -0.028 |
vern | -0.028 |
ades | -0.026 |
mercy | -0.025 |
backup | -0.025 |
Token | belong |
Token ID | 5594 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
around | +0.078 |
cy | +0.068 |
air | +0.068 |
down | +0.066 |
et | +0.064 |
Neg logit contributions | |
ves | -0.128 |
vern | -0.127 |
ades | -0.117 |
mercy | -0.115 |
backup | -0.114 |
Token | to |
Token ID | 284 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ves | +0.118 |
vern | +0.114 |
ades | +0.105 |
keys | +0.102 |
mercy | +0.101 |
Neg logit contributions | |
around | -0.106 |
down | -0.094 |
cy | -0.093 |
air | -0.089 |
et | -0.084 |
Token | a |
Token ID | 257 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ves | +0.169 |
vern | +0.168 |
ades | +0.154 |
mercy | +0.150 |
backup | +0.149 |
Neg logit contributions | |
around | -0.142 |
air | -0.127 |
cy | -0.127 |
down | -0.125 |
et | -0.122 |
Token | charity |
Token ID | 11016 |
Feature activation | +1.71e+01 |
Pos logit contributions | |
ves | +0.259 |
vern | +0.253 |
ades | +0.233 |
mercy | +0.228 |
keys | +0.222 |
Neg logit contributions | |
around | -0.260 |
air | -0.236 |
cy | -0.234 |
down | -0.232 |
| | -0.219 |
Token | that |
Token ID | 326 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
ves | +0.921 |
vern | +0.906 |
ades | +0.824 |
backup | +0.810 |
mercy | +0.808 |
Neg logit contributions | |
around | -0.903 |
cy | -0.845 |
air | -0.820 |
rated | -0.813 |
down | -0.810 |
Token | helps |
Token ID | 5419 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
ves | +0.246 |
vern | +0.240 |
ades | +0.220 |
mercy | +0.216 |
backup | +0.216 |
Neg logit contributions | |
around | -0.192 |
cy | -0.175 |
air | -0.171 |
down | -0.168 |
et | -0.167 |
Token | poor |
Token ID | 3595 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
vern | +0.249 |
ves | +0.248 |
ades | +0.227 |
mercy | +0.221 |
backup | +0.217 |
Neg logit contributions | |
around | -0.214 |
air | -0.189 |
down | -0.187 |
cy | -0.186 |
et | -0.180 |
Token | kids |
Token ID | 3988 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
vern | +0.129 |
ves | +0.126 |
ades | +0.116 |
backup | +0.113 |
mercy | +0.112 |
Neg logit contributions | |
around | -0.106 |
air | -0.099 |
down | -0.094 |
cy | -0.092 |
et | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
around | +0.041 |
cy | +0.036 |
air | +0.035 |
down | +0.035 |
et | +0.034 |
Neg logit contributions | |
ves | -0.054 |
vern | -0.053 |
ades | -0.049 |
mercy | -0.048 |
backup | -0.048 |
Token | all |
Token ID | 477 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
ves | +0.396 |
vern | +0.392 |
ades | +0.359 |
keys | +0.350 |
mercy | +0.340 |
Neg logit contributions | |
around | -0.381 |
air | -0.341 |
down | -0.335 |
cy | -0.324 |
et | -0.318 |
Token | your |
Token ID | 534 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
around | +0.126 |
air | +0.112 |
down | +0.107 |
cy | +0.104 |
et | +0.101 |
Neg logit contributions | |
ves | -0.155 |
vern | -0.153 |
ades | -0.142 |
keys | -0.139 |
mercy | -0.136 |
Token | toys |
Token ID | 14958 |
Feature activation | +6.50e+00 |
Pos logit contributions | |
ves | +0.138 |
vern | +0.132 |
ades | +0.121 |
keys | +0.117 |
mercy | +0.113 |
Neg logit contributions | |
around | -0.169 |
air | -0.158 |
cy | -0.151 |
down | -0.150 |
et | -0.144 |
Token | to |
Token ID | 284 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ves | +0.432 |
vern | +0.422 |
ades | +0.396 |
mercy | +0.391 |
keys | +0.383 |
Neg logit contributions | |
around | -0.300 |
down | -0.256 |
cy | -0.248 |
air | -0.247 |
et | -0.235 |
Token | a |
Token ID | 257 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
ves | +0.166 |
vern | +0.164 |
ades | +0.154 |
keys | +0.146 |
mercy | +0.144 |
Neg logit contributions | |
around | -0.139 |
air | -0.123 |
down | -0.120 |
cy | -0.117 |
| | -0.115 |
Token | charity |
Token ID | 11016 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
ves | +0.255 |
vern | +0.244 |
ades | +0.223 |
keys | +0.217 |
mercy | +0.215 |
Neg logit contributions | |
around | -0.260 |
air | -0.234 |
down | -0.233 |
cy | -0.230 |
| | -0.216 |
Token | that |
Token ID | 326 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
ves | +1.006 |
vern | +0.992 |
ades | +0.909 |
backup | +0.893 |
mercy | +0.891 |
Neg logit contributions | |
around | -0.790 |
cy | -0.743 |
air | -0.719 |
rated | -0.709 |
| | -0.708 |
Token | helps |
Token ID | 5419 |
Feature activation | +4.08e+00 |
Pos logit contributions | |
ves | +0.250 |
vern | +0.244 |
ades | +0.224 |
mercy | +0.221 |
backup | +0.220 |
Neg logit contributions | |
around | -0.176 |
cy | -0.159 |
air | -0.156 |
down | -0.153 |
et | -0.152 |
Token | children |
Token ID | 1751 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
vern | +0.243 |
ves | +0.242 |
ades | +0.222 |
mercy | +0.216 |
backup | +0.213 |
Neg logit contributions | |
around | -0.206 |
air | -0.181 |
down | -0.179 |
cy | -0.176 |
et | -0.171 |
Token | in |
Token ID | 287 |
Feature activation | -6.85e+00 |
Pos logit contributions | |
around | +0.040 |
down | +0.034 |
cy | +0.034 |
air | +0.034 |
et | +0.032 |
Neg logit contributions | |
ves | -0.055 |
vern | -0.054 |
ades | -0.050 |
mercy | -0.050 |
backup | -0.049 |
Token | need |
Token ID | 761 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
around | +0.321 |
air | +0.284 |
cy | +0.280 |
down | +0.278 |
et | +0.263 |
Neg logit contributions | |
ves | -0.435 |
vern | -0.424 |
ades | -0.396 |
keys | -0.387 |
mercy | -0.384 |
Token | ! |
Token ID | 0 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
around | +0.015 |
air | +0.013 |
cy | +0.013 |
down | +0.013 |
et | +0.012 |
Neg logit contributions | |
ves | -0.023 |
vern | -0.023 |
ades | -0.021 |
mercy | -0.021 |
backup | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ves | +0.009 |
vern | +0.008 |
backup | +0.008 |
ades | +0.008 |
forgiveness | +0.008 |
Neg logit contributions | |
around | -0.005 |
et | -0.004 |
rated | -0.004 |
air | -0.004 |
cy | -0.004 |
Token | are |
Token ID | 389 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
around | +0.084 |
cy | +0.076 |
down | +0.075 |
air | +0.073 |
et | +0.072 |
Neg logit contributions | |
ves | -0.128 |
vern | -0.126 |
ades | -0.115 |
mercy | -0.115 |
backup | -0.114 |
Token | for |
Token ID | 329 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ves | +0.025 |
vern | +0.025 |
ades | +0.022 |
mercy | +0.022 |
backup | +0.022 |
Neg logit contributions | |
around | -0.026 |
cy | -0.024 |
air | -0.024 |
down | -0.023 |
et | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
around | +0.098 |
air | +0.088 |
down | +0.086 |
cy | +0.077 |
alone | +0.077 |
Neg logit contributions | |
vern | -0.125 |
ves | -0.124 |
ades | -0.114 |
His | -0.109 |
keys | -0.108 |
Token | charity |
Token ID | 11016 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
around | +0.243 |
cy | +0.222 |
air | +0.222 |
down | +0.217 |
et | +0.213 |
Neg logit contributions | |
ves | -0.217 |
vern | -0.213 |
ades | -0.192 |
mercy | -0.188 |
backup | -0.185 |
Token | ! |
Token ID | 0 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ves | +0.990 |
vern | +0.977 |
ades | +0.891 |
backup | +0.880 |
mercy | +0.877 |
Neg logit contributions | |
around | -0.803 |
cy | -0.747 |
| | -0.731 |
rated | -0.730 |
air | -0.722 |
Token | I |
Token ID | 314 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ves | +0.009 |
vern | +0.009 |
backup | +0.008 |
ades | +0.008 |
forgiveness | +0.008 |
Neg logit contributions | |
around | -0.005 |
et | -0.004 |
cy | -0.004 |
rated | -0.004 |
air | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ves | +0.078 |
vern | +0.076 |
ades | +0.070 |
mercy | +0.070 |
backup | +0.069 |
Neg logit contributions | |
around | -0.054 |
air | -0.049 |
down | -0.048 |
cy | -0.048 |
et | -0.047 |
Token | going |
Token ID | 1016 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
ves | +0.098 |
vern | +0.097 |
ades | +0.088 |
backup | +0.087 |
mercy | +0.087 |
Neg logit contributions | |
around | -0.085 |
cy | -0.079 |
air | -0.077 |
down | -0.075 |
et | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
around | +0.234 |
cy | +0.215 |
air | +0.213 |
down | +0.212 |
et | +0.207 |
Neg logit contributions | |
ves | -0.171 |
vern | -0.168 |
ades | -0.149 |
mercy | -0.146 |
keys | -0.143 |
Token | " |
Token ID | 1 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
cy | +0.303 |
around | +0.296 |
et | +0.290 |
| | +0.287 |
air | +0.282 |
Neg logit contributions | |
ves | -0.281 |
vern | -0.277 |
mercy | -0.243 |
keys | -0.238 |
forgiveness | -0.234 |
Token | Let |
Token ID | 5756 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
vern | +0.776 |
ves | +0.732 |
ades | +0.701 |
backup | +0.684 |
instincts | +0.677 |
Neg logit contributions | |
around | -0.618 |
cy | -0.596 |
air | -0.565 |
| | -0.554 |
down | -0.538 |
Token | 's |
Token ID | 338 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
around | +0.057 |
cy | +0.050 |
air | +0.050 |
down | +0.049 |
et | +0.047 |
Neg logit contributions | |
ves | -0.084 |
vern | -0.084 |
ades | -0.077 |
mercy | -0.076 |
backup | -0.075 |
Token | go |
Token ID | 467 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
vern | +0.201 |
ves | +0.198 |
ades | +0.182 |
backup | +0.175 |
mercy | +0.174 |
Neg logit contributions | |
around | -0.151 |
down | -0.133 |
cy | -0.130 |
air | -0.129 |
et | -0.119 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ves | +0.062 |
vern | +0.061 |
ades | +0.056 |
mercy | +0.055 |
keys | +0.055 |
Neg logit contributions | |
around | -0.048 |
cy | -0.042 |
down | -0.042 |
air | -0.041 |
et | -0.039 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
vern | +0.089 |
ves | +0.088 |
ades | +0.082 |
mercy | +0.078 |
backup | +0.076 |
Neg logit contributions | |
around | -0.069 |
down | -0.062 |
air | -0.060 |
cy | -0.060 |
et | -0.055 |
Token | y |
Token ID | 88 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
ves | +1.194 |
vern | +1.176 |
ades | +1.103 |
mercy | +1.081 |
keys | +1.065 |
Neg logit contributions | |
around | -0.629 |
air | -0.557 |
cy | -0.545 |
down | -0.527 |
et | -0.518 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
around | +0.212 |
air | +0.187 |
cy | +0.187 |
down | +0.184 |
et | +0.176 |
Neg logit contributions | |
vern | -0.294 |
ves | -0.294 |
ades | -0.269 |
mercy | -0.263 |
backup | -0.262 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
around | +0.032 |
down | +0.028 |
air | +0.028 |
cy | +0.027 |
| | +0.026 |
Neg logit contributions | |
vern | -0.031 |
ves | -0.029 |
ades | -0.027 |
mercy | -0.026 |
backup | -0.026 |
Token | said |
Token ID | 531 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
around | +0.170 |
air | +0.150 |
cy | +0.148 |
down | +0.147 |
et | +0.141 |
Neg logit contributions | |
vern | -0.216 |
ves | -0.216 |
ades | -0.197 |
mercy | -0.194 |
backup | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ves | +0.115 |
vern | +0.115 |
ades | +0.109 |
keys | +0.106 |
backup | +0.106 |
Neg logit contributions | |
around | -0.069 |
down | -0.059 |
cy | -0.051 |
air | -0.050 |
et | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ves | +0.095 |
vern | +0.094 |
ades | +0.086 |
mercy | +0.085 |
keys | +0.084 |
Neg logit contributions | |
around | -0.086 |
cy | -0.077 |
air | -0.077 |
down | -0.075 |
| | -0.073 |
Token | " |
Token ID | 1 |
Feature activation | +9.90e+00 |
Pos logit contributions | |
ves | +0.062 |
vern | +0.061 |
mercy | +0.058 |
forgiveness | +0.055 |
ades | +0.055 |
Neg logit contributions | |
around | -0.092 |
cy | -0.087 |
| | -0.087 |
air | -0.084 |
down | -0.082 |
Token | Ar |
Token ID | 3163 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
vern | +0.670 |
ves | +0.656 |
ades | +0.610 |
mercy | +0.597 |
backup | +0.589 |
Neg logit contributions | |
around | -0.418 |
cy | -0.407 |
air | -0.388 |
et | -0.364 |
| | -0.364 |
Token | rr |
Token ID | 21062 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ves | +0.587 |
vern | +0.562 |
ades | +0.520 |
forgiveness | +0.506 |
keys | +0.495 |
Neg logit contributions | |
around | -0.499 |
et | -0.442 |
cy | -0.438 |
air | -0.436 |
down | -0.429 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ves | +0.080 |
vern | +0.080 |
ades | +0.073 |
mercy | +0.072 |
backup | +0.071 |
Neg logit contributions | |
around | -0.059 |
cy | -0.053 |
air | -0.053 |
down | -0.052 |
et | -0.051 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.67e+01 |
Pos logit contributions | |
vern | +0.066 |
ves | +0.066 |
ades | +0.060 |
keys | +0.054 |
mercy | +0.054 |
Neg logit contributions | |
around | -0.057 |
down | -0.051 |
air | -0.051 |
cy | -0.048 |
through | -0.046 |
Token | y |
Token ID | 88 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
ves | +1.064 |
vern | +1.035 |
ades | +0.979 |
mercy | +0.950 |
keys | +0.932 |
Neg logit contributions | |
around | -0.716 |
air | -0.648 |
cy | -0.630 |
down | -0.620 |
| | -0.608 |
Token | , |
Token ID | 11 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
around | +0.221 |
cy | +0.197 |
air | +0.196 |
down | +0.192 |
et | +0.187 |
Neg logit contributions | |
ves | -0.299 |
vern | -0.296 |
ades | -0.272 |
mercy | -0.267 |
backup | -0.265 |
Token | give |
Token ID | 1577 |
Feature activation | +7.56e+00 |
Pos logit contributions | |
ves | +0.055 |
vern | +0.054 |
ades | +0.049 |
keys | +0.044 |
mercy | +0.043 |
Neg logit contributions | |
around | -0.056 |
down | -0.050 |
air | -0.049 |
cy | -0.047 |
through | -0.046 |
Token | me |
Token ID | 502 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
vern | +0.571 |
ves | +0.569 |
ades | +0.520 |
keys | +0.512 |
mercy | +0.505 |
Neg logit contributions | |
around | -0.290 |
air | -0.241 |
down | -0.239 |
cy | -0.231 |
et | -0.219 |
Token | your |
Token ID | 534 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
around | +0.038 |
down | +0.034 |
et | +0.033 |
air | +0.033 |
cy | +0.031 |
Neg logit contributions | |
ves | -0.043 |
vern | -0.042 |
ades | -0.038 |
keys | -0.037 |
forgiveness | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
vern | +0.096 |
ves | +0.092 |
mercy | +0.087 |
backup | +0.085 |
ades | +0.084 |
Neg logit contributions | |
around | -0.077 |
down | -0.067 |
air | -0.063 |
through | -0.057 |
et | -0.057 |
Token | " |
Token ID | 366 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
ves | +0.051 |
vern | +0.051 |
ades | +0.045 |
mercy | +0.045 |
backup | +0.044 |
Neg logit contributions | |
around | -0.052 |
down | -0.046 |
air | -0.046 |
cy | -0.046 |
et | -0.045 |
Token | Ah |
Token ID | 10910 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ves | +0.221 |
vern | +0.218 |
ades | +0.201 |
mercy | +0.196 |
backup | +0.195 |
Neg logit contributions | |
around | -0.172 |
cy | -0.154 |
air | -0.153 |
down | -0.150 |
et | -0.147 |
Token | oy |
Token ID | 726 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
vern | +0.138 |
ves | +0.133 |
ades | +0.125 |
mercy | +0.123 |
forgiveness | +0.121 |
Neg logit contributions | |
around | -0.138 |
et | -0.132 |
air | -0.129 |
cy | -0.126 |
down | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
ves | +0.382 |
vern | +0.378 |
ades | +0.342 |
mercy | +0.341 |
forgiveness | +0.336 |
Neg logit contributions | |
around | -0.271 |
cy | -0.245 |
down | -0.242 |
air | -0.236 |
et | -0.230 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
vern | +0.047 |
ves | +0.047 |
ades | +0.042 |
mercy | +0.039 |
keys | +0.038 |
Neg logit contributions | |
around | -0.058 |
air | -0.053 |
down | -0.052 |
cy | -0.051 |
et | -0.050 |
Token | y |
Token ID | 88 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
ves | +1.141 |
vern | +1.120 |
ades | +1.066 |
mercy | +1.027 |
backup | +1.015 |
Neg logit contributions | |
around | -0.627 |
air | -0.555 |
down | -0.521 |
cy | -0.521 |
| | -0.516 |
Token | ! |
Token ID | 0 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
around | +0.223 |
cy | +0.199 |
air | +0.198 |
down | +0.194 |
et | +0.189 |
Neg logit contributions | |
ves | -0.307 |
vern | -0.305 |
ades | -0.279 |
mercy | -0.275 |
backup | -0.272 |
Token | Land |
Token ID | 6379 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ves | +0.023 |
vern | +0.022 |
ades | +0.021 |
backup | +0.020 |
mercy | +0.020 |
Neg logit contributions | |
around | -0.015 |
cy | -0.014 |
air | -0.014 |
et | -0.013 |
down | -0.013 |
Token | ho |
Token ID | 8169 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
around | +0.013 |
cy | +0.012 |
air | +0.012 |
down | +0.011 |
et | +0.011 |
Neg logit contributions | |
ves | -0.019 |
vern | -0.018 |
ades | -0.017 |
keys | -0.017 |
backup | -0.016 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
ves | +0.226 |
vern | +0.221 |
ades | +0.202 |
backup | +0.197 |
keys | +0.195 |
Neg logit contributions | |
around | -0.226 |
cy | -0.208 |
air | -0.205 |
down | -0.200 |
et | -0.197 |
Token | You |
Token ID | 921 |
Feature activation | -8.66e+00 |
Pos logit contributions | |
around | +0.014 |
cy | +0.013 |
et | +0.013 |
down | +0.012 |
air | +0.012 |
Neg logit contributions | |
ves | -0.020 |
vern | -0.020 |
backup | -0.018 |
mercy | -0.018 |
forgiveness | -0.018 |
Token | can |
Token ID | 460 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
around | +0.358 |
cy | +0.320 |
down | +0.313 |
air | +0.312 |
et | +0.309 |
Neg logit contributions | |
ves | -0.574 |
vern | -0.573 |
backup | -0.527 |
mercy | -0.526 |
ades | -0.525 |
Token | be |
Token ID | 307 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
around | +0.216 |
cy | +0.192 |
air | +0.187 |
down | +0.185 |
et | +0.180 |
Neg logit contributions | |
ves | -0.313 |
vern | -0.309 |
ades | -0.284 |
mercy | -0.278 |
keys | -0.278 |
Token | the |
Token ID | 262 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
vern | +0.163 |
ves | +0.162 |
backup | +0.142 |
ades | +0.141 |
mercy | +0.140 |
Neg logit contributions | |
around | -0.253 |
cy | -0.243 |
rated | -0.234 |
air | -0.234 |
| | -0.233 |
Token | first |
Token ID | 717 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
around | +0.263 |
air | +0.250 |
cy | +0.241 |
et | +0.238 |
down | +0.237 |
Neg logit contributions | |
ves | -0.187 |
vern | -0.168 |
ades | -0.151 |
keys | -0.147 |
mercy | -0.141 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
around | +0.164 |
air | +0.149 |
cy | +0.146 |
down | +0.146 |
et | +0.144 |
Neg logit contributions | |
vern | -0.138 |
ves | -0.133 |
ades | -0.121 |
mercy | -0.118 |
keys | -0.116 |
Token | today |
Token ID | 1909 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
ves | +0.987 |
vern | +0.969 |
ades | +0.903 |
mercy | +0.883 |
keys | +0.876 |
Neg logit contributions | |
around | -0.748 |
air | -0.709 |
cy | -0.674 |
down | -0.665 |
| | -0.660 |
Token | ." |
Token ID | 526 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
around | +0.034 |
cy | +0.032 |
| | +0.031 |
rated | +0.031 |
et | +0.031 |
Neg logit contributions | |
ves | -0.040 |
vern | -0.037 |
ades | -0.035 |
keys | -0.034 |
mercy | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
around | +0.120 |
cy | +0.107 |
air | +0.107 |
down | +0.105 |
| | +0.099 |
Neg logit contributions | |
ves | -0.167 |
vern | -0.165 |
ades | -0.151 |
mercy | -0.149 |
keys | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
vern | +0.051 |
ves | +0.051 |
keys | +0.048 |
mercy | +0.048 |
backup | +0.048 |
Neg logit contributions | |
around | -0.035 |
air | -0.030 |
cy | -0.029 |
down | -0.029 |
| | -0.027 |
Token | They |
Token ID | 2990 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
vern | +0.040 |
mercy | +0.038 |
backup | +0.037 |
crew | +0.037 |
instincts | +0.037 |
Neg logit contributions | |
around | -0.040 |
cy | -0.040 |
air | -0.038 |
ny | -0.037 |
he | -0.035 |
Token | shouting |
Token ID | 19642 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ves | +0.056 |
vern | +0.055 |
ades | +0.050 |
mercy | +0.049 |
backup | +0.049 |
Neg logit contributions | |
around | -0.046 |
cy | -0.042 |
air | -0.041 |
down | -0.040 |
et | -0.040 |
Token | " |
Token ID | 366 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
ves | +0.070 |
vern | +0.070 |
ades | +0.064 |
mercy | +0.063 |
backup | +0.063 |
Neg logit contributions | |
around | -0.046 |
cy | -0.041 |
air | -0.041 |
down | -0.040 |
et | -0.039 |
Token | Ah |
Token ID | 10910 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ves | +0.190 |
vern | +0.178 |
ades | +0.172 |
keys | +0.164 |
backup | +0.160 |
Neg logit contributions | |
around | -0.199 |
air | -0.180 |
cy | -0.177 |
down | -0.177 |
ening | -0.171 |
Token | oy |
Token ID | 726 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
vern | +0.121 |
ves | +0.110 |
forgiveness | +0.108 |
mercy | +0.107 |
ades | +0.101 |
Neg logit contributions | |
around | -0.157 |
et | -0.157 |
air | -0.148 |
down | -0.145 |
cy | -0.143 |
Token | , |
Token ID | 11 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
ves | +0.353 |
vern | +0.350 |
ades | +0.318 |
mercy | +0.314 |
backup | +0.309 |
Neg logit contributions | |
around | -0.292 |
cy | -0.263 |
air | -0.261 |
down | -0.257 |
et | -0.251 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
vern | +0.048 |
ves | +0.047 |
ades | +0.042 |
forgiveness | +0.040 |
mercy | +0.040 |
Neg logit contributions | |
around | -0.056 |
air | -0.052 |
down | -0.050 |
cy | -0.050 |
et | -0.049 |
Token | y |
Token ID | 88 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
ves | +1.157 |
vern | +1.129 |
ades | +1.078 |
mercy | +1.034 |
keys | +1.029 |
Neg logit contributions | |
around | -0.621 |
air | -0.545 |
cy | -0.514 |
down | -0.513 |
| | -0.507 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
around | +0.224 |
cy | +0.200 |
air | +0.199 |
down | +0.195 |
et | +0.190 |
Neg logit contributions | |
ves | -0.304 |
vern | -0.302 |
ades | -0.276 |
mercy | -0.273 |
backup | -0.270 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
around | +0.027 |
cy | +0.025 |
et | +0.025 |
rated | +0.025 |
ening | +0.024 |
Neg logit contributions | |
ves | -0.048 |
vern | -0.044 |
ades | -0.044 |
keys | -0.042 |
backup | -0.042 |
Token | " |
Token ID | 366 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
around | +0.079 |
cy | +0.072 |
air | +0.071 |
down | +0.070 |
et | +0.069 |
Neg logit contributions | |
ves | -0.089 |
vern | -0.087 |
ades | -0.079 |
mercy | -0.078 |
backup | -0.077 |
Token | Sh |
Token ID | 2484 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
ves | +0.180 |
vern | +0.176 |
ades | +0.160 |
mercy | +0.154 |
backup | +0.154 |
Neg logit contributions | |
around | -0.211 |
cy | -0.194 |
air | -0.192 |
down | -0.190 |
et | -0.186 |
Token | It |
Token ID | 632 |
Feature activation | -9.32e+00 |
Pos logit contributions | |
around | +0.011 |
cy | +0.010 |
et | +0.010 |
rated | +0.009 |
down | +0.009 |
Neg logit contributions | |
ves | -0.023 |
vern | -0.023 |
forgiveness | -0.021 |
mercy | -0.021 |
backup | -0.021 |
Token | needs |
Token ID | 2476 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
around | +0.377 |
cy | +0.340 |
down | +0.333 |
air | +0.330 |
rated | +0.325 |
Neg logit contributions | |
ves | -0.621 |
vern | -0.600 |
mercy | -0.556 |
keys | -0.554 |
ades | -0.548 |
Token | to |
Token ID | 284 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ves | +0.010 |
vern | +0.010 |
ades | +0.010 |
keys | +0.009 |
His | +0.008 |
Neg logit contributions | |
around | -0.009 |
air | -0.009 |
down | -0.008 |
through | -0.007 |
night | -0.007 |
Token | find |
Token ID | 1064 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
vern | +0.183 |
ves | +0.182 |
ades | +0.177 |
keys | +0.166 |
mercy | +0.157 |
Neg logit contributions | |
around | -0.136 |
air | -0.129 |
down | -0.119 |
| | -0.117 |
et | -0.115 |
Token | a |
Token ID | 257 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
vern | +0.097 |
ves | +0.096 |
ades | +0.089 |
keys | +0.085 |
His | +0.079 |
Neg logit contributions | |
around | -0.136 |
air | -0.127 |
down | -0.122 |
et | -0.115 |
through | -0.113 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
ves | +0.302 |
vern | +0.293 |
ades | +0.279 |
keys | +0.268 |
mercy | +0.266 |
Neg logit contributions | |
around | -0.224 |
air | -0.209 |
down | -0.204 |
cy | -0.199 |
night | -0.185 |
Token | and |
Token ID | 290 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ves | +1.048 |
vern | +1.033 |
ades | +0.954 |
mercy | +0.936 |
keys | +0.924 |
Neg logit contributions | |
around | -0.740 |
air | -0.669 |
cy | -0.665 |
down | -0.644 |
et | -0.633 |
Token | lay |
Token ID | 3830 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
around | +0.085 |
air | +0.078 |
down | +0.076 |
alone | +0.068 |
through | +0.068 |
Neg logit contributions | |
vern | -0.093 |
ves | -0.091 |
ades | -0.088 |
keys | -0.078 |
instincts | -0.073 |
Token | eggs |
Token ID | 9653 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
| | +0.068 |
cy | +0.065 |
around | +0.065 |
amp | +0.063 |
rated | +0.063 |
Neg logit contributions | |
ves | -0.101 |
vern | -0.094 |
ades | -0.090 |
mercy | -0.089 |
forgiveness | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
ves | +0.267 |
vern | +0.264 |
ades | +0.241 |
mercy | +0.238 |
keys | +0.237 |
Neg logit contributions | |
around | -0.179 |
cy | -0.169 |
air | -0.166 |
| | -0.161 |
et | -0.158 |
Token | Then |
Token ID | 3244 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
around | +0.013 |
cy | +0.012 |
et | +0.011 |
down | +0.011 |
air | +0.011 |
Neg logit contributions | |
ves | -0.022 |
vern | -0.021 |
mercy | -0.020 |
backup | -0.020 |
ades | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
vern | +0.050 |
ves | +0.049 |
mercy | +0.047 |
forgiveness | +0.046 |
backup | +0.046 |
Neg logit contributions | |
around | -0.036 |
air | -0.030 |
cy | -0.030 |
down | -0.029 |
| | -0.029 |
Token | " |
Token ID | 1 |
Feature activation | +9.41e+00 |
Pos logit contributions | |
forgiveness | +0.041 |
vern | +0.041 |
mercy | +0.041 |
instincts | +0.038 |
backup | +0.035 |
Neg logit contributions | |
around | -0.046 |
air | -0.040 |
cy | -0.039 |
down | -0.039 |
ny | -0.038 |
Token | Ar |
Token ID | 3163 |
Feature activation | +9.66e+00 |
Pos logit contributions | |
vern | +0.772 |
ves | +0.747 |
instincts | +0.701 |
mercy | +0.700 |
ades | +0.691 |
Neg logit contributions | |
cy | -0.251 |
around | -0.249 |
air | -0.243 |
| | -0.218 |
et | -0.199 |
Token | rr |
Token ID | 21062 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ves | +0.571 |
vern | +0.554 |
forgiveness | +0.516 |
mercy | +0.512 |
wife | +0.509 |
Neg logit contributions | |
around | -0.436 |
cy | -0.401 |
et | -0.389 |
| | -0.386 |
air | -0.369 |
Token | , |
Token ID | 11 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
ves | +0.065 |
vern | +0.065 |
mercy | +0.059 |
ades | +0.059 |
forgiveness | +0.059 |
Neg logit contributions | |
around | -0.047 |
cy | -0.042 |
air | -0.041 |
down | -0.041 |
et | -0.040 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
vern | +0.042 |
ves | +0.041 |
ades | +0.038 |
His | +0.031 |
keys | +0.031 |
Neg logit contributions | |
around | -0.063 |
air | -0.058 |
down | -0.057 |
through | -0.054 |
cy | -0.053 |
Token | y |
Token ID | 88 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
ves | +1.205 |
vern | +1.181 |
ades | +1.119 |
mercy | +1.092 |
keys | +1.078 |
Neg logit contributions | |
around | -0.585 |
air | -0.508 |
cy | -0.486 |
down | -0.485 |
et | -0.465 |
Token | , |
Token ID | 11 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
around | +0.216 |
air | +0.193 |
cy | +0.192 |
down | +0.187 |
et | +0.183 |
Neg logit contributions | |
vern | -0.316 |
ves | -0.315 |
ades | -0.289 |
mercy | -0.284 |
backup | -0.283 |
Token | let |
Token ID | 1309 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
vern | +0.039 |
ves | +0.039 |
ades | +0.034 |
keys | +0.030 |
mercy | +0.029 |
Neg logit contributions | |
around | -0.065 |
air | -0.060 |
down | -0.060 |
through | -0.056 |
cy | -0.056 |
Token | 's |
Token ID | 338 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ves | +0.036 |
vern | +0.035 |
ades | +0.032 |
mercy | +0.032 |
backup | +0.032 |
Neg logit contributions | |
around | -0.027 |
cy | -0.024 |
air | -0.024 |
down | -0.023 |
et | -0.023 |
Token | sail |
Token ID | 14936 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
ves | +0.134 |
vern | +0.133 |
ades | +0.121 |
mercy | +0.119 |
backup | +0.117 |
Neg logit contributions | |
around | -0.113 |
cy | -0.101 |
air | -0.100 |
down | -0.099 |
et | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
vern | +0.051 |
ves | +0.050 |
mercy | +0.049 |
forgiveness | +0.047 |
keys | +0.047 |
Neg logit contributions | |
around | -0.036 |
cy | -0.031 |
| | -0.030 |
air | -0.030 |
down | -0.030 |
Token | " |
Token ID | 1 |
Feature activation | +9.42e+00 |
Pos logit contributions | |
mercy | +0.038 |
vern | +0.038 |
forgiveness | +0.037 |
backup | +0.033 |
ves | +0.033 |
Neg logit contributions | |
around | -0.048 |
cy | -0.045 |
ny | -0.043 |
air | -0.042 |
et | -0.041 |
Token | Ar |
Token ID | 3163 |
Feature activation | +9.70e+00 |
Pos logit contributions | |
vern | +0.607 |
ves | +0.580 |
mercy | +0.537 |
ades | +0.532 |
backup | +0.527 |
Neg logit contributions | |
around | -0.448 |
cy | -0.432 |
air | -0.406 |
| | -0.388 |
down | -0.385 |
Token | rr |
Token ID | 21062 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ves | +0.571 |
vern | +0.550 |
mercy | +0.511 |
forgiveness | +0.505 |
wife | +0.504 |
Neg logit contributions | |
around | -0.452 |
cy | -0.417 |
| | -0.401 |
et | -0.395 |
down | -0.380 |
Token | , |
Token ID | 11 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
ves | +0.064 |
vern | +0.064 |
ades | +0.058 |
mercy | +0.057 |
backup | +0.057 |
Neg logit contributions | |
around | -0.050 |
cy | -0.045 |
air | -0.045 |
down | -0.044 |
et | -0.043 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
vern | +0.056 |
ves | +0.056 |
ades | +0.052 |
mercy | +0.047 |
His | +0.046 |
Neg logit contributions | |
around | -0.050 |
air | -0.044 |
down | -0.043 |
cy | -0.041 |
through | -0.040 |
Token | y |
Token ID | 88 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
ves | +1.182 |
vern | +1.158 |
ades | +1.119 |
mercy | +1.081 |
keys | +1.052 |
Neg logit contributions | |
around | -0.557 |
air | -0.498 |
down | -0.454 |
| | -0.446 |
et | -0.439 |
Token | , |
Token ID | 11 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
around | +0.233 |
cy | +0.211 |
air | +0.207 |
down | +0.204 |
| | +0.200 |
Neg logit contributions | |
ves | -0.294 |
vern | -0.288 |
ades | -0.264 |
mercy | -0.261 |
keys | -0.257 |
Token | this |
Token ID | 428 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ves | +0.052 |
vern | +0.052 |
ades | +0.048 |
mercy | +0.044 |
keys | +0.043 |
Neg logit contributions | |
around | -0.053 |
air | -0.046 |
down | -0.046 |
cy | -0.044 |
et | -0.043 |
Token | is |
Token ID | 318 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
vern | +0.209 |
ves | +0.206 |
ades | +0.192 |
mercy | +0.191 |
backup | +0.189 |
Neg logit contributions | |
around | -0.114 |
air | -0.102 |
cy | -0.097 |
et | -0.095 |
down | -0.094 |
Token | our |
Token ID | 674 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
around | +0.056 |
air | +0.051 |
down | +0.050 |
cy | +0.050 |
et | +0.049 |
Neg logit contributions | |
ves | -0.052 |
vern | -0.051 |
ades | -0.047 |
mercy | -0.045 |
keys | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
vern | +0.047 |
ves | +0.046 |
mercy | +0.044 |
forgiveness | +0.043 |
keys | +0.043 |
Neg logit contributions | |
around | -0.036 |
cy | -0.031 |
air | -0.030 |
down | -0.030 |
| | -0.030 |
Token | " |
Token ID | 1 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
vern | +0.035 |
mercy | +0.034 |
forgiveness | +0.033 |
ves | +0.030 |
instincts | +0.030 |
Neg logit contributions | |
around | -0.048 |
cy | -0.044 |
down | -0.042 |
air | -0.042 |
et | -0.042 |
Token | Ar |
Token ID | 3163 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
vern | +0.694 |
ves | +0.670 |
mercy | +0.625 |
ades | +0.618 |
backup | +0.611 |
Neg logit contributions | |
around | -0.349 |
cy | -0.328 |
air | -0.312 |
| | -0.301 |
et | -0.294 |
Token | rr |
Token ID | 21062 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ves | +0.570 |
vern | +0.550 |
mercy | +0.516 |
forgiveness | +0.508 |
ades | +0.497 |
Neg logit contributions | |
around | -0.451 |
cy | -0.415 |
| | -0.399 |
et | -0.396 |
down | -0.380 |
Token | , |
Token ID | 11 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
ves | +0.063 |
vern | +0.063 |
ades | +0.057 |
mercy | +0.056 |
backup | +0.056 |
Neg logit contributions | |
around | -0.047 |
cy | -0.042 |
air | -0.042 |
down | -0.041 |
et | -0.040 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
vern | +0.049 |
ves | +0.048 |
ades | +0.043 |
mercy | +0.041 |
keys | +0.039 |
Neg logit contributions | |
around | -0.053 |
air | -0.047 |
down | -0.047 |
cy | -0.045 |
| | -0.043 |
Token | y |
Token ID | 88 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
ves | +1.192 |
vern | +1.167 |
ades | +1.121 |
mercy | +1.083 |
keys | +1.065 |
Neg logit contributions | |
around | -0.566 |
air | -0.501 |
down | -0.466 |
cy | -0.454 |
| | -0.450 |
Token | , |
Token ID | 11 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
around | +0.231 |
cy | +0.209 |
air | +0.206 |
down | +0.202 |
| | +0.198 |
Neg logit contributions | |
ves | -0.299 |
vern | -0.292 |
ades | -0.270 |
mercy | -0.265 |
keys | -0.262 |
Token | we |
Token ID | 356 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
vern | +0.051 |
ves | +0.050 |
ades | +0.045 |
mercy | +0.043 |
keys | +0.042 |
Neg logit contributions | |
around | -0.052 |
air | -0.046 |
down | -0.045 |
cy | -0.044 |
et | -0.043 |
Token | are |
Token ID | 389 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
vern | +0.368 |
ves | +0.366 |
backup | +0.340 |
ades | +0.335 |
mercy | +0.333 |
Neg logit contributions | |
around | -0.264 |
down | -0.241 |
air | -0.239 |
cy | -0.233 |
ening | -0.232 |
Token | the |
Token ID | 262 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ves | +0.033 |
vern | +0.033 |
ades | +0.029 |
backup | +0.029 |
mercy | +0.029 |
Neg logit contributions | |
around | -0.038 |
cy | -0.036 |
air | -0.035 |
down | -0.034 |
et | -0.034 |
Token | said |
Token ID | 531 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
around | +0.080 |
down | +0.073 |
air | +0.065 |
cy | +0.063 |
through | +0.063 |
Neg logit contributions | |
vern | -0.115 |
ves | -0.104 |
ades | -0.100 |
mercy | -0.094 |
backup | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
vern | +0.110 |
ves | +0.107 |
mercy | +0.102 |
forgiveness | +0.100 |
backup | +0.100 |
Neg logit contributions | |
around | -0.059 |
down | -0.053 |
air | -0.043 |
through | -0.041 |
et | -0.038 |
Token | " |
Token ID | 366 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
ves | +0.047 |
vern | +0.046 |
ades | +0.042 |
mercy | +0.041 |
backup | +0.040 |
Neg logit contributions | |
around | -0.050 |
cy | -0.046 |
air | -0.046 |
down | -0.045 |
et | -0.044 |
Token | Ah |
Token ID | 10910 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ves | +0.239 |
vern | +0.236 |
ades | +0.220 |
mercy | +0.215 |
backup | +0.214 |
Neg logit contributions | |
around | -0.149 |
cy | -0.130 |
air | -0.130 |
down | -0.127 |
et | -0.124 |
Token | oy |
Token ID | 726 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
vern | +0.116 |
ves | +0.115 |
ades | +0.104 |
mercy | +0.101 |
forgiveness | +0.098 |
Neg logit contributions | |
around | -0.155 |
et | -0.149 |
cy | -0.144 |
air | -0.144 |
down | -0.143 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
ves | +0.379 |
vern | +0.373 |
ades | +0.339 |
mercy | +0.335 |
forgiveness | +0.329 |
Neg logit contributions | |
around | -0.271 |
cy | -0.245 |
down | -0.240 |
air | -0.236 |
et | -0.229 |
Token | y |
Token ID | 88 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
ves | +1.163 |
vern | +1.153 |
ades | +1.101 |
mercy | +1.068 |
backup | +1.050 |
Neg logit contributions | |
around | -0.578 |
air | -0.517 |
cy | -0.472 |
| | -0.468 |
et | -0.468 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
around | +0.220 |
cy | +0.196 |
air | +0.196 |
down | +0.192 |
et | +0.186 |
Neg logit contributions | |
ves | -0.314 |
vern | -0.313 |
ades | -0.285 |
mercy | -0.281 |
backup | -0.278 |
Token | to |
Token ID | 284 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
around | +0.029 |
cy | +0.026 |
air | +0.025 |
et | +0.025 |
down | +0.024 |
Neg logit contributions | |
ves | -0.052 |
vern | -0.050 |
ades | -0.047 |
mercy | -0.046 |
backup | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
vern | +0.223 |
ves | +0.218 |
ades | +0.208 |
keys | +0.203 |
eed | +0.188 |
Neg logit contributions | |
around | -0.114 |
down | -0.098 |
air | -0.094 |
through | -0.088 |
alone | -0.087 |
Token | pirate |
Token ID | 25868 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
around | +0.267 |
air | +0.265 |
down | +0.249 |
cy | +0.239 |
night | +0.237 |
Neg logit contributions | |
vern | -0.191 |
ves | -0.187 |
ades | -0.164 |
keys | -0.160 |
mercy | -0.151 |
Token | say |
Token ID | 910 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
around | +0.247 |
down | +0.216 |
air | +0.211 |
cy | +0.211 |
et | +0.202 |
Neg logit contributions | |
ves | -0.291 |
vern | -0.290 |
ades | -0.265 |
forgiveness | -0.257 |
backup | -0.257 |
Token | ' |
Token ID | 705 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
around | +0.017 |
air | +0.015 |
down | +0.015 |
et | +0.014 |
through | +0.013 |
Neg logit contributions | |
vern | -0.015 |
ves | -0.014 |
ades | -0.013 |
mercy | -0.013 |
keys | -0.012 |
Token | Ah |
Token ID | 10910 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
ves | +0.375 |
vern | +0.346 |
ades | +0.336 |
keys | +0.334 |
backup | +0.309 |
Neg logit contributions | |
around | -0.363 |
air | -0.332 |
down | -0.318 |
rated | -0.316 |
ening | -0.315 |
Token | oy |
Token ID | 726 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
vern | +0.142 |
ves | +0.134 |
mercy | +0.129 |
ades | +0.127 |
forgiveness | +0.124 |
Neg logit contributions | |
around | -0.132 |
et | -0.125 |
air | -0.119 |
cy | -0.117 |
down | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
ves | +0.328 |
vern | +0.324 |
ades | +0.290 |
mercy | +0.288 |
backup | +0.282 |
Neg logit contributions | |
around | -0.316 |
cy | -0.288 |
down | -0.283 |
air | -0.282 |
et | -0.273 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
vern | +0.041 |
ves | +0.041 |
ades | +0.036 |
mercy | +0.034 |
forgiveness | +0.033 |
Neg logit contributions | |
around | -0.060 |
down | -0.055 |
air | -0.054 |
cy | -0.053 |
et | -0.053 |
Token | y |
Token ID | 88 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
ves | +1.297 |
vern | +1.282 |
ades | +1.208 |
mercy | +1.185 |
keys | +1.176 |
Neg logit contributions | |
around | -0.496 |
air | -0.417 |
cy | -0.407 |
down | -0.396 |
et | -0.382 |
Token | !' |
Token ID | 13679 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
around | +0.242 |
cy | +0.218 |
air | +0.218 |
down | +0.213 |
et | +0.207 |
Neg logit contributions | |
ves | -0.291 |
vern | -0.291 |
ades | -0.263 |
mercy | -0.259 |
backup | -0.257 |
Token | and |
Token ID | 290 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ves | +0.123 |
vern | +0.122 |
ades | +0.113 |
keys | +0.111 |
mercy | +0.109 |
Neg logit contributions | |
around | -0.073 |
air | -0.065 |
down | -0.064 |
cy | -0.060 |
et | -0.056 |
Token | ' |
Token ID | 705 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
around | +0.084 |
cy | +0.077 |
air | +0.076 |
down | +0.074 |
et | +0.073 |
Neg logit contributions | |
ves | -0.087 |
vern | -0.085 |
ades | -0.078 |
mercy | -0.077 |
backup | -0.076 |
Token | Land |
Token ID | 22342 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ves | +0.355 |
vern | +0.344 |
ades | +0.322 |
keys | +0.311 |
backup | +0.307 |
Neg logit contributions | |
around | -0.383 |
air | -0.349 |
cy | -0.340 |
down | -0.339 |
et | -0.334 |
Token | , |
Token ID | 11 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
vern | +0.113 |
ves | +0.111 |
keys | +0.107 |
ades | +0.105 |
mercy | +0.105 |
Neg logit contributions | |
around | -0.055 |
down | -0.048 |
air | -0.039 |
through | -0.036 |
et | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
vern | +0.053 |
ves | +0.052 |
mercy | +0.047 |
ades | +0.047 |
backup | +0.046 |
Neg logit contributions | |
around | -0.048 |
down | -0.043 |
air | -0.042 |
cy | -0.040 |
et | -0.039 |
Token | Ah |
Token ID | 10910 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ves | +0.206 |
vern | +0.203 |
ades | +0.186 |
mercy | +0.182 |
backup | +0.181 |
Neg logit contributions | |
around | -0.183 |
cy | -0.165 |
air | -0.164 |
down | -0.162 |
et | -0.158 |
Token | oy |
Token ID | 726 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
vern | +0.170 |
ves | +0.167 |
ades | +0.161 |
keys | +0.153 |
mercy | +0.153 |
Neg logit contributions | |
around | -0.104 |
et | -0.096 |
air | -0.095 |
down | -0.092 |
cy | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
ves | +0.382 |
vern | +0.380 |
ades | +0.345 |
mercy | +0.341 |
forgiveness | +0.335 |
Neg logit contributions | |
around | -0.263 |
cy | -0.236 |
down | -0.234 |
air | -0.230 |
et | -0.222 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
vern | +0.041 |
ves | +0.040 |
ades | +0.037 |
keys | +0.033 |
mercy | +0.031 |
Neg logit contributions | |
around | -0.061 |
air | -0.056 |
down | -0.055 |
et | -0.054 |
cy | -0.053 |
Token | y |
Token ID | 88 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
ves | +1.132 |
vern | +1.109 |
ades | +1.058 |
mercy | +1.023 |
backup | +1.007 |
Neg logit contributions | |
around | -0.626 |
air | -0.550 |
down | -0.517 |
| | -0.515 |
cy | -0.515 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
around | +0.222 |
cy | +0.199 |
air | +0.198 |
down | +0.193 |
et | +0.188 |
Neg logit contributions | |
ves | -0.311 |
vern | -0.309 |
ades | -0.283 |
mercy | -0.279 |
backup | -0.276 |
Token | I |
Token ID | 314 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
around | +0.015 |
cy | +0.014 |
air | +0.014 |
down | +0.013 |
et | +0.013 |
Neg logit contributions | |
ves | -0.023 |
vern | -0.022 |
ades | -0.021 |
mercy | -0.020 |
backup | -0.020 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ves | +0.092 |
vern | +0.091 |
ades | +0.084 |
mercy | +0.082 |
backup | +0.082 |
Neg logit contributions | |
around | -0.062 |
cy | -0.055 |
air | -0.054 |
down | -0.053 |
et | -0.052 |
Token | Captain |
Token ID | 8599 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
vern | +0.107 |
ves | +0.106 |
backup | +0.097 |
mercy | +0.094 |
ades | +0.093 |
Neg logit contributions | |
cy | -0.113 |
around | -0.112 |
rated | -0.105 |
air | -0.105 |
| | -0.103 |
Token | shouted |
Token ID | 17293 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
around | +0.050 |
et | +0.042 |
air | +0.042 |
cy | +0.042 |
down | +0.041 |
Neg logit contributions | |
vern | -0.068 |
ves | -0.064 |
ades | -0.061 |
backup | -0.061 |
mercy | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
ves | +0.001 |
vern | +0.001 |
ades | +0.001 |
mercy | +0.001 |
keys | +0.001 |
Neg logit contributions | |
around | -0.001 |
down | -0.001 |
air | -0.001 |
cy | -0.001 |
et | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
ves | +0.050 |
vern | +0.049 |
ades | +0.045 |
mercy | +0.044 |
backup | +0.043 |
Neg logit contributions | |
around | -0.055 |
cy | -0.050 |
air | -0.050 |
down | -0.049 |
et | -0.048 |
Token | Ar |
Token ID | 3163 |
Feature activation | +9.67e+00 |
Pos logit contributions | |
ves | +0.203 |
vern | +0.203 |
ades | +0.183 |
mercy | +0.178 |
backup | +0.177 |
Neg logit contributions | |
around | -0.193 |
cy | -0.180 |
air | -0.175 |
down | -0.171 |
et | -0.170 |
Token | gh |
Token ID | 456 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
ves | +0.564 |
vern | +0.533 |
ades | +0.492 |
forgiveness | +0.483 |
keys | +0.473 |
Neg logit contributions | |
around | -0.481 |
et | -0.439 |
cy | -0.433 |
down | -0.414 |
air | -0.410 |
Token | mate |
Token ID | 16133 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
ves | +0.158 |
vern | +0.157 |
mercy | +0.145 |
forgiveness | +0.142 |
ades | +0.142 |
Neg logit contributions | |
around | -0.110 |
cy | -0.098 |
down | -0.098 |
et | -0.094 |
air | -0.092 |
Token | ys |
Token ID | 893 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ves | +1.137 |
vern | +1.112 |
ades | +1.058 |
mercy | +1.027 |
keys | +1.013 |
Neg logit contributions | |
around | -0.620 |
air | -0.562 |
cy | -0.533 |
down | -0.520 |
| | -0.514 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
around | +0.078 |
cy | +0.070 |
air | +0.069 |
down | +0.068 |
et | +0.066 |
Neg logit contributions | |
ves | -0.107 |
vern | -0.105 |
ades | -0.097 |
mercy | -0.095 |
backup | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
around | +0.034 |
air | +0.030 |
cy | +0.030 |
down | +0.030 |
et | +0.028 |
Neg logit contributions | |
vern | -0.052 |
ves | -0.051 |
ades | -0.047 |
mercy | -0.046 |
backup | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
vern | +0.047 |
mercy | +0.045 |
forgiveness | +0.044 |
ves | +0.044 |
instincts | +0.043 |
Neg logit contributions | |
around | -0.027 |
| | -0.024 |
cy | -0.021 |
amp | -0.021 |
air | -0.021 |
Token | The |
Token ID | 464 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
vern | +0.035 |
forgiveness | +0.034 |
mercy | +0.033 |
instincts | +0.031 |
ves | +0.031 |
Neg logit contributions | |
| | -0.035 |
around | -0.034 |
ny | -0.032 |
amp | -0.032 |
cy | -0.031 |
Token | â |
Token ID | 22940 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
around | +0.023 |
et | +0.021 |
rated | +0.021 |
cy | +0.021 |
down | +0.020 |
Neg logit contributions | |
vern | -0.034 |
ves | -0.034 |
backup | -0.031 |
forgiveness | -0.031 |
ades | -0.031 |
Token | € |
Token ID | 26391 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
around | +0.069 |
down | +0.062 |
through | +0.056 |
cy | +0.054 |
ening | +0.052 |
Neg logit contributions | |
vern | -0.101 |
ves | -0.101 |
ggy | -0.093 |
forgiveness | -0.091 |
His | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
around | +0.862 |
cy | +0.788 |
air | +0.777 |
et | +0.773 |
down | +0.772 |
Neg logit contributions | |
ves | -0.793 |
vern | -0.750 |
ades | -0.685 |
keys | -0.659 |
backup | -0.627 |
Token |
|
Token ID | 198 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
ves | +0.032 |
vern | +0.032 |
mercy | +0.029 |
ades | +0.029 |
backup | +0.029 |
Neg logit contributions | |
around | -0.028 |
air | -0.025 |
cy | -0.025 |
down | -0.024 |
| | -0.024 |
Token | M |
Token ID | 44 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
vern | +0.024 |
ves | +0.024 |
mercy | +0.023 |
backup | +0.022 |
forgiveness | +0.022 |
Neg logit contributions | |
around | -0.033 |
| | -0.030 |
cy | -0.030 |
amp | -0.029 |
air | -0.029 |
Token | az |
Token ID | 1031 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
ves | +0.249 |
vern | +0.244 |
ades | +0.214 |
mercy | +0.211 |
backup | +0.207 |
Neg logit contributions | |
around | -0.392 |
cy | -0.365 |
air | -0.363 |
down | -0.356 |
et | -0.353 |
Token | zy |
Token ID | 7357 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
around | +0.640 |
air | +0.597 |
cy | +0.593 |
down | +0.587 |
| | +0.544 |
Neg logit contributions | |
ves | -1.145 |
vern | -1.004 |
ades | -0.970 |
ggy | -0.961 |
keys | -0.937 |
Token | could |
Token ID | 714 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
around | +0.555 |
cy | +0.504 |
air | +0.503 |
down | +0.503 |
| | +0.491 |
Neg logit contributions | |
ves | -0.611 |
vern | -0.568 |
ades | -0.535 |
keys | -0.530 |
mercy | -0.512 |
Token | barely |
Token ID | 8523 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
around | +0.294 |
air | +0.257 |
down | +0.256 |
cy | +0.250 |
et | +0.243 |
Neg logit contributions | |
vern | -0.277 |
ves | -0.275 |
ades | -0.253 |
mercy | -0.245 |
backup | -0.244 |
Token | contain |
Token ID | 3994 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
ves | +0.279 |
vern | +0.278 |
ades | +0.256 |
mercy | +0.244 |
backup | +0.242 |
Neg logit contributions | |
around | -0.271 |
cy | -0.239 |
air | -0.238 |
down | -0.235 |
et | -0.230 |
Token | her |
Token ID | 607 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
around | +0.012 |
air | +0.010 |
down | +0.010 |
cy | +0.010 |
et | +0.010 |
Neg logit contributions | |
ves | -0.015 |
vern | -0.015 |
ades | -0.014 |
keys | -0.014 |
mercy | -0.014 |
Token | ors |
Token ID | 669 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
around | +0.806 |
cy | +0.754 |
air | +0.737 |
down | +0.726 |
| | +0.716 |
Neg logit contributions | |
ves | -0.966 |
vern | -0.870 |
ades | -0.829 |
keys | -0.783 |
ggy | -0.778 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
air | +0.248 |
cy | +0.243 |
rated | +0.241 |
| | +0.236 |
amp | +0.231 |
Neg logit contributions | |
ves | -0.268 |
vern | -0.239 |
keys | -0.239 |
ades | -0.233 |
else | -0.232 |
Token | The |
Token ID | 383 |
Feature activation | -8.33e+00 |
Pos logit contributions | |
around | +0.022 |
rated | +0.020 |
cy | +0.020 |
et | +0.020 |
down | +0.019 |
Neg logit contributions | |
ves | -0.037 |
vern | -0.035 |
ades | -0.034 |
His | -0.034 |
forgiveness | -0.033 |
Token | other |
Token ID | 584 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
around | +0.494 |
cy | +0.454 |
air | +0.450 |
down | +0.444 |
et | +0.436 |
Neg logit contributions | |
ves | -0.418 |
vern | -0.411 |
ades | -0.369 |
mercy | -0.361 |
backup | -0.357 |
Token | r |
Token ID | 374 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ves | +0.052 |
vern | +0.050 |
ades | +0.047 |
forgiveness | +0.046 |
mercy | +0.045 |
Neg logit contributions | |
around | -0.065 |
| | -0.061 |
cy | -0.059 |
down | -0.059 |
rated | -0.058 |
Token | az |
Token ID | 1031 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
vern | +0.158 |
ves | +0.155 |
ades | +0.152 |
mercy | +0.137 |
forgiveness | +0.137 |
Neg logit contributions | |
around | -0.132 |
| | -0.120 |
down | -0.119 |
cy | -0.117 |
air | -0.115 |
Token | ors |
Token ID | 669 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
around | +0.801 |
cy | +0.756 |
air | +0.747 |
down | +0.737 |
| | +0.706 |
Neg logit contributions | |
ves | -0.979 |
vern | -0.870 |
ades | -0.835 |
ggy | -0.782 |
keys | -0.777 |
Token | would |
Token ID | 561 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
air | +0.240 |
amp | +0.230 |
| | +0.230 |
around | +0.229 |
rated | +0.228 |
Neg logit contributions | |
ves | -0.274 |
vern | -0.246 |
ades | -0.245 |
keys | -0.236 |
else | -0.234 |
Token | laugh |
Token ID | 6487 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
around | +0.144 |
air | +0.127 |
cy | +0.125 |
down | +0.125 |
et | +0.122 |
Neg logit contributions | |
ves | -0.164 |
vern | -0.162 |
ades | -0.149 |
keys | -0.144 |
mercy | -0.143 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
cy | +0.108 |
| | +0.102 |
around | +0.102 |
air | +0.101 |
rated | +0.096 |
Neg logit contributions | |
ves | -0.148 |
vern | -0.140 |
ades | -0.134 |
keys | -0.127 |
forgiveness | -0.125 |
Token | say |
Token ID | 910 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
around | +0.091 |
cy | +0.083 |
air | +0.081 |
down | +0.080 |
et | +0.079 |
Neg logit contributions | |
ves | -0.103 |
vern | -0.101 |
ades | -0.092 |
mercy | -0.091 |
backup | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
ves | +0.163 |
vern | +0.160 |
ades | +0.147 |
mercy | +0.144 |
backup | +0.143 |
Neg logit contributions | |
around | -0.137 |
cy | -0.124 |
air | -0.123 |
down | -0.120 |
et | -0.118 |
Token | park |
Token ID | 3952 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
around | +0.219 |
cy | +0.199 |
air | +0.197 |
down | +0.194 |
et | +0.190 |
Neg logit contributions | |
ves | -0.242 |
vern | -0.239 |
ades | -0.218 |
mercy | -0.214 |
backup | -0.213 |
Token | , |
Token ID | 11 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
ves | +0.012 |
vern | +0.012 |
ades | +0.011 |
mercy | +0.011 |
forgiveness | +0.011 |
Neg logit contributions | |
around | -0.010 |
cy | -0.010 |
air | -0.010 |
| | -0.009 |
et | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
ves | +0.037 |
vern | +0.036 |
ades | +0.032 |
mercy | +0.032 |
backup | +0.032 |
Neg logit contributions | |
around | -0.041 |
cy | -0.038 |
air | -0.037 |
et | -0.037 |
down | -0.037 |
Token | g |
Token ID | 308 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
around | +0.224 |
cy | +0.203 |
air | +0.203 |
down | +0.198 |
et | +0.194 |
Neg logit contributions | |
ves | -0.239 |
vern | -0.236 |
ades | -0.215 |
mercy | -0.210 |
backup | -0.208 |
Token | az |
Token ID | 1031 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
around | +0.120 |
cy | +0.109 |
down | +0.108 |
air | +0.104 |
| | +0.100 |
Neg logit contributions | |
ves | -0.169 |
vern | -0.166 |
ades | -0.159 |
keys | -0.145 |
mercy | -0.144 |
Token | eb |
Token ID | 1765 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
around | +0.632 |
air | +0.573 |
cy | +0.571 |
down | +0.560 |
| | +0.520 |
Neg logit contributions | |
ves | -1.146 |
vern | -1.076 |
ades | -1.019 |
keys | -0.966 |
ggy | -0.956 |
Token | o |
Token ID | 78 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
around | +0.190 |
et | +0.179 |
cy | +0.176 |
down | +0.170 |
air | +0.165 |
Neg logit contributions | |
vern | -0.165 |
ves | -0.162 |
mercy | -0.153 |
backup | -0.150 |
forgiveness | -0.147 |
Token | would |
Token ID | 561 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
around | +0.256 |
cy | +0.233 |
air | +0.230 |
down | +0.225 |
et | +0.220 |
Neg logit contributions | |
ves | -0.325 |
vern | -0.317 |
ades | -0.291 |
mercy | -0.286 |
keys | -0.284 |
Token | be |
Token ID | 307 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
around | +0.146 |
air | +0.129 |
down | +0.128 |
cy | +0.127 |
et | +0.125 |
Neg logit contributions | |
ves | -0.160 |
vern | -0.155 |
ades | -0.146 |
keys | -0.140 |
backup | -0.137 |
Token | there |
Token ID | 612 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ves | +0.205 |
vern | +0.203 |
ades | +0.184 |
mercy | +0.181 |
backup | +0.180 |
Neg logit contributions | |
around | -0.192 |
cy | -0.178 |
air | -0.175 |
down | -0.170 |
et | -0.167 |
Token | stand |
Token ID | 1302 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ves | +0.485 |
vern | +0.477 |
ades | +0.443 |
mercy | +0.426 |
backup | +0.425 |
Neg logit contributions | |
around | -0.412 |
air | -0.358 |
down | -0.358 |
cy | -0.355 |
et | -0.343 |
Token | like |
Token ID | 588 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
cy | +0.050 |
around | +0.050 |
air | +0.049 |
| | +0.048 |
et | +0.045 |
Neg logit contributions | |
vern | -0.078 |
ves | -0.078 |
ades | -0.072 |
keys | -0.069 |
mercy | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
around | +0.250 |
air | +0.230 |
down | +0.220 |
et | +0.202 |
ening | +0.196 |
Neg logit contributions | |
ves | -0.296 |
vern | -0.294 |
ades | -0.274 |
keys | -0.268 |
mercy | -0.258 |
Token | other |
Token ID | 584 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
around | +0.238 |
cy | +0.226 |
| | +0.220 |
down | +0.213 |
et | +0.211 |
Neg logit contributions | |
ves | -0.210 |
vern | -0.209 |
mercy | -0.189 |
ades | -0.188 |
forgiveness | -0.188 |
Token | r |
Token ID | 374 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ves | +0.051 |
vern | +0.049 |
forgiveness | +0.046 |
mercy | +0.045 |
ades | +0.045 |
Neg logit contributions | |
around | -0.066 |
| | -0.062 |
cy | -0.061 |
rated | -0.059 |
down | -0.059 |
Token | az |
Token ID | 1031 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
vern | +0.173 |
ades | +0.166 |
ves | +0.165 |
ups | +0.152 |
mercy | +0.152 |
Neg logit contributions | |
around | -0.116 |
| | -0.107 |
cy | -0.102 |
down | -0.102 |
rated | -0.098 |
Token | ors |
Token ID | 669 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
around | +0.806 |
cy | +0.754 |
air | +0.737 |
down | +0.726 |
| | +0.716 |
Neg logit contributions | |
ves | -0.966 |
vern | -0.870 |
ades | -0.829 |
keys | -0.783 |
ggy | -0.778 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
air | +0.248 |
cy | +0.243 |
rated | +0.241 |
| | +0.236 |
amp | +0.231 |
Neg logit contributions | |
ves | -0.268 |
vern | -0.239 |
keys | -0.239 |
ades | -0.233 |
else | -0.232 |
Token | The |
Token ID | 383 |
Feature activation | -8.33e+00 |
Pos logit contributions | |
around | +0.022 |
rated | +0.020 |
cy | +0.020 |
et | +0.020 |
down | +0.019 |
Neg logit contributions | |
ves | -0.037 |
vern | -0.035 |
ades | -0.034 |
His | -0.034 |
forgiveness | -0.033 |
Token | other |
Token ID | 584 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
around | +0.494 |
cy | +0.454 |
air | +0.450 |
down | +0.444 |
et | +0.436 |
Neg logit contributions | |
ves | -0.418 |
vern | -0.411 |
ades | -0.369 |
mercy | -0.361 |
backup | -0.357 |
Token | r |
Token ID | 374 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ves | +0.052 |
vern | +0.050 |
ades | +0.047 |
forgiveness | +0.046 |
mercy | +0.045 |
Neg logit contributions | |
around | -0.065 |
| | -0.061 |
cy | -0.059 |
down | -0.059 |
rated | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ves | +0.485 |
vern | +0.478 |
ades | +0.440 |
mercy | +0.433 |
backup | +0.429 |
Neg logit contributions | |
around | -0.349 |
cy | -0.314 |
air | -0.310 |
down | -0.303 |
et | -0.296 |
Token | She |
Token ID | 1375 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
around | +0.023 |
cy | +0.022 |
et | +0.022 |
rated | +0.022 |
| | +0.021 |
Neg logit contributions | |
ves | -0.032 |
vern | -0.030 |
forgiveness | -0.029 |
backup | -0.029 |
His | -0.029 |
Token | knew |
Token ID | 2993 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
around | +0.248 |
cy | +0.210 |
air | +0.209 |
down | +0.203 |
et | +0.202 |
Neg logit contributions | |
vern | -0.426 |
ves | -0.387 |
backup | -0.377 |
ades | -0.374 |
mercy | -0.361 |
Token | that |
Token ID | 326 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
around | +0.017 |
down | +0.015 |
air | +0.014 |
et | +0.014 |
cy | +0.013 |
Neg logit contributions | |
vern | -0.020 |
ves | -0.019 |
ades | -0.019 |
keys | -0.017 |
backup | -0.017 |
Token | r |
Token ID | 374 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
vern | +0.225 |
ves | +0.224 |
ades | +0.207 |
mercy | +0.197 |
backup | +0.197 |
Neg logit contributions | |
around | -0.215 |
air | -0.192 |
cy | -0.190 |
down | -0.190 |
et | -0.182 |
Token | az |
Token ID | 1031 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
vern | +0.129 |
ades | +0.129 |
ves | +0.127 |
forgiveness | +0.109 |
ups | +0.109 |
Neg logit contributions | |
around | -0.163 |
| | -0.148 |
air | -0.146 |
down | -0.143 |
cy | -0.143 |
Token | ors |
Token ID | 669 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
around | +0.816 |
air | +0.760 |
cy | +0.758 |
down | +0.742 |
| | +0.736 |
Neg logit contributions | |
ves | -0.964 |
vern | -0.783 |
ggy | -0.766 |
ades | -0.756 |
keys | -0.714 |
Token | were |
Token ID | 547 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
air | +0.222 |
around | +0.222 |
| | +0.214 |
rated | +0.211 |
amp | +0.210 |
Neg logit contributions | |
ves | -0.287 |
vern | -0.262 |
ades | -0.252 |
forgiveness | -0.248 |
keys | -0.247 |
Token | very |
Token ID | 845 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
ves | +0.034 |
vern | +0.033 |
ades | +0.031 |
mercy | +0.030 |
backup | +0.029 |
Neg logit contributions | |
around | -0.031 |
air | -0.028 |
down | -0.028 |
cy | -0.028 |
et | -0.027 |
Token | sharp |
Token ID | 7786 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
around | +0.315 |
air | +0.273 |
down | +0.269 |
cy | +0.266 |
et | +0.250 |
Neg logit contributions | |
ves | -0.387 |
vern | -0.379 |
ades | -0.355 |
mercy | -0.352 |
keys | -0.348 |
Token | and |
Token ID | 290 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ves | +0.095 |
vern | +0.091 |
mercy | +0.084 |
forgiveness | +0.084 |
ades | +0.083 |
Neg logit contributions | |
| | -0.079 |
cy | -0.078 |
around | -0.076 |
amp | -0.070 |
rated | -0.070 |
Token | he |
Token ID | 339 |
Feature activation | +9.35e+00 |
Pos logit contributions | |
vern | +0.066 |
ves | +0.062 |
ades | +0.058 |
keys | +0.054 |
mercy | +0.053 |
Neg logit contributions | |
around | -0.093 |
down | -0.084 |
air | -0.083 |
alone | -0.076 |
et | -0.075 |
Token | would |
Token ID | 561 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
ves | +0.572 |
vern | +0.563 |
ades | +0.516 |
mercy | +0.508 |
backup | +0.502 |
Neg logit contributions | |
around | -0.448 |
cy | -0.402 |
air | -0.401 |
down | -0.393 |
et | -0.384 |
Token | never |
Token ID | 1239 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
around | +0.147 |
air | +0.128 |
down | +0.128 |
cy | +0.126 |
et | +0.122 |
Neg logit contributions | |
ves | -0.149 |
vern | -0.144 |
ades | -0.138 |
keys | -0.133 |
mercy | -0.127 |
Token | touch |
Token ID | 3638 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
ves | +0.004 |
vern | +0.004 |
ades | +0.003 |
mercy | +0.003 |
backup | +0.003 |
Neg logit contributions | |
around | -0.003 |
cy | -0.003 |
air | -0.003 |
down | -0.003 |
et | -0.002 |
Token | r |
Token ID | 374 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
ves | +0.048 |
vern | +0.045 |
ades | +0.042 |
mercy | +0.042 |
forgiveness | +0.042 |
Neg logit contributions | |
around | -0.053 |
cy | -0.051 |
rated | -0.050 |
| | -0.049 |
air | -0.048 |
Token | az |
Token ID | 1031 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
ades | +0.167 |
ves | +0.154 |
vern | +0.153 |
ups | +0.140 |
keys | +0.139 |
Neg logit contributions | |
around | -0.130 |
rated | -0.120 |
air | -0.118 |
ening | -0.114 |
| | -0.108 |
Token | ors |
Token ID | 669 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
around | +0.731 |
cy | +0.669 |
air | +0.668 |
down | +0.637 |
| | +0.630 |
Neg logit contributions | |
ves | -1.022 |
vern | -0.948 |
ades | -0.906 |
keys | -0.872 |
mercy | -0.855 |
Token | again |
Token ID | 757 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
air | +0.248 |
around | +0.242 |
cy | +0.241 |
| | +0.236 |
rated | +0.233 |
Neg logit contributions | |
ves | -0.270 |
vern | -0.257 |
keys | -0.244 |
mercy | -0.243 |
ades | -0.242 |
Token | . |
Token ID | 13 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
around | +0.025 |
cy | +0.022 |
air | +0.022 |
down | +0.022 |
et | +0.021 |
Neg logit contributions | |
ves | -0.036 |
vern | -0.035 |
ades | -0.032 |
mercy | -0.032 |
backup | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
around | +0.025 |
cy | +0.023 |
air | +0.023 |
et | +0.022 |
down | +0.022 |
Neg logit contributions | |
ves | -0.034 |
vern | -0.033 |
ades | -0.030 |
backup | -0.030 |
mercy | -0.030 |
Token | said |
Token ID | 531 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
around | +0.071 |
cy | +0.064 |
air | +0.063 |
et | +0.062 |
down | +0.060 |
Neg logit contributions | |
vern | -0.084 |
ves | -0.081 |
ades | -0.076 |
backup | -0.075 |
mercy | -0.073 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ves | +0.062 |
vern | +0.061 |
ades | +0.058 |
keys | +0.056 |
backup | +0.054 |
Neg logit contributions | |
around | -0.089 |
down | -0.083 |
cy | -0.081 |
air | -0.081 |
et | -0.078 |
Token | said |
Token ID | 531 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
vern | +0.223 |
ves | +0.219 |
ades | +0.205 |
backup | +0.201 |
keys | +0.191 |
Neg logit contributions | |
around | -0.188 |
et | -0.162 |
down | -0.160 |
cy | -0.159 |
air | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
ves | +0.092 |
vern | +0.091 |
ades | +0.085 |
backup | +0.082 |
keys | +0.082 |
Neg logit contributions | |
around | -0.059 |
down | -0.051 |
air | -0.050 |
cy | -0.049 |
et | -0.047 |
Token | " |
Token ID | 366 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
around | +0.026 |
cy | +0.023 |
air | +0.023 |
down | +0.023 |
et | +0.022 |
Neg logit contributions | |
ves | -0.030 |
vern | -0.030 |
ades | -0.027 |
mercy | -0.027 |
backup | -0.026 |
Token | R |
Token ID | 49 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
ves | +0.174 |
vern | +0.172 |
ades | +0.155 |
mercy | +0.152 |
backup | +0.150 |
Neg logit contributions | |
around | -0.199 |
cy | -0.183 |
air | -0.181 |
down | -0.178 |
et | -0.174 |
Token | az |
Token ID | 1031 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
ves | +0.244 |
vern | +0.242 |
ades | +0.217 |
mercy | +0.210 |
backup | +0.208 |
Neg logit contributions | |
around | -0.300 |
down | -0.268 |
air | -0.266 |
cy | -0.265 |
et | -0.258 |
Token | ors |
Token ID | 669 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
around | +0.735 |
air | +0.679 |
| | +0.678 |
cy | +0.672 |
down | +0.663 |
Neg logit contributions | |
ves | -1.034 |
vern | -0.898 |
ggy | -0.864 |
ades | -0.843 |
instincts | -0.804 |
Token | are |
Token ID | 389 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
around | +0.230 |
| | +0.217 |
rated | +0.213 |
cy | +0.213 |
air | +0.212 |
Neg logit contributions | |
ves | -0.287 |
vern | -0.280 |
forgiveness | -0.263 |
mercy | -0.260 |
ades | -0.259 |
Token | not |
Token ID | 407 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
ves | +0.025 |
vern | +0.025 |
ades | +0.022 |
mercy | +0.021 |
keys | +0.021 |
Neg logit contributions | |
around | -0.032 |
air | -0.029 |
cy | -0.029 |
down | -0.029 |
et | -0.028 |
Token | toys |
Token ID | 14958 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
ves | +0.424 |
vern | +0.418 |
ades | +0.377 |
mercy | +0.370 |
backup | +0.366 |
Neg logit contributions | |
around | -0.459 |
cy | -0.420 |
air | -0.416 |
down | -0.409 |
et | -0.402 |
Token | , |
Token ID | 11 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
ves | +0.405 |
vern | +0.400 |
ades | +0.367 |
mercy | +0.362 |
backup | +0.359 |
Neg logit contributions | |
around | -0.302 |
cy | -0.271 |
air | -0.268 |
down | -0.263 |
et | -0.257 |
Token | stand |
Token ID | 1302 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ves | +0.033 |
vern | +0.033 |
ades | +0.030 |
backup | +0.029 |
mercy | +0.029 |
Neg logit contributions | |
around | -0.032 |
cy | -0.028 |
air | -0.028 |
down | -0.028 |
et | -0.027 |
Token | like |
Token ID | 588 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
around | +0.045 |
cy | +0.045 |
air | +0.044 |
| | +0.043 |
rated | +0.041 |
Neg logit contributions | |
ves | -0.081 |
vern | -0.081 |
ades | -0.075 |
backup | -0.073 |
mercy | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
around | +0.258 |
air | +0.231 |
down | +0.227 |
et | +0.208 |
cy | +0.205 |
Neg logit contributions | |
ves | -0.292 |
vern | -0.289 |
ades | -0.265 |
keys | -0.254 |
mercy | -0.250 |
Token | other |
Token ID | 584 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
around | +0.246 |
cy | +0.233 |
| | +0.224 |
down | +0.221 |
et | +0.217 |
Neg logit contributions | |
ves | -0.200 |
vern | -0.200 |
mercy | -0.179 |
forgiveness | -0.177 |
backup | -0.177 |
Token | r |
Token ID | 374 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ves | +0.056 |
vern | +0.055 |
mercy | +0.050 |
forgiveness | +0.049 |
ades | +0.049 |
Neg logit contributions | |
around | -0.071 |
cy | -0.066 |
| | -0.065 |
down | -0.064 |
rated | -0.063 |
Token | az |
Token ID | 1031 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
vern | +0.191 |
ves | +0.183 |
ades | +0.179 |
mercy | +0.170 |
forgiveness | +0.168 |
Neg logit contributions | |
around | -0.111 |
| | -0.101 |
cy | -0.096 |
down | -0.095 |
rated | -0.090 |
Token | ors |
Token ID | 669 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
around | +0.764 |
cy | +0.720 |
air | +0.696 |
down | +0.678 |
| | +0.677 |
Neg logit contributions | |
ves | -0.996 |
vern | -0.921 |
ades | -0.859 |
keys | -0.825 |
mercy | -0.807 |
Token | . |
Token ID | 13 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
| | +0.239 |
cy | +0.234 |
air | +0.230 |
rated | +0.228 |
around | +0.226 |
Neg logit contributions | |
ves | -0.255 |
vern | -0.248 |
keys | -0.245 |
ades | -0.233 |
forgiveness | -0.231 |
Token | They |
Token ID | 1119 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
around | +0.021 |
et | +0.020 |
cy | +0.020 |
rated | +0.019 |
ening | +0.019 |
Neg logit contributions | |
ves | -0.026 |
vern | -0.025 |
keys | -0.025 |
backup | -0.025 |
forgiveness | -0.024 |
Token | laugh |
Token ID | 6487 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
around | +0.084 |
cy | +0.081 |
et | +0.078 |
air | +0.077 |
amp | +0.077 |
Neg logit contributions | |
ves | -0.112 |
vern | -0.111 |
keys | -0.103 |
mercy | -0.102 |
ades | -0.100 |
Token | at |
Token ID | 379 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
cy | +0.109 |
| | +0.107 |
amp | +0.099 |
around | +0.098 |
et | +0.098 |
Neg logit contributions | |
ves | -0.130 |
vern | -0.125 |
ades | -0.119 |
keys | -0.115 |
mercy | -0.111 |
Token | up |
Token ID | 929 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
ves | +0.414 |
vern | +0.398 |
ades | +0.368 |
keys | +0.362 |
mercy | +0.355 |
Neg logit contributions | |
around | -0.478 |
down | -0.432 |
air | -0.426 |
cy | -0.418 |
et | -0.413 |
Token | tools |
Token ID | 4899 |
Feature activation | +9.19e+00 |
Pos logit contributions | |
ves | +0.722 |
vern | +0.714 |
ades | +0.657 |
mercy | +0.647 |
backup | +0.641 |
Neg logit contributions | |
around | -0.507 |
cy | -0.452 |
air | -0.448 |
down | -0.438 |
et | -0.428 |
Token | like |
Token ID | 588 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
ves | +0.561 |
vern | +0.556 |
ades | +0.507 |
mercy | +0.501 |
backup | +0.497 |
Neg logit contributions | |
around | -0.433 |
cy | -0.393 |
air | -0.389 |
down | -0.378 |
et | -0.371 |
Token | delicate |
Token ID | 19217 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
around | +0.275 |
air | +0.254 |
down | +0.242 |
et | +0.230 |
ening | +0.222 |
Neg logit contributions | |
ves | -0.261 |
vern | -0.257 |
ades | -0.234 |
keys | -0.229 |
mercy | -0.226 |
Token | r |
Token ID | 374 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
around | +0.010 |
air | +0.009 |
cy | +0.009 |
down | +0.009 |
et | +0.009 |
Neg logit contributions | |
ves | -0.008 |
vern | -0.008 |
ades | -0.007 |
mercy | -0.007 |
backup | -0.007 |
Token | az |
Token ID | 1031 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
vern | +0.176 |
ades | +0.169 |
ves | +0.161 |
ups | +0.154 |
eed | +0.151 |
Neg logit contributions | |
around | -0.128 |
| | -0.123 |
cy | -0.112 |
down | -0.110 |
rated | -0.109 |
Token | ors |
Token ID | 669 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
around | +0.723 |
cy | +0.675 |
air | +0.657 |
| | +0.647 |
down | +0.641 |
Neg logit contributions | |
ves | -1.035 |
vern | -0.976 |
ades | -0.904 |
keys | -0.855 |
forgiveness | -0.843 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
air | +0.199 |
| | +0.198 |
rated | +0.190 |
cy | +0.187 |
around | +0.186 |
Neg logit contributions | |
vern | -0.294 |
ves | -0.289 |
forgiveness | -0.277 |
ades | -0.267 |
keys | -0.266 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
around | +0.022 |
et | +0.020 |
cy | +0.020 |
down | +0.020 |
air | +0.019 |
Neg logit contributions | |
vern | -0.022 |
ves | -0.022 |
ades | -0.019 |
forgiveness | -0.019 |
mercy | -0.019 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ves | +0.044 |
ades | +0.039 |
vern | +0.038 |
His | +0.034 |
forgiveness | +0.031 |
Neg logit contributions | |
rated | -0.094 |
et | -0.092 |
ening | -0.089 |
ishy | -0.087 |
around | -0.082 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
ves | +0.143 |
vern | +0.142 |
ades | +0.126 |
backup | +0.120 |
forgiveness | +0.119 |
Neg logit contributions | |
around | -0.169 |
air | -0.164 |
et | -0.162 |
cy | -0.158 |
rated | -0.156 |
Token | a |
Token ID | 257 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
ves | +0.071 |
vern | +0.070 |
ades | +0.061 |
mercy | +0.059 |
backup | +0.059 |
Neg logit contributions | |
around | -0.120 |
cy | -0.113 |
rated | -0.111 |
et | -0.111 |
down | -0.110 |
Token | strong |
Token ID | 1913 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
ves | +0.224 |
vern | +0.220 |
ades | +0.197 |
mercy | +0.191 |
backup | +0.191 |
Neg logit contributions | |
around | -0.288 |
cy | -0.263 |
air | -0.262 |
down | -0.259 |
et | -0.256 |
Token | lizard |
Token ID | 42406 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
| | +0.166 |
around | +0.166 |
ained | +0.159 |
rated | +0.158 |
cy | +0.156 |
Neg logit contributions | |
wife | -0.094 |
ves | -0.092 |
crew | -0.084 |
keys | -0.081 |
fisherman | -0.080 |
Token | named |
Token ID | 3706 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
vern | +0.010 |
ves | +0.010 |
ades | +0.010 |
backup | +0.009 |
mercy | +0.009 |
Neg logit contributions | |
around | -0.009 |
cy | -0.007 |
down | -0.007 |
air | -0.007 |
et | -0.007 |
Token | T |
Token ID | 309 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
ves | +0.024 |
vern | +0.022 |
backup | +0.020 |
keys | +0.020 |
ggy | +0.020 |
Neg logit contributions | |
around | -0.024 |
cy | -0.024 |
rated | -0.023 |
air | -0.023 |
et | -0.023 |
Token | az |
Token ID | 1031 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
around | +0.204 |
cy | +0.188 |
air | +0.187 |
et | +0.186 |
down | +0.182 |
Neg logit contributions | |
ves | -0.149 |
vern | -0.143 |
mercy | -0.131 |
backup | -0.131 |
ades | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
around | +0.790 |
cy | +0.749 |
air | +0.747 |
down | +0.723 |
| | +0.698 |
Neg logit contributions | |
ves | -0.956 |
vern | -0.887 |
ades | -0.811 |
keys | -0.792 |
mercy | -0.773 |
Token | He |
Token ID | 679 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
around | +0.025 |
rated | +0.023 |
cy | +0.023 |
et | +0.023 |
| | +0.022 |
Neg logit contributions | |
ves | -0.017 |
vern | -0.016 |
His | -0.016 |
backup | -0.016 |
ades | -0.015 |
Token | lived |
Token ID | 5615 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
around | +0.057 |
cy | +0.054 |
down | +0.052 |
air | +0.052 |
rated | +0.050 |
Neg logit contributions | |
ves | -0.080 |
vern | -0.075 |
ades | -0.069 |
keys | -0.068 |
mercy | -0.067 |
Token | happily |
Token ID | 18177 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
around | +0.019 |
cy | +0.017 |
air | +0.017 |
et | +0.017 |
rated | +0.016 |
Neg logit contributions | |
ves | -0.038 |
vern | -0.038 |
ades | -0.035 |
mercy | -0.034 |
backup | -0.034 |
Token | among |
Token ID | 1871 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
around | +0.001 |
cy | +0.001 |
air | +0.001 |
rated | +0.001 |
et | +0.001 |
Neg logit contributions | |
ves | -0.002 |
vern | -0.002 |
keys | -0.002 |
ades | -0.002 |
mercy | -0.002 |
Token | shapes |
Token ID | 15268 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
around | +0.083 |
air | +0.074 |
down | +0.071 |
cy | +0.069 |
et | +0.068 |
Neg logit contributions | |
vern | -0.107 |
ves | -0.102 |
ades | -0.095 |
mercy | -0.095 |
keys | -0.092 |
Token | to |
Token ID | 284 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
vern | +0.091 |
ves | +0.090 |
mercy | +0.083 |
backup | +0.081 |
ades | +0.081 |
Neg logit contributions | |
around | -0.072 |
down | -0.061 |
air | -0.060 |
cy | -0.059 |
et | -0.058 |
Token | design |
Token ID | 1486 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ves | +0.158 |
vern | +0.156 |
ades | +0.142 |
mercy | +0.139 |
backup | +0.137 |
Neg logit contributions | |
around | -0.154 |
cy | -0.139 |
air | -0.139 |
down | -0.136 |
et | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ves | +0.029 |
vern | +0.028 |
ades | +0.025 |
mercy | +0.025 |
backup | +0.024 |
Neg logit contributions | |
around | -0.032 |
cy | -0.030 |
air | -0.030 |
down | -0.029 |
et | -0.029 |
Token | j |
Token ID | 474 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
vern | +0.254 |
ves | +0.253 |
mercy | +0.228 |
ades | +0.225 |
keys | +0.220 |
Neg logit contributions | |
around | -0.264 |
air | -0.241 |
down | -0.234 |
cy | -0.233 |
et | -0.223 |
Token | az |
Token ID | 1031 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
around | +0.230 |
down | +0.214 |
air | +0.211 |
cy | +0.208 |
rated | +0.206 |
Neg logit contributions | |
vern | -0.211 |
ves | -0.210 |
ades | -0.192 |
backup | -0.178 |
keys | -0.169 |
Token | zy |
Token ID | 7357 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
around | +0.750 |
air | +0.735 |
cy | +0.728 |
| | +0.696 |
down | +0.682 |
Neg logit contributions | |
ves | -0.998 |
vern | -0.891 |
ades | -0.831 |
keys | -0.796 |
ggy | -0.793 |
Token | picture |
Token ID | 4286 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
around | +0.559 |
cy | +0.527 |
air | +0.510 |
down | +0.506 |
| | +0.503 |
Neg logit contributions | |
ves | -0.589 |
vern | -0.550 |
ades | -0.512 |
keys | -0.503 |
forgiveness | -0.495 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
around | +0.013 |
cy | +0.012 |
air | +0.012 |
down | +0.011 |
| | +0.011 |
Neg logit contributions | |
ves | -0.014 |
vern | -0.014 |
ades | -0.013 |
mercy | -0.012 |
backup | -0.012 |
Token | Then |
Token ID | 3244 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
rated | +0.017 |
et | +0.017 |
around | +0.016 |
| | +0.015 |
ening | +0.015 |
Neg logit contributions | |
ves | -0.023 |
vern | -0.023 |
backup | -0.022 |
forgiveness | -0.022 |
ades | -0.022 |
Token | she |
Token ID | 673 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
around | +0.239 |
air | +0.218 |
down | +0.217 |
cy | +0.215 |
et | +0.204 |
Neg logit contributions | |
vern | -0.199 |
ves | -0.196 |
ades | -0.178 |
mercy | -0.169 |
keys | -0.168 |
Token | â |
Token ID | 22940 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
around | +0.018 |
et | +0.017 |
rated | +0.017 |
cy | +0.016 |
ening | +0.016 |
Neg logit contributions | |
vern | -0.022 |
ves | -0.022 |
backup | -0.020 |
ades | -0.020 |
forgiveness | -0.020 |
Token | € |
Token ID | 26391 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
around | +0.063 |
down | +0.056 |
through | +0.052 |
ening | +0.052 |
cy | +0.052 |
Neg logit contributions | |
ves | -0.090 |
vern | -0.087 |
ggy | -0.082 |
His | -0.077 |
forgiveness | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
around | +0.832 |
cy | +0.763 |
et | +0.750 |
air | +0.744 |
rated | +0.743 |
Neg logit contributions | |
ves | -0.797 |
vern | -0.756 |
ades | -0.689 |
keys | -0.662 |
backup | -0.632 |
Token |
|
Token ID | 198 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
ves | +0.043 |
vern | +0.043 |
mercy | +0.040 |
ades | +0.040 |
backup | +0.040 |
Neg logit contributions | |
around | -0.035 |
air | -0.031 |
cy | -0.031 |
down | -0.030 |
| | -0.030 |
Token | M |
Token ID | 44 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
vern | +0.033 |
mercy | +0.032 |
ves | +0.032 |
backup | +0.030 |
forgiveness | +0.030 |
Neg logit contributions | |
around | -0.045 |
| | -0.042 |
cy | -0.041 |
amp | -0.041 |
air | -0.040 |
Token | az |
Token ID | 1031 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
ves | +0.255 |
vern | +0.251 |
ades | +0.220 |
mercy | +0.215 |
backup | +0.212 |
Neg logit contributions | |
around | -0.409 |
cy | -0.379 |
air | -0.377 |
down | -0.372 |
et | -0.366 |
Token | zy |
Token ID | 7357 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
around | +0.660 |
air | +0.638 |
cy | +0.624 |
down | +0.619 |
| | +0.580 |
Neg logit contributions | |
ves | -1.100 |
vern | -0.946 |
ades | -0.916 |
ggy | -0.900 |
keys | -0.868 |
Token | was |
Token ID | 373 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
around | +0.535 |
down | +0.482 |
air | +0.481 |
cy | +0.480 |
| | +0.469 |
Neg logit contributions | |
ves | -0.610 |
vern | -0.577 |
ades | -0.536 |
mercy | -0.525 |
keys | -0.524 |
Token | so |
Token ID | 523 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
ves | +0.100 |
vern | +0.100 |
mercy | +0.088 |
wife | +0.088 |
backup | +0.087 |
Neg logit contributions | |
cy | -0.089 |
around | -0.083 |
| | -0.082 |
rated | -0.080 |
air | -0.079 |
Token | excited |
Token ID | 6568 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
around | +0.290 |
cy | +0.271 |
et | +0.269 |
air | +0.269 |
| | +0.260 |
Neg logit contributions | |
vern | -0.296 |
ves | -0.294 |
ades | -0.262 |
mercy | -0.255 |
keys | -0.254 |
Token | about |
Token ID | 546 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
around | +0.184 |
cy | +0.170 |
air | +0.167 |
down | +0.163 |
et | +0.162 |
Neg logit contributions | |
ves | -0.195 |
vern | -0.191 |
ades | -0.175 |
mercy | -0.171 |
backup | -0.169 |
Token |
|
Token ID | 198 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
vern | +0.047 |
ves | +0.046 |
mercy | +0.044 |
backup | +0.043 |
ades | +0.043 |
Neg logit contributions | |
around | -0.035 |
cy | -0.030 |
| | -0.029 |
air | -0.029 |
down | -0.029 |
Token | One |
Token ID | 3198 |
Feature activation | +6.71e+00 |
Pos logit contributions | |
vern | +0.035 |
ves | +0.033 |
mercy | +0.032 |
forgiveness | +0.031 |
keys | +0.030 |
Neg logit contributions | |
around | -0.046 |
air | -0.041 |
| | -0.041 |
cy | -0.040 |
et | -0.040 |
Token | day |
Token ID | 1110 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
ves | +0.467 |
vern | +0.447 |
wife | +0.423 |
His | +0.418 |
keys | +0.416 |
Neg logit contributions | |
around | -0.220 |
ening | -0.204 |
et | -0.199 |
air | -0.197 |
down | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
around | +0.470 |
down | +0.410 |
air | +0.402 |
cy | +0.394 |
through | +0.354 |
Neg logit contributions | |
vern | -0.830 |
ves | -0.798 |
mercy | -0.759 |
ades | -0.749 |
keys | -0.734 |
Token | T |
Token ID | 309 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
vern | +0.058 |
ves | +0.056 |
ades | +0.052 |
mercy | +0.052 |
keys | +0.050 |
Neg logit contributions | |
around | -0.041 |
down | -0.037 |
air | -0.036 |
cy | -0.036 |
et | -0.033 |
Token | az |
Token ID | 1031 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
around | +0.187 |
cy | +0.172 |
air | +0.170 |
down | +0.168 |
et | +0.164 |
Neg logit contributions | |
ves | -0.168 |
vern | -0.166 |
ades | -0.149 |
mercy | -0.145 |
backup | -0.143 |
Token | heard |
Token ID | 2982 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
around | +0.716 |
cy | +0.695 |
air | +0.686 |
down | +0.666 |
| | +0.649 |
Neg logit contributions | |
ves | -1.016 |
vern | -0.913 |
ades | -0.854 |
ggy | -0.835 |
His | -0.826 |
Token | some |
Token ID | 617 |
Feature activation | +9.54e+00 |
Pos logit contributions | |
vern | +0.137 |
ves | +0.127 |
keys | +0.119 |
ades | +0.118 |
mercy | +0.113 |
Neg logit contributions | |
around | -0.122 |
air | -0.110 |
down | -0.103 |
through | -0.097 |
et | -0.094 |
Token | voices |
Token ID | 10839 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
ves | +0.548 |
vern | +0.547 |
ades | +0.494 |
backup | +0.481 |
mercy | +0.481 |
Neg logit contributions | |
around | -0.495 |
air | -0.451 |
cy | -0.436 |
down | -0.435 |
et | -0.421 |
Token | coming |
Token ID | 2406 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
ves | +0.277 |
vern | +0.273 |
ades | +0.255 |
mercy | +0.251 |
backup | +0.248 |
Neg logit contributions | |
around | -0.152 |
cy | -0.138 |
air | -0.134 |
down | -0.129 |
et | -0.127 |
Token | from |
Token ID | 422 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
vern | +0.042 |
ves | +0.041 |
mercy | +0.038 |
ades | +0.038 |
backup | +0.037 |
Neg logit contributions | |
around | -0.046 |
air | -0.044 |
cy | -0.044 |
et | -0.043 |
| | -0.041 |
Token | up |
Token ID | 510 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
around | +0.043 |
cy | +0.040 |
air | +0.039 |
| | +0.037 |
down | +0.036 |
Neg logit contributions | |
ves | -0.075 |
vern | -0.074 |
ades | -0.069 |
mercy | -0.067 |
backup | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
around | +0.317 |
cy | +0.312 |
| | +0.308 |
air | +0.302 |
rated | +0.295 |
Neg logit contributions | |
ves | -0.413 |
vern | -0.409 |
ades | -0.380 |
mercy | -0.371 |
forgiveness | -0.366 |
Token | The |
Token ID | 383 |
Feature activation | -8.15e+00 |
Pos logit contributions | |
around | +0.013 |
cy | +0.012 |
et | +0.012 |
rated | +0.012 |
| | +0.011 |
Neg logit contributions | |
ves | -0.026 |
vern | -0.025 |
ades | -0.024 |
backup | -0.024 |
forgiveness | -0.023 |
Token | other |
Token ID | 584 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
around | +0.467 |
air | +0.453 |
cy | +0.423 |
down | +0.420 |
et | +0.407 |
Neg logit contributions | |
ves | -0.437 |
vern | -0.423 |
ades | -0.391 |
keys | -0.372 |
mercy | -0.360 |
Token | r |
Token ID | 374 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ves | +0.066 |
vern | +0.065 |
ades | +0.059 |
mercy | +0.057 |
backup | +0.057 |
Neg logit contributions | |
around | -0.076 |
cy | -0.069 |
air | -0.069 |
down | -0.068 |
et | -0.066 |
Token | az |
Token ID | 1031 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
vern | +0.172 |
ves | +0.169 |
ades | +0.159 |
mercy | +0.154 |
forgiveness | +0.151 |
Neg logit contributions | |
around | -0.147 |
cy | -0.129 |
down | -0.129 |
| | -0.129 |
air | -0.126 |
Token | ors |
Token ID | 669 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
around | +0.836 |
cy | +0.778 |
air | +0.766 |
down | +0.753 |
| | +0.732 |
Neg logit contributions | |
ves | -0.910 |
vern | -0.848 |
ades | -0.781 |
keys | -0.748 |
mercy | -0.739 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
around | +0.231 |
air | +0.223 |
| | +0.219 |
amp | +0.214 |
rated | +0.213 |
Neg logit contributions | |
ves | -0.271 |
vern | -0.253 |
ades | -0.249 |
keys | -0.243 |
forgiveness | -0.239 |
Token | this |
Token ID | 428 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
vern | +0.023 |
ves | +0.023 |
ades | +0.020 |
keys | +0.020 |
mercy | +0.020 |
Neg logit contributions | |
around | -0.018 |
air | -0.016 |
down | -0.016 |
et | -0.014 |
cy | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ves | +0.188 |
vern | +0.186 |
ades | +0.171 |
mercy | +0.168 |
backup | +0.167 |
Neg logit contributions | |
around | -0.130 |
cy | -0.117 |
air | -0.114 |
down | -0.112 |
| | -0.110 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
around | +0.081 |
down | +0.070 |
air | +0.068 |
cy | +0.064 |
et | +0.063 |
Neg logit contributions | |
vern | -0.107 |
ves | -0.097 |
backup | -0.094 |
ades | -0.093 |
mercy | -0.091 |
Token | no |
Token ID | 645 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
vern | +0.076 |
ves | +0.069 |
ades | +0.069 |
backup | +0.065 |
keys | +0.063 |
Neg logit contributions | |
around | -0.088 |
air | -0.079 |
down | -0.077 |
et | -0.075 |
ening | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
ves | +0.384 |
vern | +0.379 |
ades | +0.345 |
mercy | +0.344 |
forgiveness | +0.340 |
Neg logit contributions | |
around | -0.298 |
cy | -0.272 |
air | -0.264 |
down | -0.259 |
| | -0.258 |
Token | He |
Token ID | 679 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
around | +0.018 |
cy | +0.017 |
rated | +0.017 |
et | +0.017 |
ening | +0.017 |
Neg logit contributions | |
ves | -0.020 |
vern | -0.019 |
His | -0.019 |
ades | -0.019 |
backup | -0.018 |
Token | said |
Token ID | 531 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
around | +0.060 |
cy | +0.054 |
air | +0.052 |
et | +0.052 |
down | +0.050 |
Neg logit contributions | |
vern | -0.076 |
ves | -0.072 |
ades | -0.069 |
backup | -0.067 |
keys | -0.065 |
Token | r |
Token ID | 374 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
vern | +0.083 |
ves | +0.076 |
ades | +0.071 |
mercy | +0.069 |
backup | +0.067 |
Neg logit contributions | |
around | -0.083 |
air | -0.074 |
down | -0.073 |
et | -0.068 |
ening | -0.065 |
Token | az |
Token ID | 1031 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
vern | +0.138 |
ades | +0.137 |
ves | +0.136 |
mercy | +0.117 |
forgiveness | +0.116 |
Neg logit contributions | |
around | -0.172 |
| | -0.159 |
air | -0.158 |
down | -0.154 |
cy | -0.153 |
Token | ors |
Token ID | 669 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
around | +0.735 |
air | +0.704 |
cy | +0.686 |
down | +0.674 |
| | +0.649 |
Neg logit contributions | |
ves | -1.006 |
vern | -0.882 |
ades | -0.863 |
His | -0.825 |
ggy | -0.811 |
Token | were |
Token ID | 547 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
around | +0.221 |
air | +0.216 |
cy | +0.212 |
| | +0.212 |
rated | +0.203 |
Neg logit contributions | |
ves | -0.298 |
vern | -0.280 |
ades | -0.267 |
mercy | -0.259 |
forgiveness | -0.258 |
Token | sharp |
Token ID | 7786 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ves | +0.041 |
vern | +0.040 |
ades | +0.037 |
mercy | +0.036 |
keys | +0.035 |
Neg logit contributions | |
around | -0.040 |
air | -0.036 |
down | -0.036 |
cy | -0.035 |
et | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ves | +0.100 |
vern | +0.095 |
mercy | +0.090 |
forgiveness | +0.087 |
ades | +0.087 |
Neg logit contributions | |
| | -0.092 |
cy | -0.088 |
around | -0.088 |
amp | -0.081 |
rated | -0.080 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
around | +0.094 |
cy | +0.087 |
air | +0.086 |
down | +0.085 |
et | +0.083 |
Neg logit contributions | |
ves | -0.078 |
vern | -0.077 |
ades | -0.069 |
mercy | -0.068 |
backup | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
around | +0.377 |
air | +0.364 |
cy | +0.364 |
down | +0.362 |
rated | +0.350 |
Neg logit contributions | |
ves | -0.428 |
vern | -0.389 |
keys | -0.362 |
ades | -0.356 |
ggy | -0.343 |
Token | never |
Token ID | 1239 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ves | +0.103 |
vern | +0.102 |
ades | +0.095 |
keys | +0.091 |
mercy | +0.091 |
Neg logit contributions | |
around | -0.100 |
air | -0.088 |
down | -0.088 |
cy | -0.087 |
et | -0.086 |
Token | scared |
Token ID | 12008 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
vern | +0.011 |
ves | +0.011 |
mercy | +0.010 |
backup | +0.010 |
forgiveness | +0.010 |
Neg logit contributions | |
around | -0.008 |
cy | -0.008 |
air | -0.008 |
et | -0.007 |
| | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
cy | +0.205 |
around | +0.203 |
| | +0.200 |
air | +0.199 |
et | +0.196 |
Neg logit contributions | |
vern | -0.176 |
ves | -0.172 |
backup | -0.163 |
mercy | -0.162 |
forgiveness | -0.160 |
Token | r |
Token ID | 374 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ves | +0.258 |
vern | +0.255 |
ades | +0.230 |
mercy | +0.227 |
backup | +0.225 |
Neg logit contributions | |
around | -0.255 |
cy | -0.236 |
air | -0.231 |
down | -0.227 |
et | -0.224 |
Token | az |
Token ID | 1031 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
vern | +0.171 |
ades | +0.168 |
ves | +0.162 |
mercy | +0.150 |
ups | +0.149 |
Neg logit contributions | |
around | -0.136 |
air | -0.124 |
| | -0.123 |
cy | -0.121 |
down | -0.118 |
Token | ors |
Token ID | 669 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
around | +0.730 |
cy | +0.694 |
air | +0.669 |
| | +0.653 |
down | +0.646 |
Neg logit contributions | |
ves | -0.989 |
vern | -0.934 |
ades | -0.868 |
keys | -0.850 |
mercy | -0.837 |
Token | again |
Token ID | 757 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
around | +0.242 |
cy | +0.236 |
air | +0.236 |
| | +0.225 |
rated | +0.223 |
Neg logit contributions | |
ves | -0.273 |
vern | -0.272 |
mercy | -0.249 |
forgiveness | -0.248 |
keys | -0.245 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
around | +0.017 |
cy | +0.016 |
air | +0.015 |
down | +0.015 |
et | +0.015 |
Neg logit contributions | |
ves | -0.023 |
vern | -0.023 |
ades | -0.021 |
mercy | -0.021 |
backup | -0.021 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
around | +0.021 |
et | +0.020 |
rated | +0.020 |
down | +0.019 |
cy | +0.019 |
Neg logit contributions | |
vern | -0.016 |
ves | -0.015 |
forgiveness | -0.014 |
His | -0.014 |
backup | -0.014 |
Token | W |
Token ID | 54 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ves | +0.050 |
ades | +0.044 |
His | +0.039 |
vern | +0.039 |
lor | +0.036 |
Neg logit contributions | |
rated | -0.095 |
et | -0.093 |
ishy | -0.090 |
ening | -0.089 |
around | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
ves | +0.164 |
vern | +0.158 |
mercy | +0.146 |
backup | +0.145 |
forgiveness | +0.143 |
Neg logit contributions | |
around | -0.147 |
cy | -0.145 |
| | -0.133 |
air | -0.132 |
rated | -0.132 |
Token | rhythm |
Token ID | 18662 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
around | +0.181 |
cy | +0.168 |
down | +0.157 |
et | +0.155 |
| | +0.155 |
Neg logit contributions | |
ves | -0.257 |
vern | -0.253 |
ades | -0.235 |
mercy | -0.232 |
backup | -0.231 |
Token | of |
Token ID | 286 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
ves | +0.063 |
vern | +0.057 |
ades | +0.054 |
backup | +0.051 |
keys | +0.051 |
Neg logit contributions | |
cy | -0.063 |
around | -0.061 |
| | -0.060 |
rated | -0.059 |
air | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ves | +0.285 |
vern | +0.280 |
ades | +0.256 |
mercy | +0.254 |
backup | +0.253 |
Neg logit contributions | |
around | -0.227 |
cy | -0.211 |
air | -0.200 |
down | -0.199 |
et | -0.196 |
Token | j |
Token ID | 474 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ves | +0.260 |
vern | +0.257 |
ades | +0.232 |
mercy | +0.228 |
backup | +0.225 |
Neg logit contributions | |
around | -0.262 |
cy | -0.237 |
air | -0.237 |
down | -0.232 |
et | -0.227 |
Token | az |
Token ID | 1031 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
around | +0.246 |
down | +0.236 |
rated | +0.234 |
cy | +0.230 |
air | +0.229 |
Neg logit contributions | |
ves | -0.185 |
vern | -0.183 |
ades | -0.165 |
backup | -0.147 |
ggy | -0.135 |
Token | zy |
Token ID | 7357 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
cy | +0.773 |
around | +0.756 |
air | +0.734 |
| | +0.710 |
down | +0.695 |
Neg logit contributions | |
ves | -0.990 |
vern | -0.849 |
ades | -0.792 |
ggy | -0.784 |
keys | -0.773 |
Token | tune |
Token ID | 14009 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
cy | +0.501 |
around | +0.485 |
| | +0.480 |
rated | +0.469 |
down | +0.449 |
Neg logit contributions | |
ves | -0.613 |
vern | -0.524 |
keys | -0.523 |
ades | -0.513 |
forgiveness | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
around | +0.064 |
cy | +0.059 |
air | +0.057 |
down | +0.056 |
| | +0.055 |
Neg logit contributions | |
ves | -0.089 |
vern | -0.087 |
ades | -0.080 |
mercy | -0.079 |
backup | -0.078 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
cy | +0.015 |
rated | +0.014 |
| | +0.014 |
et | +0.013 |
ening | +0.013 |
Neg logit contributions | |
ves | -0.022 |
backup | -0.020 |
His | -0.019 |
wife | -0.019 |
vern | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
around | +0.259 |
rated | +0.258 |
| | +0.257 |
cy | +0.256 |
et | +0.254 |
Neg logit contributions | |
ves | -0.111 |
vern | -0.095 |
backup | -0.080 |
forgiveness | -0.077 |
ades | -0.077 |
Token | that |
Token ID | 326 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
vern | +0.080 |
ves | +0.079 |
ades | +0.072 |
mercy | +0.070 |
backup | +0.070 |
Neg logit contributions | |
around | -0.088 |
air | -0.080 |
down | -0.078 |
cy | -0.077 |
et | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
vern | +0.205 |
ves | +0.198 |
ades | +0.181 |
keys | +0.174 |
mercy | +0.173 |
Neg logit contributions | |
around | -0.257 |
air | -0.235 |
down | -0.229 |
et | -0.224 |
cy | -0.224 |
Token | He |
Token ID | 679 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
around | +0.017 |
cy | +0.016 |
rated | +0.016 |
et | +0.016 |
ening | +0.015 |
Neg logit contributions | |
ves | -0.017 |
vern | -0.016 |
His | -0.016 |
ades | -0.016 |
backup | -0.015 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
around | +0.057 |
cy | +0.051 |
air | +0.050 |
et | +0.049 |
down | +0.048 |
Neg logit contributions | |
vern | -0.076 |
ves | -0.074 |
ades | -0.068 |
backup | -0.067 |
mercy | -0.066 |
Token | r |
Token ID | 374 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
around | +0.076 |
air | +0.066 |
down | +0.065 |
et | +0.064 |
cy | +0.062 |
Neg logit contributions | |
vern | -0.072 |
ves | -0.070 |
mercy | -0.064 |
ades | -0.063 |
keys | -0.063 |
Token | az |
Token ID | 1031 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
ades | +0.133 |
ves | +0.129 |
vern | +0.127 |
keys | +0.107 |
ups | +0.104 |
Neg logit contributions | |
around | -0.183 |
air | -0.174 |
| | -0.167 |
down | -0.166 |
cy | -0.165 |
Token | ors |
Token ID | 669 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
around | +0.755 |
air | +0.718 |
cy | +0.702 |
down | +0.693 |
| | +0.673 |
Neg logit contributions | |
ves | -0.976 |
ades | -0.824 |
vern | -0.821 |
His | -0.795 |
ggy | -0.761 |
Token | were |
Token ID | 547 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
air | +0.214 |
around | +0.212 |
| | +0.208 |
cy | +0.202 |
rated | +0.199 |
Neg logit contributions | |
ves | -0.288 |
vern | -0.263 |
ades | -0.258 |
forgiveness | -0.248 |
keys | -0.245 |
Token | fun |
Token ID | 1257 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
ves | +0.044 |
vern | +0.043 |
ades | +0.039 |
mercy | +0.038 |
backup | +0.038 |
Neg logit contributions | |
around | -0.042 |
air | -0.038 |
down | -0.037 |
cy | -0.037 |
et | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
around | +0.027 |
air | +0.023 |
cy | +0.023 |
down | +0.023 |
et | +0.022 |
Neg logit contributions | |
ves | -0.039 |
vern | -0.039 |
ades | -0.036 |
mercy | -0.035 |
keys | -0.035 |
Token | cool |
Token ID | 3608 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
around | +0.083 |
air | +0.074 |
down | +0.072 |
cy | +0.072 |
et | +0.070 |
Neg logit contributions | |
vern | -0.089 |
ves | -0.088 |
ades | -0.081 |
backup | -0.077 |
mercy | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ves | +0.168 |
vern | +0.165 |
ades | +0.152 |
mercy | +0.149 |
backup | +0.147 |
Neg logit contributions | |
around | -0.120 |
cy | -0.114 |
air | -0.110 |
| | -0.107 |
et | -0.105 |
Token | As |
Token ID | 1081 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
around | +0.015 |
cy | +0.014 |
et | +0.014 |
rated | +0.014 |
air | +0.014 |
Neg logit contributions | |
ves | -0.019 |
vern | -0.018 |
ades | -0.018 |
backup | -0.017 |
forgiveness | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
vern | +0.118 |
ves | +0.111 |
ades | +0.104 |
mercy | +0.102 |
keys | +0.101 |
Neg logit contributions | |
around | -0.146 |
air | -0.131 |
down | -0.131 |
cy | -0.130 |
through | -0.123 |
Token | passed |
Token ID | 3804 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ves | +0.536 |
vern | +0.521 |
ades | +0.482 |
mercy | +0.472 |
keys | +0.470 |
Neg logit contributions | |
around | -0.471 |
air | -0.426 |
cy | -0.425 |
down | -0.417 |
et | -0.410 |
Token | T |
Token ID | 309 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ves | +0.081 |
vern | +0.078 |
ades | +0.075 |
backup | +0.073 |
mercy | +0.072 |
Neg logit contributions | |
around | -0.064 |
rated | -0.064 |
air | -0.061 |
et | -0.061 |
| | -0.060 |
Token | az |
Token ID | 1031 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
around | +0.149 |
cy | +0.134 |
air | +0.132 |
down | +0.130 |
| | +0.126 |
Neg logit contributions | |
ves | -0.203 |
vern | -0.201 |
ades | -0.186 |
mercy | -0.179 |
backup | -0.178 |
Token | , |
Token ID | 11 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
around | +0.684 |
cy | +0.645 |
air | +0.638 |
down | +0.611 |
| | +0.604 |
Neg logit contributions | |
ves | -1.051 |
vern | -0.946 |
ades | -0.895 |
keys | -0.878 |
mercy | -0.857 |
Token | the |
Token ID | 262 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
vern | +0.062 |
ves | +0.059 |
ades | +0.055 |
mercy | +0.054 |
keys | +0.053 |
Neg logit contributions | |
around | -0.045 |
air | -0.040 |
down | -0.040 |
cy | -0.039 |
through | -0.036 |
Token | little |
Token ID | 1310 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
around | +0.231 |
cy | +0.221 |
et | +0.213 |
| | +0.212 |
rated | +0.212 |
Neg logit contributions | |
ves | -0.194 |
vern | -0.191 |
mercy | -0.176 |
ades | -0.172 |
backup | -0.171 |
Token | boy |
Token ID | 2933 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
wife | +0.108 |
ves | +0.104 |
mercy | +0.103 |
vern | +0.100 |
forgiveness | +0.100 |
Neg logit contributions | |
| | -0.144 |
rated | -0.140 |
around | -0.138 |
ained | -0.134 |
et | -0.131 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
around | +0.316 |
cy | +0.270 |
down | +0.270 |
air | +0.269 |
et | +0.261 |
Neg logit contributions | |
vern | -0.430 |
ves | -0.411 |
mercy | -0.381 |
ades | -0.379 |
backup | -0.377 |
Token | â |
Token ID | 22940 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
ves | +0.064 |
vern | +0.062 |
ades | +0.057 |
keys | +0.057 |
forgiveness | +0.056 |
Neg logit contributions | |
around | -0.043 |
cy | -0.039 |
et | -0.039 |
air | -0.039 |
rated | -0.038 |
Token | € |
Token ID | 26391 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
around | +0.043 |
down | +0.039 |
air | +0.035 |
through | +0.034 |
cy | +0.033 |
Neg logit contributions | |
ves | -0.054 |
vern | -0.053 |
His | -0.049 |
forgiveness | -0.048 |
keys | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
around | +0.734 |
air | +0.668 |
cy | +0.666 |
et | +0.653 |
down | +0.652 |
Neg logit contributions | |
ves | -0.840 |
vern | -0.797 |
ades | -0.737 |
keys | -0.714 |
ggy | -0.678 |
Token |
|
Token ID | 198 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
ves | +0.059 |
vern | +0.058 |
ades | +0.053 |
mercy | +0.052 |
backup | +0.052 |
Neg logit contributions | |
around | -0.054 |
cy | -0.049 |
air | -0.049 |
down | -0.048 |
et | -0.047 |
Token | M |
Token ID | 44 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
ves | +0.042 |
vern | +0.041 |
mercy | +0.039 |
forgiveness | +0.037 |
ades | +0.037 |
Neg logit contributions | |
around | -0.060 |
| | -0.056 |
cy | -0.055 |
air | -0.054 |
amp | -0.053 |
Token | az |
Token ID | 1031 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
ves | +0.298 |
vern | +0.293 |
ades | +0.260 |
mercy | +0.256 |
backup | +0.254 |
Neg logit contributions | |
around | -0.382 |
cy | -0.354 |
air | -0.353 |
down | -0.342 |
et | -0.341 |
Token | zy |
Token ID | 7357 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
around | +0.639 |
air | +0.608 |
cy | +0.596 |
down | +0.595 |
| | +0.533 |
Neg logit contributions | |
ves | -1.086 |
vern | -0.985 |
ades | -0.940 |
ggy | -0.916 |
keys | -0.901 |
Token | â |
Token ID | 22940 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
around | +0.563 |
air | +0.514 |
cy | +0.514 |
down | +0.513 |
| | +0.506 |
Neg logit contributions | |
ves | -0.567 |
vern | -0.522 |
keys | -0.493 |
ades | -0.492 |
mercy | -0.477 |
Token | € |
Token ID | 26391 |
Feature activation | -1.46e+01 |
Pos logit contributions | |
around | +0.059 |
down | +0.051 |
through | +0.046 |
cy | +0.044 |
air | +0.043 |
Neg logit contributions | |
vern | -0.085 |
His | -0.081 |
ves | -0.080 |
forgiveness | -0.078 |
ggy | -0.077 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
around | +0.816 |
air | +0.742 |
cy | +0.741 |
down | +0.727 |
et | +0.715 |
Neg logit contributions | |
ves | -0.784 |
vern | -0.764 |
ades | -0.695 |
keys | -0.670 |
backup | -0.663 |
Token | s |
Token ID | 82 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
around | +0.071 |
air | +0.068 |
cy | +0.064 |
down | +0.064 |
ening | +0.063 |
Neg logit contributions | |
ves | -0.086 |
vern | -0.083 |
ades | -0.077 |
keys | -0.072 |
backup | -0.071 |
Token | about |
Token ID | 546 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
vern | +0.125 |
ves | +0.123 |
ades | +0.111 |
keys | +0.108 |
backup | +0.102 |
Neg logit contributions | |
around | -0.133 |
air | -0.121 |
down | -0.115 |
et | -0.109 |
ening | -0.106 |
Token | a |
Token ID | 257 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
around | +0.069 |
down | +0.060 |
air | +0.059 |
ening | +0.055 |
et | +0.054 |
Neg logit contributions | |
ves | -0.080 |
vern | -0.078 |
ades | -0.074 |
keys | -0.071 |
backup | -0.068 |
Token | cave |
Token ID | 11527 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ves | +0.279 |
vern | +0.264 |
ades | +0.250 |
keys | +0.239 |
mercy | +0.230 |
Neg logit contributions | |
around | -0.260 |
air | -0.239 |
down | -0.234 |
cy | -0.230 |
night | -0.215 |
Token | with |
Token ID | 351 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
ves | +0.126 |
vern | +0.124 |
ades | +0.114 |
mercy | +0.112 |
backup | +0.111 |
Neg logit contributions | |
around | -0.092 |
cy | -0.082 |
air | -0.082 |
down | -0.080 |
et | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
ves | +0.248 |
vern | +0.245 |
ades | +0.223 |
keys | +0.222 |
mercy | +0.202 |
Neg logit contributions | |
around | -0.250 |
air | -0.231 |
down | -0.216 |
et | -0.205 |
through | -0.202 |
Token | treasure |
Token ID | 14068 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
ves | +0.286 |
vern | +0.274 |
ades | +0.255 |
keys | +0.250 |
mercy | +0.246 |
Neg logit contributions | |
around | -0.250 |
air | -0.230 |
down | -0.222 |
cy | -0.204 |
ening | -0.197 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
vern | +0.710 |
ves | +0.708 |
ades | +0.649 |
mercy | +0.636 |
backup | +0.632 |
Neg logit contributions | |
around | -0.558 |
air | -0.488 |
down | -0.482 |
cy | -0.473 |
et | -0.466 |
Token | . |
Token ID | 13 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
around | +0.152 |
cy | +0.144 |
air | +0.138 |
| | +0.136 |
et | +0.134 |
Neg logit contributions | |
ves | -0.190 |
vern | -0.184 |
ades | -0.170 |
mercy | -0.167 |
forgiveness | -0.165 |
Token | The |
Token ID | 383 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
around | +0.012 |
cy | +0.011 |
air | +0.010 |
et | +0.010 |
down | +0.010 |
Neg logit contributions | |
ves | -0.022 |
vern | -0.021 |
ades | -0.020 |
mercy | -0.020 |
backup | -0.020 |
Token | old |
Token ID | 1468 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
around | +0.379 |
air | +0.344 |
cy | +0.326 |
down | +0.326 |
et | +0.312 |
Neg logit contributions | |
ves | -0.518 |
vern | -0.513 |
ades | -0.471 |
keys | -0.461 |
mercy | -0.456 |
Token | man |
Token ID | 582 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
around | +0.145 |
air | +0.135 |
down | +0.132 |
cy | +0.127 |
et | +0.124 |
Neg logit contributions | |
vern | -0.110 |
ves | -0.109 |
ades | -0.098 |
keys | -0.096 |
backup | -0.094 |
Token | us |
Token ID | 514 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
around | +0.021 |
air | +0.019 |
cy | +0.019 |
down | +0.018 |
et | +0.018 |
Neg logit contributions | |
ves | -0.021 |
vern | -0.021 |
ades | -0.019 |
mercy | -0.019 |
backup | -0.019 |
Token | feel |
Token ID | 1254 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ves | +0.008 |
vern | +0.008 |
ades | +0.007 |
mercy | +0.007 |
backup | +0.007 |
Neg logit contributions | |
around | -0.006 |
air | -0.006 |
down | -0.006 |
cy | -0.005 |
et | -0.005 |
Token | something |
Token ID | 1223 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
around | +0.162 |
cy | +0.153 |
air | +0.148 |
down | +0.146 |
| | +0.145 |
Neg logit contributions | |
ves | -0.157 |
vern | -0.157 |
ades | -0.140 |
mercy | -0.138 |
backup | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
ves | +0.755 |
vern | +0.742 |
ades | +0.676 |
mercy | +0.665 |
backup | +0.660 |
Neg logit contributions | |
around | -0.777 |
air | -0.690 |
down | -0.681 |
cy | -0.662 |
et | -0.647 |
Token | or |
Token ID | 393 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ves | +0.064 |
vern | +0.064 |
ades | +0.059 |
mercy | +0.058 |
backup | +0.057 |
Neg logit contributions | |
around | -0.039 |
air | -0.034 |
down | -0.033 |
cy | -0.032 |
et | -0.031 |
Token | something |
Token ID | 1223 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
vern | +0.061 |
ves | +0.061 |
ades | +0.056 |
backup | +0.051 |
mercy | +0.051 |
Neg logit contributions | |
around | -0.061 |
air | -0.054 |
down | -0.053 |
cy | -0.049 |
through | -0.048 |
Token | that |
Token ID | 326 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
vern | +0.803 |
ves | +0.801 |
ades | +0.733 |
mercy | +0.723 |
backup | +0.716 |
Neg logit contributions | |
around | -0.721 |
air | -0.636 |
down | -0.619 |
cy | -0.601 |
et | -0.589 |
Token | reminds |
Token ID | 17603 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ves | +0.282 |
vern | +0.277 |
ades | +0.257 |
mercy | +0.253 |
backup | +0.251 |
Neg logit contributions | |
around | -0.170 |
cy | -0.151 |
air | -0.148 |
down | -0.145 |
et | -0.142 |
Token | us |
Token ID | 514 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
vern | +0.120 |
ves | +0.120 |
ades | +0.110 |
mercy | +0.107 |
backup | +0.106 |
Neg logit contributions | |
around | -0.087 |
air | -0.077 |
cy | -0.074 |
down | -0.074 |
et | -0.072 |
Token | of |
Token ID | 286 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ves | +0.008 |
vern | +0.007 |
ades | +0.007 |
mercy | +0.007 |
keys | +0.007 |
Neg logit contributions | |
around | -0.006 |
air | -0.005 |
down | -0.005 |
through | -0.005 |
over | -0.004 |
Token | something |
Token ID | 1223 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
ves | +0.273 |
vern | +0.273 |
ades | +0.251 |
mercy | +0.243 |
keys | +0.239 |
Neg logit contributions | |
around | -0.249 |
air | -0.225 |
down | -0.216 |
et | -0.213 |
cy | -0.213 |
Token | , |
Token ID | 11 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
around | +0.003 |
cy | +0.003 |
air | +0.003 |
et | +0.003 |
| | +0.002 |
Neg logit contributions | |
ves | -0.004 |
vern | -0.004 |
ades | -0.003 |
mercy | -0.003 |
backup | -0.003 |
Token | as |
Token ID | 355 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
ves | +0.051 |
vern | +0.051 |
ades | +0.046 |
mercy | +0.045 |
backup | +0.044 |
Neg logit contributions | |
around | -0.053 |
down | -0.047 |
air | -0.047 |
cy | -0.047 |
et | -0.046 |
Token | he |
Token ID | 339 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
ves | +0.204 |
vern | +0.200 |
ades | +0.176 |
mercy | +0.173 |
backup | +0.170 |
Neg logit contributions | |
around | -0.306 |
cy | -0.284 |
air | -0.282 |
down | -0.278 |
et | -0.275 |
Token | moved |
Token ID | 3888 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
vern | +0.624 |
ves | +0.590 |
mercy | +0.553 |
forgiveness | +0.548 |
backup | +0.542 |
Neg logit contributions | |
around | -0.449 |
cy | -0.391 |
air | -0.388 |
down | -0.377 |
et | -0.376 |
Token | his |
Token ID | 465 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
ves | +0.019 |
vern | +0.018 |
ades | +0.017 |
backup | +0.017 |
mercy | +0.017 |
Neg logit contributions | |
around | -0.015 |
cy | -0.015 |
air | -0.014 |
rated | -0.014 |
| | -0.014 |
Token | soldiers |
Token ID | 5795 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
ves | +0.417 |
vern | +0.413 |
ades | +0.369 |
mercy | +0.363 |
keys | +0.357 |
Neg logit contributions | |
around | -0.455 |
air | -0.412 |
cy | -0.406 |
down | -0.405 |
et | -0.390 |
Token | forward |
Token ID | 2651 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
ves | +0.816 |
vern | +0.809 |
ades | +0.752 |
mercy | +0.747 |
backup | +0.746 |
Neg logit contributions | |
around | -0.342 |
cy | -0.325 |
air | -0.310 |
| | -0.297 |
et | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
around | +0.496 |
cy | +0.465 |
air | +0.459 |
et | +0.440 |
| | +0.440 |
Neg logit contributions | |
ves | -0.567 |
vern | -0.558 |
ades | -0.511 |
mercy | -0.501 |
backup | -0.499 |
Token | " |
Token ID | 366 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
around | +0.013 |
cy | +0.013 |
et | +0.012 |
rated | +0.012 |
air | +0.012 |
Neg logit contributions | |
ves | -0.020 |
vern | -0.019 |
ades | -0.018 |
backup | -0.018 |
mercy | -0.017 |
Token | You |
Token ID | 1639 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
ves | +0.195 |
vern | +0.191 |
ades | +0.175 |
backup | +0.169 |
mercy | +0.169 |
Neg logit contributions | |
around | -0.193 |
cy | -0.177 |
air | -0.174 |
down | -0.173 |
et | -0.170 |
Token | have |
Token ID | 423 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
around | +0.186 |
cy | +0.163 |
air | +0.162 |
down | +0.158 |
et | +0.153 |
Neg logit contributions | |
ves | -0.319 |
vern | -0.315 |
ades | -0.292 |
mercy | -0.287 |
backup | -0.285 |
Token | . |
Token ID | 13 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ves | +0.095 |
vern | +0.093 |
ades | +0.085 |
keys | +0.083 |
mercy | +0.083 |
Neg logit contributions | |
around | -0.088 |
down | -0.077 |
air | -0.077 |
cy | -0.075 |
et | -0.073 |
Token | The |
Token ID | 383 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
around | +0.014 |
cy | +0.012 |
et | +0.012 |
rated | +0.012 |
air | +0.012 |
Neg logit contributions | |
vern | -0.021 |
ves | -0.021 |
backup | -0.020 |
ades | -0.019 |
mercy | -0.019 |
Token | pilot |
Token ID | 8022 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
around | +0.482 |
air | +0.442 |
cy | +0.439 |
down | +0.431 |
et | +0.423 |
Neg logit contributions | |
ves | -0.411 |
vern | -0.406 |
ades | -0.365 |
mercy | -0.354 |
backup | -0.351 |
Token | told |
Token ID | 1297 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
vern | +0.132 |
ves | +0.132 |
ades | +0.120 |
backup | +0.117 |
mercy | +0.116 |
Neg logit contributions | |
around | -0.125 |
cy | -0.113 |
air | -0.112 |
down | -0.110 |
et | -0.108 |
Token | him |
Token ID | 683 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ves | +0.319 |
vern | +0.312 |
mercy | +0.286 |
ades | +0.285 |
backup | +0.282 |
Neg logit contributions | |
around | -0.275 |
cy | -0.255 |
air | -0.246 |
down | -0.244 |
et | -0.238 |
Token | something |
Token ID | 1223 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
around | +0.074 |
down | +0.064 |
air | +0.063 |
through | +0.059 |
et | +0.059 |
Neg logit contributions | |
vern | -0.055 |
ves | -0.054 |
ades | -0.052 |
keys | -0.047 |
backup | -0.046 |
Token | special |
Token ID | 2041 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
ves | +0.777 |
vern | +0.765 |
ades | +0.702 |
mercy | +0.683 |
backup | +0.682 |
Neg logit contributions | |
around | -0.739 |
air | -0.656 |
cy | -0.649 |
down | -0.647 |
et | -0.630 |
Token | ; |
Token ID | 26 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ves | +0.318 |
vern | +0.315 |
ades | +0.291 |
mercy | +0.284 |
backup | +0.284 |
Neg logit contributions | |
around | -0.248 |
cy | -0.218 |
air | -0.218 |
down | -0.213 |
et | -0.209 |
Token | he |
Token ID | 339 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
ves | +0.259 |
vern | +0.258 |
ades | +0.238 |
keys | +0.221 |
mercy | +0.218 |
Neg logit contributions | |
around | -0.276 |
down | -0.247 |
air | -0.244 |
through | -0.223 |
cy | -0.219 |
Token | said |
Token ID | 531 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ves | +0.605 |
vern | +0.602 |
ades | +0.556 |
backup | +0.543 |
mercy | +0.542 |
Neg logit contributions | |
around | -0.438 |
cy | -0.384 |
air | -0.379 |
down | -0.372 |
et | -0.364 |
Token | : |
Token ID | 25 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
ves | +0.075 |
vern | +0.075 |
ades | +0.069 |
backup | +0.064 |
keys | +0.063 |
Neg logit contributions | |
around | -0.096 |
air | -0.083 |
down | -0.082 |
ening | -0.076 |
et | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
around | +0.060 |
down | +0.052 |
cy | +0.052 |
air | +0.050 |
et | +0.048 |
Neg logit contributions | |
ves | -0.087 |
vern | -0.086 |
ades | -0.080 |
mercy | -0.079 |
keys | -0.079 |
Token | They |
Token ID | 1119 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
ves | +0.194 |
vern | +0.188 |
ades | +0.176 |
keys | +0.173 |
backup | +0.172 |
Neg logit contributions | |
around | -0.120 |
cy | -0.109 |
et | -0.108 |
air | -0.108 |
rated | -0.106 |
Token | explored |
Token ID | 18782 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
around | +0.021 |
cy | +0.020 |
air | +0.020 |
down | +0.019 |
et | +0.019 |
Neg logit contributions | |
ves | -0.025 |
vern | -0.024 |
mercy | -0.023 |
ades | -0.022 |
backup | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
ves | +0.112 |
vern | +0.107 |
ades | +0.100 |
mercy | +0.097 |
backup | +0.097 |
Neg logit contributions | |
around | -0.086 |
cy | -0.083 |
air | -0.081 |
| | -0.078 |
et | -0.078 |
Token | brilliant |
Token ID | 10457 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
around | +0.171 |
cy | +0.157 |
down | +0.154 |
air | +0.151 |
et | +0.151 |
Neg logit contributions | |
ves | -0.184 |
vern | -0.180 |
ades | -0.170 |
backup | -0.165 |
mercy | -0.162 |
Token | coral |
Token ID | 29537 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
around | +0.042 |
| | +0.040 |
rated | +0.040 |
cy | +0.039 |
ained | +0.039 |
Neg logit contributions | |
ves | -0.043 |
ades | -0.041 |
vern | -0.041 |
forgiveness | -0.038 |
backup | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
vern | +0.514 |
ves | +0.508 |
mercy | +0.457 |
backup | +0.453 |
ades | +0.442 |
Neg logit contributions | |
around | -0.629 |
air | -0.567 |
cy | -0.560 |
down | -0.553 |
et | -0.536 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
around | +0.065 |
cy | +0.059 |
air | +0.058 |
down | +0.057 |
et | +0.056 |
Neg logit contributions | |
ves | -0.077 |
vern | -0.075 |
ades | -0.069 |
mercy | -0.068 |
backup | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
ves | +0.070 |
vern | +0.069 |
ades | +0.063 |
mercy | +0.062 |
backup | +0.062 |
Neg logit contributions | |
around | -0.060 |
cy | -0.055 |
air | -0.054 |
down | -0.053 |
et | -0.052 |
Token | fish |
Token ID | 5916 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
around | +0.229 |
air | +0.210 |
cy | +0.207 |
down | +0.204 |
et | +0.197 |
Neg logit contributions | |
ves | -0.198 |
vern | -0.197 |
ades | -0.174 |
mercy | -0.171 |
backup | -0.169 |
Token | swimming |
Token ID | 14899 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
vern | +0.427 |
ves | +0.424 |
mercy | +0.380 |
ades | +0.379 |
backup | +0.376 |
Neg logit contributions | |
around | -0.382 |
down | -0.335 |
air | -0.331 |
cy | -0.327 |
et | -0.314 |
Token | and |
Token ID | 290 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ves | +0.115 |
vern | +0.100 |
His | +0.095 |
ades | +0.092 |
keys | +0.092 |
Neg logit contributions | |
around | -0.119 |
cy | -0.117 |
| | -0.116 |
air | -0.114 |
down | -0.110 |
Token | his |
Token ID | 465 |
Feature activation | +7.72e+00 |
Pos logit contributions | |
around | +0.124 |
cy | +0.117 |
air | +0.116 |
et | +0.113 |
| | +0.113 |
Neg logit contributions | |
ves | -0.060 |
vern | -0.055 |
forgiveness | -0.051 |
mercy | -0.049 |
His | -0.047 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ves | +0.303 |
vern | +0.296 |
ades | +0.256 |
keys | +0.248 |
mercy | +0.247 |
Neg logit contributions | |
around | -0.549 |
air | -0.512 |
cy | -0.508 |
down | -0.500 |
et | -0.487 |
Token | my |
Token ID | 1820 |
Feature activation | -8.98e+00 |
Pos logit contributions | |
ves | +0.258 |
vern | +0.245 |
ades | +0.243 |
His | +0.241 |
mercy | +0.236 |
Neg logit contributions | |
around | -0.102 |
| | -0.099 |
air | -0.097 |
rated | -0.092 |
cy | -0.089 |
Token | had |
Token ID | 550 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
around | +0.477 |
air | +0.447 |
cy | +0.446 |
| | +0.444 |
rated | +0.430 |
Neg logit contributions | |
ves | -0.471 |
vern | -0.441 |
ades | -0.410 |
mercy | -0.398 |
keys | -0.397 |
Token | a |
Token ID | 257 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
around | +0.173 |
air | +0.152 |
down | +0.146 |
et | +0.138 |
cy | +0.133 |
Neg logit contributions | |
ves | -0.291 |
vern | -0.283 |
keys | -0.265 |
ades | -0.263 |
mercy | -0.259 |
Token | brilliant |
Token ID | 10457 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ves | +0.266 |
vern | +0.259 |
ades | +0.237 |
mercy | +0.234 |
keys | +0.233 |
Neg logit contributions | |
around | -0.245 |
cy | -0.224 |
air | -0.222 |
down | -0.218 |
et | -0.211 |
Token | time |
Token ID | 640 |
Feature activation | -8.25e+00 |
Pos logit contributions | |
around | +0.057 |
cy | +0.051 |
down | +0.049 |
| | +0.049 |
air | +0.049 |
Neg logit contributions | |
ves | -0.102 |
vern | -0.101 |
ades | -0.093 |
backup | -0.090 |
mercy | -0.090 |
Token | riding |
Token ID | 10311 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
around | +0.356 |
down | +0.301 |
air | +0.300 |
cy | +0.296 |
et | +0.284 |
Neg logit contributions | |
ves | -0.559 |
vern | -0.556 |
ades | -0.512 |
mercy | -0.509 |
keys | -0.501 |
Token | in |
Token ID | 287 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
cy | +0.063 |
rated | +0.063 |
| | +0.061 |
air | +0.059 |
around | +0.058 |
Neg logit contributions | |
ves | -0.084 |
vern | -0.075 |
ades | -0.072 |
His | -0.069 |
mercy | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
around | +0.332 |
rated | +0.324 |
cy | +0.321 |
| | +0.304 |
et | +0.302 |
Neg logit contributions | |
ves | -0.375 |
vern | -0.373 |
backup | -0.340 |
mercy | -0.337 |
forgiveness | -0.336 |
Token | cool |
Token ID | 3608 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
around | +0.319 |
cy | +0.308 |
et | +0.301 |
air | +0.293 |
ening | +0.289 |
Neg logit contributions | |
vern | -0.285 |
ves | -0.284 |
ades | -0.255 |
His | -0.242 |
backup | -0.237 |
Token | . |
Token ID | 13 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
| | +0.283 |
cy | +0.264 |
rated | +0.258 |
amp | +0.247 |
zie | +0.244 |
Neg logit contributions | |
ves | -0.184 |
vern | -0.169 |
ades | -0.157 |
mercy | -0.152 |
backup | -0.147 |
Token | |
Token ID | 220 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
around | +0.026 |
et | +0.026 |
cy | +0.025 |
ening | +0.025 |
rated | +0.025 |
Neg logit contributions | |
ves | -0.025 |
vern | -0.023 |
His | -0.023 |
ades | -0.023 |
backup | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
around | +0.220 |
cy | +0.202 |
air | +0.201 |
down | +0.195 |
et | +0.194 |
Neg logit contributions | |
ves | -0.236 |
vern | -0.233 |
ades | -0.212 |
mercy | -0.205 |
backup | -0.204 |
Token |
|
Token ID | 198 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ves | +0.036 |
vern | +0.035 |
ades | +0.032 |
mercy | +0.032 |
backup | +0.031 |
Neg logit contributions | |
around | -0.031 |
cy | -0.028 |
air | -0.028 |
down | -0.027 |
et | -0.027 |
Token | Later |
Token ID | 18602 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
vern | +0.029 |
ves | +0.027 |
mercy | +0.026 |
forgiveness | +0.025 |
backup | +0.025 |
Neg logit contributions | |
around | -0.040 |
cy | -0.036 |
down | -0.036 |
air | -0.035 |
et | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
ves | +0.216 |
vern | +0.207 |
ades | +0.182 |
mercy | +0.181 |
backup | +0.177 |
Neg logit contributions | |
around | -0.425 |
cy | -0.402 |
air | -0.394 |
et | -0.392 |
| | -0.389 |
Token | day |
Token ID | 1110 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
ves | +0.295 |
vern | +0.284 |
ades | +0.262 |
forgiveness | +0.262 |
His | +0.261 |
Neg logit contributions | |
around | -0.118 |
et | -0.111 |
cy | -0.105 |
air | -0.100 |
ening | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
around | +0.564 |
cy | +0.510 |
air | +0.504 |
et | +0.493 |
down | +0.489 |
Neg logit contributions | |
ves | -0.709 |
vern | -0.689 |
ades | -0.637 |
backup | -0.622 |
mercy | -0.622 |
Token | Tim |
Token ID | 5045 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
vern | +0.060 |
ves | +0.060 |
ades | +0.056 |
mercy | +0.055 |
keys | +0.055 |
Neg logit contributions | |
around | -0.023 |
cy | -0.019 |
air | -0.019 |
down | -0.019 |
et | -0.017 |
Token | my |
Token ID | 1820 |
Feature activation | -9.00e+00 |
Pos logit contributions | |
around | +0.277 |
air | +0.228 |
ening | +0.226 |
| | +0.216 |
down | +0.208 |
Neg logit contributions | |
vern | -0.472 |
ves | -0.456 |
His | -0.446 |
mercy | -0.446 |
forgiveness | -0.444 |
Token | she |
Token ID | 673 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
around | +0.053 |
air | +0.048 |
down | +0.047 |
cy | +0.047 |
et | +0.044 |
Neg logit contributions | |
vern | -0.050 |
ves | -0.049 |
ades | -0.045 |
backup | -0.043 |
mercy | -0.042 |
Token | replied |
Token ID | 8712 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
vern | +0.329 |
ves | +0.311 |
backup | +0.307 |
ades | +0.304 |
charity | +0.291 |
Neg logit contributions | |
around | -0.241 |
air | -0.204 |
down | -0.201 |
et | -0.190 |
cy | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ves | +0.063 |
vern | +0.063 |
ades | +0.059 |
backup | +0.057 |
mercy | +0.057 |
Neg logit contributions | |
around | -0.042 |
down | -0.037 |
air | -0.036 |
cy | -0.035 |
et | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
around | +0.027 |
cy | +0.024 |
air | +0.024 |
et | +0.023 |
down | +0.023 |
Neg logit contributions | |
ves | -0.034 |
vern | -0.033 |
ades | -0.031 |
mercy | -0.030 |
backup | -0.030 |
Token | Let |
Token ID | 5756 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ves | +0.177 |
vern | +0.174 |
ades | +0.157 |
mercy | +0.154 |
backup | +0.152 |
Neg logit contributions | |
around | -0.189 |
cy | -0.172 |
air | -0.172 |
down | -0.169 |
et | -0.166 |
Token | 's |
Token ID | 338 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
around | +0.141 |
cy | +0.131 |
air | +0.127 |
| | +0.125 |
down | +0.125 |
Neg logit contributions | |
ves | -0.169 |
vern | -0.163 |
ades | -0.149 |
keys | -0.146 |
mercy | -0.146 |
Token | do |
Token ID | 466 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
ves | +0.116 |
vern | +0.114 |
ades | +0.104 |
mercy | +0.103 |
backup | +0.102 |
Neg logit contributions | |
around | -0.101 |
cy | -0.092 |
air | -0.091 |
down | -0.089 |
et | -0.088 |
Token | it |
Token ID | 340 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
around | +0.262 |
air | +0.226 |
down | +0.225 |
et | +0.207 |
through | +0.197 |
Neg logit contributions | |
vern | -0.313 |
ves | -0.291 |
mercy | -0.281 |
ades | -0.279 |
backup | -0.275 |
Token | again |
Token ID | 757 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
around | +0.231 |
cy | +0.205 |
air | +0.203 |
down | +0.201 |
et | +0.195 |
Neg logit contributions | |
ves | -0.308 |
vern | -0.305 |
ades | -0.279 |
mercy | -0.276 |
backup | -0.274 |
Token | !" |
Token ID | 2474 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
around | +0.030 |
cy | +0.027 |
air | +0.027 |
down | +0.027 |
et | +0.025 |
Neg logit contributions | |
ves | -0.035 |
vern | -0.035 |
ades | -0.032 |
mercy | -0.031 |
backup | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
around | +0.044 |
cy | +0.040 |
air | +0.039 |
et | +0.039 |
rated | +0.038 |
Neg logit contributions | |
ves | -0.061 |
vern | -0.060 |
ades | -0.055 |
mercy | -0.054 |
keys | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
ves | +0.043 |
vern | +0.043 |
mercy | +0.040 |
backup | +0.040 |
ades | +0.039 |
Neg logit contributions | |
cy | -0.037 |
air | -0.036 |
around | -0.036 |
| | -0.035 |
et | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ves | +0.054 |
vern | +0.052 |
ades | +0.049 |
mercy | +0.048 |
forgiveness | +0.048 |
Neg logit contributions | |
around | -0.037 |
cy | -0.036 |
air | -0.033 |
et | -0.032 |
| | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | +9.41e+00 |
Pos logit contributions | |
around | +0.092 |
down | +0.082 |
air | +0.079 |
cy | +0.074 |
through | +0.073 |
Neg logit contributions | |
vern | -0.097 |
ves | -0.095 |
ades | -0.088 |
keys | -0.082 |
mercy | -0.079 |
Token | needed |
Token ID | 2622 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
vern | +0.602 |
ves | +0.599 |
ades | +0.552 |
backup | +0.537 |
mercy | +0.536 |
Neg logit contributions | |
around | -0.435 |
cy | -0.381 |
air | -0.379 |
down | -0.373 |
et | -0.360 |
Token | to |
Token ID | 284 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
around | +0.042 |
air | +0.038 |
down | +0.037 |
through | +0.035 |
night | +0.035 |
Neg logit contributions | |
ves | -0.049 |
keys | -0.048 |
ades | -0.048 |
sters | -0.045 |
vern | -0.044 |
Token | find |
Token ID | 1064 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ves | +0.171 |
vern | +0.168 |
ades | +0.166 |
keys | +0.152 |
backup | +0.144 |
Neg logit contributions | |
around | -0.143 |
air | -0.133 |
down | -0.127 |
et | -0.120 |
| | -0.119 |
Token | a |
Token ID | 257 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
ves | +0.118 |
vern | +0.115 |
ades | +0.110 |
keys | +0.107 |
oral | +0.096 |
Neg logit contributions | |
around | -0.110 |
down | -0.100 |
air | -0.099 |
through | -0.089 |
et | -0.088 |
Token | safe |
Token ID | 3338 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
ves | +0.329 |
ades | +0.300 |
vern | +0.297 |
keys | +0.290 |
His | +0.271 |
Neg logit contributions | |
around | -0.204 |
down | -0.194 |
air | -0.188 |
night | -0.166 |
cy | -0.163 |
Token | place |
Token ID | 1295 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
around | +0.117 |
air | +0.103 |
down | +0.101 |
cy | +0.100 |
et | +0.095 |
Neg logit contributions | |
ves | -0.180 |
vern | -0.177 |
ades | -0.166 |
keys | -0.161 |
mercy | -0.159 |
Token | to |
Token ID | 284 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ves | +0.027 |
vern | +0.026 |
ades | +0.024 |
keys | +0.023 |
mercy | +0.023 |
Neg logit contributions | |
around | -0.027 |
down | -0.024 |
cy | -0.024 |
air | -0.023 |
et | -0.023 |
Token | hide |
Token ID | 7808 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ves | +0.177 |
vern | +0.175 |
ades | +0.170 |
keys | +0.164 |
backup | +0.154 |
Neg logit contributions | |
around | -0.139 |
air | -0.125 |
down | -0.122 |
| | -0.116 |
et | -0.115 |
Token | he |
Token ID | 339 |
Feature activation | +9.51e+00 |
Pos logit contributions | |
vern | +0.095 |
ves | +0.088 |
ades | +0.082 |
mercy | +0.075 |
forgiveness | +0.074 |
Neg logit contributions | |
around | -0.173 |
down | -0.160 |
air | -0.158 |
cy | -0.156 |
through | -0.149 |
Token | made |
Token ID | 925 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
vern | +0.564 |
ves | +0.557 |
ades | +0.507 |
mercy | +0.504 |
backup | +0.498 |
Neg logit contributions | |
around | -0.482 |
cy | -0.435 |
air | -0.431 |
down | -0.423 |
et | -0.412 |
Token | his |
Token ID | 465 |
Feature activation | +7.88e+00 |
Pos logit contributions | |
around | +0.083 |
air | +0.075 |
down | +0.075 |
through | +0.066 |
et | +0.065 |
Neg logit contributions | |
vern | -0.094 |
ves | -0.090 |
keys | -0.087 |
ades | -0.086 |
forgiveness | -0.083 |
Token | way |
Token ID | 835 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ves | +0.462 |
vern | +0.456 |
mercy | +0.414 |
ades | +0.410 |
backup | +0.406 |
Neg logit contributions | |
around | -0.381 |
cy | -0.352 |
et | -0.340 |
air | -0.335 |
| | -0.334 |
Token | , |
Token ID | 11 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
around | +0.032 |
cy | +0.030 |
air | +0.029 |
et | +0.028 |
| | +0.027 |
Neg logit contributions | |
vern | -0.107 |
ves | -0.107 |
ades | -0.099 |
mercy | -0.098 |
backup | -0.098 |
Token | he |
Token ID | 339 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
vern | +0.041 |
ves | +0.037 |
ades | +0.035 |
keys | +0.031 |
backup | +0.030 |
Neg logit contributions | |
around | -0.067 |
down | -0.063 |
air | -0.062 |
cy | -0.059 |
through | -0.058 |
Token | noticed |
Token ID | 6810 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
vern | +0.633 |
ves | +0.603 |
mercy | +0.567 |
ades | +0.563 |
forgiveness | +0.562 |
Neg logit contributions | |
around | -0.445 |
air | -0.377 |
down | -0.377 |
cy | -0.373 |
et | -0.365 |
Token | something |
Token ID | 1223 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
vern | +0.208 |
ves | +0.195 |
keys | +0.184 |
ades | +0.175 |
backup | +0.171 |
Neg logit contributions | |
around | -0.197 |
air | -0.174 |
down | -0.168 |
through | -0.156 |
et | -0.154 |
Token | strange |
Token ID | 6283 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
vern | +0.775 |
ves | +0.775 |
ades | +0.699 |
backup | +0.693 |
mercy | +0.689 |
Neg logit contributions | |
around | -0.775 |
down | -0.666 |
air | -0.661 |
et | -0.629 |
cy | -0.629 |
Token | . |
Token ID | 13 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ves | +0.156 |
vern | +0.150 |
ades | +0.140 |
mercy | +0.138 |
forgiveness | +0.135 |
Neg logit contributions | |
around | -0.113 |
cy | -0.111 |
| | -0.106 |
air | -0.105 |
down | -0.100 |
Token | He |
Token ID | 679 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
around | +0.013 |
et | +0.012 |
cy | +0.012 |
rated | +0.011 |
ening | +0.011 |
Neg logit contributions | |
ves | -0.021 |
vern | -0.021 |
His | -0.020 |
ades | -0.020 |
backup | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
around | +0.014 |
et | +0.013 |
rated | +0.013 |
cy | +0.012 |
ening | +0.012 |
Neg logit contributions | |
ves | -0.019 |
vern | -0.019 |
His | -0.019 |
ades | -0.018 |
backup | -0.018 |
Token | No |
Token ID | 2949 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
vern | +0.209 |
ves | +0.208 |
ades | +0.188 |
mercy | +0.183 |
backup | +0.180 |
Neg logit contributions | |
around | -0.187 |
cy | -0.172 |
air | -0.166 |
| | -0.162 |
down | -0.162 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
vern | +0.096 |
ves | +0.096 |
ades | +0.089 |
keys | +0.085 |
backup | +0.084 |
Neg logit contributions | |
around | -0.072 |
air | -0.068 |
cy | -0.065 |
down | -0.064 |
et | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
around | +0.038 |
air | +0.035 |
down | +0.034 |
cy | +0.032 |
et | +0.030 |
Neg logit contributions | |
vern | -0.046 |
ves | -0.042 |
ades | -0.040 |
backup | -0.039 |
mercy | -0.038 |
Token | little |
Token ID | 1310 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
around | +0.138 |
air | +0.126 |
cy | +0.119 |
down | +0.116 |
et | +0.103 |
Neg logit contributions | |
ves | -0.307 |
vern | -0.307 |
keys | -0.278 |
ades | -0.276 |
mercy | -0.275 |
Token | boy |
Token ID | 2933 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
ves | +0.135 |
vern | +0.131 |
mercy | +0.127 |
ades | +0.127 |
forgiveness | +0.127 |
Neg logit contributions | |
around | -0.127 |
| | -0.116 |
et | -0.113 |
amp | -0.112 |
rated | -0.110 |
Token | yelled |
Token ID | 22760 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
around | +0.363 |
cy | +0.321 |
air | +0.319 |
down | +0.319 |
et | +0.313 |
Neg logit contributions | |
vern | -0.368 |
ves | -0.358 |
ades | -0.333 |
backup | -0.325 |
mercy | -0.318 |
Token | . |
Token ID | 13 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ves | +0.045 |
vern | +0.044 |
mercy | +0.041 |
forgiveness | +0.040 |
backup | +0.040 |
Neg logit contributions | |
around | -0.036 |
cy | -0.036 |
air | -0.034 |
| | -0.034 |
et | -0.034 |
Token | His |
Token ID | 2399 |
Feature activation | +7.71e+00 |
Pos logit contributions | |
around | +0.016 |
cy | +0.015 |
air | +0.014 |
et | +0.014 |
down | +0.014 |
Neg logit contributions | |
ves | -0.017 |
vern | -0.017 |
ades | -0.016 |
mercy | -0.015 |
backup | -0.015 |
Token | parents |
Token ID | 3397 |
Feature activation | +9.89e+00 |
Pos logit contributions | |
ves | +0.333 |
vern | +0.325 |
keys | +0.290 |
ades | +0.278 |
mercy | +0.267 |
Neg logit contributions | |
around | -0.529 |
air | -0.508 |
down | -0.488 |
cy | -0.468 |
night | -0.459 |
Token | told |
Token ID | 1297 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
ves | +0.544 |
vern | +0.516 |
mercy | +0.479 |
ades | +0.477 |
forgiveness | +0.474 |
Neg logit contributions | |
around | -0.500 |
cy | -0.480 |
air | -0.475 |
| | -0.466 |
et | -0.453 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ves | +0.045 |
ades | +0.039 |
His | +0.034 |
vern | +0.034 |
lor | +0.032 |
Neg logit contributions | |
rated | -0.088 |
et | -0.086 |
ening | -0.084 |
ishy | -0.083 |
around | -0.075 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ves | +0.139 |
vern | +0.137 |
ades | +0.123 |
backup | +0.116 |
mercy | +0.114 |
Neg logit contributions | |
around | -0.167 |
air | -0.164 |
et | -0.160 |
cy | -0.156 |
rated | -0.154 |
Token | a |
Token ID | 257 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
ves | +0.193 |
vern | +0.192 |
ades | +0.177 |
keys | +0.172 |
backup | +0.172 |
Neg logit contributions | |
around | -0.194 |
air | -0.174 |
down | -0.171 |
| | -0.168 |
cy | -0.168 |
Token | time |
Token ID | 640 |
Feature activation | -8.25e+00 |
Pos logit contributions | |
vern | +0.342 |
ves | +0.341 |
ades | +0.311 |
backup | +0.306 |
mercy | +0.302 |
Neg logit contributions | |
around | -0.160 |
down | -0.143 |
air | -0.141 |
cy | -0.132 |
ening | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
around | +0.373 |
cy | +0.331 |
air | +0.324 |
down | +0.323 |
et | +0.308 |
Neg logit contributions | |
ves | -0.529 |
vern | -0.522 |
ades | -0.481 |
mercy | -0.477 |
backup | -0.470 |
Token | there |
Token ID | 612 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ves | +0.030 |
vern | +0.025 |
His | +0.025 |
else | +0.024 |
ades | +0.023 |
Neg logit contributions | |
air | -0.052 |
et | -0.051 |
rated | -0.049 |
ening | -0.049 |
amp | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
around | +0.060 |
rated | +0.058 |
air | +0.058 |
et | +0.058 |
down | +0.056 |
Neg logit contributions | |
ves | -0.047 |
vern | -0.040 |
ades | -0.038 |
ggy | -0.037 |
His | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ves | +0.076 |
vern | +0.075 |
ades | +0.066 |
mercy | +0.064 |
backup | +0.064 |
Neg logit contributions | |
around | -0.114 |
cy | -0.106 |
air | -0.104 |
down | -0.104 |
et | -0.103 |
Token | pretty |
Token ID | 2495 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
ves | +0.229 |
vern | +0.225 |
ades | +0.202 |
mercy | +0.198 |
backup | +0.195 |
Neg logit contributions | |
around | -0.281 |
cy | -0.258 |
air | -0.257 |
down | -0.253 |
et | -0.248 |
Token | princess |
Token ID | 21752 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
around | +0.147 |
| | +0.136 |
rated | +0.135 |
cy | +0.133 |
air | +0.132 |
Neg logit contributions | |
ves | -0.103 |
vern | -0.098 |
ades | -0.090 |
wife | -0.090 |
forgiveness | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
vern | +0.160 |
ves | +0.156 |
ades | +0.145 |
backup | +0.145 |
mercy | +0.144 |
Neg logit contributions | |
around | -0.134 |
cy | -0.117 |
down | -0.114 |
et | -0.113 |
air | -0.113 |
Token | day |
Token ID | 1110 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
around | +0.049 |
et | +0.045 |
down | +0.044 |
cy | +0.044 |
air | +0.042 |
Neg logit contributions | |
ves | -0.096 |
vern | -0.090 |
keys | -0.087 |
forgiveness | -0.086 |
mercy | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
around | +0.463 |
down | +0.402 |
air | +0.388 |
cy | +0.369 |
through | +0.341 |
Neg logit contributions | |
vern | -0.871 |
ves | -0.835 |
ades | -0.793 |
mercy | -0.780 |
keys | -0.765 |
Token | a |
Token ID | 257 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
vern | +0.042 |
ves | +0.040 |
ades | +0.036 |
mercy | +0.035 |
backup | +0.034 |
Neg logit contributions | |
around | -0.037 |
down | -0.034 |
air | -0.034 |
cy | -0.032 |
through | -0.031 |
Token | loud |
Token ID | 7812 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ves | +0.257 |
vern | +0.253 |
ades | +0.224 |
mercy | +0.218 |
keys | +0.211 |
Neg logit contributions | |
around | -0.245 |
air | -0.229 |
cy | -0.222 |
down | -0.219 |
wind | -0.199 |
Token | noise |
Token ID | 7838 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
cy | +0.165 |
around | +0.161 |
| | +0.153 |
ained | +0.151 |
amp | +0.150 |
Neg logit contributions | |
ves | -0.122 |
keys | -0.101 |
vern | -0.101 |
mercy | -0.100 |
ggy | -0.099 |
Token | came |
Token ID | 1625 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
ves | +0.004 |
vern | +0.004 |
ades | +0.003 |
mercy | +0.003 |
backup | +0.003 |
Neg logit contributions | |
around | -0.003 |
cy | -0.003 |
air | -0.003 |
down | -0.003 |
et | -0.003 |
Token | from |
Token ID | 422 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
vern | +0.046 |
ves | +0.046 |
ades | +0.042 |
mercy | +0.041 |
backup | +0.040 |
Neg logit contributions | |
cy | -0.043 |
around | -0.043 |
et | -0.043 |
air | -0.041 |
| | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
mercy | +0.284 |
backup | +0.276 |
ves | +0.272 |
vern | +0.263 |
forgiveness | +0.262 |
Neg logit contributions | |
cy | -0.299 |
rated | -0.293 |
amp | -0.290 |
et | -0.288 |
| | -0.285 |
Token | village |
Token ID | 7404 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
around | +0.204 |
cy | +0.189 |
et | +0.184 |
down | +0.179 |
| | +0.178 |
Neg logit contributions | |
ves | -0.245 |
vern | -0.241 |
backup | -0.226 |
mercy | -0.225 |
ades | -0.224 |
Token | . |
Token ID | 13 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
around | +0.025 |
cy | +0.024 |
air | +0.023 |
et | +0.022 |
| | +0.022 |
Neg logit contributions | |
ves | -0.031 |
vern | -0.030 |
ades | -0.028 |
keys | -0.027 |
mercy | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
around | +0.021 |
et | +0.021 |
cy | +0.021 |
rated | +0.020 |
ening | +0.019 |
Neg logit contributions | |
ves | -0.036 |
vern | -0.034 |
ades | -0.033 |
His | -0.033 |
keys | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
around | +0.347 |
cy | +0.303 |
down | +0.299 |
air | +0.288 |
| | +0.279 |
Neg logit contributions | |
ves | -0.548 |
vern | -0.538 |
mercy | -0.503 |
ades | -0.501 |
backup | -0.493 |
Token | there |
Token ID | 612 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
ves | +0.038 |
vern | +0.035 |
His | +0.032 |
ades | +0.032 |
else | +0.031 |
Neg logit contributions | |
air | -0.054 |
et | -0.054 |
around | -0.053 |
ening | -0.051 |
rated | -0.051 |
Token | was |
Token ID | 373 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
around | +0.053 |
air | +0.050 |
rated | +0.050 |
et | +0.050 |
down | +0.049 |
Neg logit contributions | |
ves | -0.043 |
vern | -0.037 |
ades | -0.035 |
ggy | -0.034 |
His | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
ves | +0.075 |
vern | +0.074 |
ades | +0.064 |
mercy | +0.062 |
backup | +0.062 |
Neg logit contributions | |
around | -0.126 |
cy | -0.117 |
air | -0.116 |
et | -0.115 |
down | -0.115 |
Token | big |
Token ID | 1263 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ves | +0.224 |
vern | +0.220 |
ades | +0.196 |
mercy | +0.191 |
backup | +0.191 |
Neg logit contributions | |
around | -0.298 |
cy | -0.272 |
air | -0.272 |
down | -0.268 |
et | -0.265 |
Token | bear |
Token ID | 6842 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
wife | +0.040 |
ves | +0.037 |
crew | +0.036 |
backup | +0.035 |
forgiveness | +0.035 |
Neg logit contributions | |
rated | -0.064 |
around | -0.061 |
| | -0.061 |
ained | -0.060 |
idget | -0.058 |
Token | who |
Token ID | 508 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
around | +0.039 |
cy | +0.034 |
down | +0.033 |
air | +0.032 |
et | +0.032 |
Neg logit contributions | |
vern | -0.051 |
ves | -0.050 |
ades | -0.046 |
mercy | -0.045 |
backup | -0.045 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
ves | +0.205 |
vern | +0.188 |
His | +0.183 |
ggy | +0.176 |
ades | +0.168 |
Neg logit contributions | |
around | -0.191 |
air | -0.187 |
amp | -0.182 |
down | -0.182 |
ening | -0.181 |
Token | to |
Token ID | 284 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
around | +0.168 |
down | +0.153 |
air | +0.152 |
cy | +0.143 |
et | +0.138 |
Neg logit contributions | |
ves | -0.150 |
vern | -0.147 |
ades | -0.130 |
keys | -0.127 |
mercy | -0.124 |
Token | play |
Token ID | 711 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
vern | +0.184 |
ves | +0.184 |
ades | +0.169 |
keys | +0.164 |
mercy | +0.164 |
Neg logit contributions | |
around | -0.140 |
air | -0.125 |
down | -0.123 |
cy | -0.120 |
et | -0.119 |
Token | in |
Token ID | 287 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
around | +0.075 |
down | +0.061 |
air | +0.058 |
cy | +0.054 |
et | +0.054 |
Neg logit contributions | |
vern | -0.143 |
ves | -0.140 |
mercy | -0.131 |
keys | -0.130 |
backup | -0.129 |
Token | whenever |
Token ID | 8797 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
around | +0.044 |
down | +0.038 |
air | +0.037 |
cy | +0.037 |
et | +0.036 |
Neg logit contributions | |
vern | -0.077 |
ves | -0.076 |
ades | -0.070 |
mercy | -0.070 |
backup | -0.069 |
Token | he |
Token ID | 339 |
Feature activation | +9.30e+00 |
Pos logit contributions | |
vern | +0.093 |
ves | +0.082 |
ades | +0.079 |
keys | +0.075 |
mercy | +0.073 |
Neg logit contributions | |
around | -0.128 |
down | -0.119 |
air | -0.112 |
cy | -0.111 |
night | -0.110 |
Token | played |
Token ID | 2826 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
ves | +0.471 |
else | +0.412 |
vern | +0.410 |
ades | +0.408 |
His | +0.392 |
Neg logit contributions | |
around | -0.462 |
rated | -0.459 |
air | -0.443 |
ening | -0.443 |
| | -0.439 |
Token | . |
Token ID | 13 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
around | +0.168 |
cy | +0.166 |
air | +0.159 |
rated | +0.158 |
| | +0.156 |
Neg logit contributions | |
ves | -0.159 |
vern | -0.155 |
ades | -0.142 |
backup | -0.135 |
forgiveness | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
around | +0.028 |
rated | +0.026 |
cy | +0.026 |
ening | +0.026 |
et | +0.026 |
Neg logit contributions | |
ves | -0.024 |
vern | -0.022 |
His | -0.022 |
ades | -0.021 |
forgiveness | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ves | +0.035 |
vern | +0.034 |
ades | +0.031 |
mercy | +0.031 |
backup | +0.031 |
Neg logit contributions | |
around | -0.030 |
cy | -0.027 |
air | -0.027 |
down | -0.027 |
et | -0.026 |
Token | One |
Token ID | 3198 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
vern | +0.026 |
ves | +0.025 |
mercy | +0.023 |
backup | +0.022 |
forgiveness | +0.022 |
Neg logit contributions | |
around | -0.041 |
cy | -0.038 |
et | -0.037 |
air | -0.037 |
down | -0.037 |
Token | day |
Token ID | 1110 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
ves | +0.501 |
vern | +0.489 |
forgiveness | +0.454 |
ades | +0.451 |
wife | +0.451 |
Neg logit contributions | |
around | -0.189 |
air | -0.163 |
et | -0.162 |
ening | -0.155 |
down | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
around | +0.468 |
down | +0.415 |
cy | +0.398 |
air | +0.396 |
et | +0.351 |
Neg logit contributions | |
vern | -0.850 |
ves | -0.823 |
ades | -0.769 |
mercy | -0.766 |
keys | -0.757 |
Token | Tim |
Token ID | 5045 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
vern | +0.068 |
ves | +0.065 |
ades | +0.061 |
mercy | +0.060 |
keys | +0.060 |
Neg logit contributions | |
around | -0.020 |
down | -0.017 |
cy | -0.016 |
air | -0.015 |
et | -0.012 |
Token | my |
Token ID | 1820 |
Feature activation | -9.01e+00 |
Pos logit contributions | |
around | +0.276 |
ening | +0.246 |
air | +0.229 |
| | +0.222 |
amp | +0.218 |
Neg logit contributions | |
ves | -0.450 |
vern | -0.439 |
His | -0.428 |
wife | -0.428 |
forgiveness | -0.420 |
Token | adventure |
Token ID | 8855 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ves | +0.043 |
vern | +0.042 |
ades | +0.038 |
backup | +0.038 |
mercy | +0.038 |
Neg logit contributions | |
around | -0.055 |
cy | -0.053 |
rated | -0.050 |
air | -0.050 |
| | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
ves | +0.071 |
vern | +0.068 |
ades | +0.063 |
mercy | +0.062 |
backup | +0.061 |
Neg logit contributions | |
around | -0.058 |
cy | -0.057 |
air | -0.055 |
et | -0.053 |
| | -0.052 |
Token | It |
Token ID | 632 |
Feature activation | -9.44e+00 |
Pos logit contributions | |
cy | +0.018 |
around | +0.017 |
et | +0.017 |
rated | +0.016 |
ening | +0.016 |
Neg logit contributions | |
ves | -0.027 |
His | -0.026 |
backup | -0.025 |
mercy | -0.024 |
wife | -0.024 |
Token | went |
Token ID | 1816 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
around | +0.456 |
cy | +0.411 |
air | +0.407 |
down | +0.399 |
et | +0.390 |
Neg logit contributions | |
ves | -0.574 |
vern | -0.566 |
ades | -0.519 |
mercy | -0.510 |
backup | -0.505 |
Token | up |
Token ID | 510 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
cy | +0.157 |
et | +0.143 |
around | +0.143 |
air | +0.142 |
rated | +0.141 |
Neg logit contributions | |
ves | -0.165 |
vern | -0.158 |
backup | -0.151 |
ades | -0.149 |
mercy | -0.142 |
Token | high |
Token ID | 1029 |
Feature activation | -9.89e+00 |
Pos logit contributions | |
around | +0.348 |
cy | +0.346 |
et | +0.340 |
air | +0.329 |
rated | +0.328 |
Neg logit contributions | |
ves | -0.388 |
vern | -0.373 |
ades | -0.349 |
backup | -0.341 |
mercy | -0.333 |
Token | on |
Token ID | 319 |
Feature activation | -7.95e+00 |
Pos logit contributions | |
| | +0.452 |
cy | +0.439 |
rated | +0.417 |
idget | +0.416 |
et | +0.412 |
Neg logit contributions | |
ves | -0.540 |
ades | -0.495 |
vern | -0.484 |
keys | -0.459 |
mercy | -0.452 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
around | +0.361 |
cy | +0.322 |
air | +0.319 |
down | +0.313 |
et | +0.305 |
Neg logit contributions | |
ves | -0.510 |
vern | -0.504 |
ades | -0.464 |
mercy | -0.456 |
backup | -0.452 |
Token | waves |
Token ID | 9813 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
around | +0.233 |
cy | +0.229 |
| | +0.215 |
down | +0.212 |
et | +0.211 |
Neg logit contributions | |
ves | -0.205 |
vern | -0.198 |
ades | -0.182 |
backup | -0.174 |
mercy | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ves | +0.094 |
vern | +0.088 |
ades | +0.083 |
backup | +0.081 |
keys | +0.080 |
Neg logit contributions | |
cy | -0.076 |
around | -0.074 |
| | -0.073 |
rated | -0.071 |
air | -0.070 |
Token | The |
Token ID | 383 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
cy | +0.018 |
et | +0.017 |
rated | +0.016 |
around | +0.016 |
ening | +0.015 |
Neg logit contributions | |
ves | -0.025 |
His | -0.023 |
backup | -0.022 |
wife | -0.022 |
ades | -0.022 |
Token | out |
Token ID | 503 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
ves | +0.050 |
vern | +0.048 |
backup | +0.045 |
ades | +0.045 |
mercy | +0.044 |
Neg logit contributions | |
around | -0.044 |
cy | -0.041 |
rated | -0.040 |
air | -0.040 |
| | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
around | +0.027 |
down | +0.024 |
air | +0.024 |
cy | +0.022 |
through | +0.022 |
Neg logit contributions | |
vern | -0.032 |
ves | -0.032 |
keys | -0.029 |
ades | -0.028 |
mercy | -0.028 |
Token | small |
Token ID | 1402 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ves | +0.254 |
vern | +0.251 |
mercy | +0.229 |
keys | +0.225 |
ades | +0.223 |
Neg logit contributions | |
around | -0.248 |
air | -0.230 |
down | -0.229 |
cy | -0.212 |
through | -0.198 |
Token | box |
Token ID | 3091 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
ves | +0.129 |
vern | +0.126 |
ades | +0.114 |
keys | +0.111 |
mercy | +0.110 |
Neg logit contributions | |
around | -0.135 |
air | -0.125 |
cy | -0.123 |
down | -0.122 |
et | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
around | +0.021 |
down | +0.018 |
air | +0.016 |
cy | +0.016 |
et | +0.016 |
Neg logit contributions | |
vern | -0.030 |
ves | -0.030 |
ades | -0.027 |
forgiveness | -0.027 |
mercy | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
around | +0.021 |
cy | +0.018 |
air | +0.018 |
et | +0.017 |
down | +0.017 |
Neg logit contributions | |
ves | -0.039 |
vern | -0.038 |
ades | -0.036 |
backup | -0.035 |
mercy | -0.035 |
Token | had |
Token ID | 550 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
around | +0.401 |
cy | +0.341 |
down | +0.331 |
air | +0.322 |
et | +0.318 |
Neg logit contributions | |
vern | -0.710 |
ves | -0.651 |
backup | -0.627 |
ades | -0.624 |
mercy | -0.614 |
Token | a |
Token ID | 257 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
air | +0.219 |
around | +0.219 |
down | +0.190 |
et | +0.187 |
through | +0.180 |
Neg logit contributions | |
vern | -0.252 |
ves | -0.241 |
keys | -0.228 |
ades | -0.223 |
forgiveness | -0.216 |
Token | colorful |
Token ID | 20239 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
ves | +0.264 |
vern | +0.262 |
keys | +0.236 |
ades | +0.236 |
mercy | +0.235 |
Neg logit contributions | |
around | -0.236 |
air | -0.222 |
down | -0.213 |
cy | -0.198 |
et | -0.189 |
Token | sticker |
Token ID | 27735 |
Feature activation | +7.32e+00 |
Pos logit contributions | |
around | +0.037 |
air | +0.036 |
down | +0.034 |
et | +0.032 |
cy | +0.032 |
Neg logit contributions | |
vern | -0.038 |
ves | -0.037 |
keys | -0.034 |
mercy | -0.033 |
ades | -0.033 |
Token | on |
Token ID | 319 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
vern | +0.471 |
ves | +0.466 |
ades | +0.429 |
mercy | +0.426 |
backup | +0.420 |
Neg logit contributions | |
around | -0.338 |
air | -0.293 |
down | -0.289 |
cy | -0.288 |
et | -0.281 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
around | +0.302 |
down | +0.271 |
air | +0.271 |
et | +0.255 |
cy | +0.249 |
Neg logit contributions | |
vern | -0.248 |
ves | -0.241 |
ades | -0.228 |
keys | -0.222 |
mercy | -0.212 |
Token | x |
Token ID | 2124 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
around | +0.245 |
air | +0.226 |
cy | +0.223 |
down | +0.221 |
et | +0.216 |
Neg logit contributions | |
ves | -0.204 |
vern | -0.200 |
ades | -0.182 |
keys | -0.173 |
mercy | -0.173 |
Token | - |
Token ID | 12 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
around | +0.168 |
et | +0.153 |
down | +0.146 |
air | +0.144 |
cy | +0.138 |
Neg logit contributions | |
vern | -0.172 |
ves | -0.163 |
ades | -0.162 |
keys | -0.152 |
backup | -0.149 |
Token | ray |
Token ID | 2433 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
ves | +0.026 |
vern | +0.026 |
ades | +0.024 |
mercy | +0.023 |
backup | +0.022 |
Neg logit contributions | |
around | -0.033 |
cy | -0.030 |
air | -0.029 |
down | -0.029 |
et | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
ves | +0.201 |
vern | +0.197 |
ades | +0.180 |
mercy | +0.178 |
backup | +0.176 |
Neg logit contributions | |
around | -0.173 |
cy | -0.158 |
air | -0.155 |
down | -0.152 |
et | -0.149 |
Token | The |
Token ID | 383 |
Feature activation | -8.17e+00 |
Pos logit contributions | |
around | +0.016 |
cy | +0.014 |
et | +0.014 |
rated | +0.013 |
air | +0.013 |
Neg logit contributions | |
ves | -0.027 |
vern | -0.027 |
backup | -0.025 |
ades | -0.025 |
mercy | -0.024 |
Token | doctor |
Token ID | 6253 |
Feature activation | +9.17e+00 |
Pos logit contributions | |
around | +0.572 |
air | +0.558 |
cy | +0.526 |
down | +0.525 |
et | +0.513 |
Neg logit contributions | |
ves | -0.324 |
vern | -0.320 |
ades | -0.299 |
keys | -0.259 |
backup | -0.237 |
Token | was |
Token ID | 373 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
vern | +0.535 |
ves | +0.513 |
ades | +0.479 |
backup | +0.468 |
mercy | +0.457 |
Neg logit contributions | |
around | -0.494 |
cy | -0.441 |
air | -0.428 |
et | -0.426 |
down | -0.420 |
Token | very |
Token ID | 845 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
ves | +0.123 |
vern | +0.119 |
ades | +0.114 |
keys | +0.110 |
backup | +0.108 |
Neg logit contributions | |
around | -0.082 |
down | -0.068 |
air | -0.068 |
et | -0.065 |
cy | -0.062 |
Token | nice |
Token ID | 3621 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
around | +0.328 |
down | +0.287 |
air | +0.271 |
alone | +0.267 |
cy | +0.257 |
Neg logit contributions | |
ves | -0.384 |
vern | -0.348 |
ades | -0.345 |
keys | -0.320 |
lor | -0.318 |
Token | and |
Token ID | 290 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ves | +0.110 |
vern | +0.109 |
ades | +0.101 |
mercy | +0.099 |
backup | +0.098 |
Neg logit contributions | |
around | -0.068 |
cy | -0.059 |
air | -0.059 |
down | -0.058 |
et | -0.056 |
Token | What |
Token ID | 2061 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ves | +0.147 |
vern | +0.144 |
ades | +0.127 |
mercy | +0.124 |
backup | +0.122 |
Neg logit contributions | |
around | -0.223 |
air | -0.206 |
cy | -0.205 |
down | -0.202 |
et | -0.200 |
Token | happened |
Token ID | 3022 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ves | +0.121 |
vern | +0.119 |
ades | +0.111 |
backup | +0.109 |
mercy | +0.108 |
Neg logit contributions | |
around | -0.081 |
cy | -0.071 |
air | -0.071 |
down | -0.069 |
| | -0.065 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
vern | +0.117 |
ves | +0.116 |
mercy | +0.107 |
ades | +0.106 |
backup | +0.106 |
Neg logit contributions | |
around | -0.117 |
cy | -0.113 |
air | -0.111 |
et | -0.110 |
| | -0.109 |
Token | her |
Token ID | 607 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
around | +0.060 |
down | +0.054 |
air | +0.053 |
cy | +0.052 |
| | +0.048 |
Neg logit contributions | |
vern | -0.058 |
ves | -0.057 |
ades | -0.053 |
mercy | -0.051 |
keys | -0.050 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
ves | +0.058 |
vern | +0.056 |
ades | +0.050 |
keys | +0.048 |
backup | +0.047 |
Neg logit contributions | |
around | -0.098 |
cy | -0.091 |
down | -0.090 |
air | -0.090 |
et | -0.086 |
Token | my |
Token ID | 1820 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
ves | +0.293 |
vern | +0.291 |
mercy | +0.275 |
forgiveness | +0.273 |
ades | +0.272 |
Neg logit contributions | |
around | -0.090 |
air | -0.079 |
cy | -0.077 |
| | -0.073 |
et | -0.069 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
around | +0.460 |
down | +0.409 |
air | +0.394 |
cy | +0.392 |
et | +0.385 |
Neg logit contributions | |
vern | -0.551 |
ves | -0.540 |
ades | -0.505 |
backup | -0.492 |
mercy | -0.479 |
Token | . |
Token ID | 13 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
ves | +0.063 |
vern | +0.062 |
forgiveness | +0.057 |
mercy | +0.057 |
ades | +0.055 |
Neg logit contributions | |
around | -0.054 |
air | -0.052 |
cy | -0.051 |
et | -0.050 |
| | -0.049 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
around | +0.026 |
cy | +0.024 |
air | +0.024 |
et | +0.023 |
down | +0.023 |
Neg logit contributions | |
ves | -0.027 |
vern | -0.027 |
ades | -0.024 |
mercy | -0.024 |
backup | -0.024 |
Token | told |
Token ID | 1297 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
around | +0.278 |
cy | +0.246 |
down | +0.245 |
air | +0.245 |
et | +0.237 |
Neg logit contributions | |
vern | -0.322 |
ves | -0.321 |
ades | -0.293 |
backup | -0.288 |
mercy | -0.286 |
Token | her |
Token ID | 607 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ves | +0.315 |
vern | +0.311 |
ades | +0.285 |
mercy | +0.277 |
keys | +0.276 |
Neg logit contributions | |
around | -0.270 |
air | -0.241 |
cy | -0.241 |
down | -0.238 |
et | -0.231 |
Token | the |
Token ID | 262 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
ves | +0.279 |
vern | +0.272 |
ades | +0.250 |
mercy | +0.247 |
backup | +0.244 |
Neg logit contributions | |
around | -0.234 |
cy | -0.218 |
air | -0.208 |
down | -0.206 |
| | -0.203 |
Token | jungle |
Token ID | 20712 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
around | +0.222 |
cy | +0.219 |
| | +0.214 |
et | +0.211 |
down | +0.206 |
Neg logit contributions | |
ves | -0.195 |
vern | -0.179 |
keys | -0.175 |
ades | -0.172 |
wife | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
around | +0.050 |
cy | +0.045 |
air | +0.044 |
down | +0.044 |
et | +0.043 |
Neg logit contributions | |
ves | -0.070 |
vern | -0.069 |
ades | -0.064 |
mercy | -0.063 |
backup | -0.062 |
Token | But |
Token ID | 887 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
around | +0.018 |
rated | +0.018 |
et | +0.017 |
ening | +0.017 |
cy | +0.017 |
Neg logit contributions | |
ves | -0.018 |
vern | -0.017 |
ades | -0.016 |
His | -0.016 |
backup | -0.016 |
Token | one |
Token ID | 530 |
Feature activation | +7.51e+00 |
Pos logit contributions | |
around | +0.385 |
cy | +0.349 |
air | +0.346 |
down | +0.342 |
et | +0.336 |
Neg logit contributions | |
ves | -0.381 |
vern | -0.381 |
ades | -0.345 |
mercy | -0.335 |
backup | -0.333 |
Token | day |
Token ID | 1110 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
ves | +0.597 |
vern | +0.573 |
forgiveness | +0.544 |
keys | +0.541 |
mercy | +0.540 |
Neg logit contributions | |
around | -0.197 |
air | -0.172 |
down | -0.166 |
cy | -0.157 |
| | -0.157 |
Token | , |
Token ID | 11 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
around | +0.447 |
down | +0.388 |
air | +0.372 |
cy | +0.339 |
through | +0.327 |
Neg logit contributions | |
vern | -0.883 |
ves | -0.824 |
ades | -0.795 |
mercy | -0.771 |
backup | -0.757 |
Token | the |
Token ID | 262 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
vern | +0.067 |
ves | +0.064 |
ades | +0.060 |
mercy | +0.057 |
backup | +0.056 |
Neg logit contributions | |
around | -0.039 |
down | -0.034 |
air | -0.034 |
cy | -0.032 |
et | -0.029 |
Token | music |
Token ID | 2647 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
around | +0.218 |
cy | +0.211 |
| | +0.204 |
down | +0.196 |
amp | +0.196 |
Neg logit contributions | |
ves | -0.211 |
vern | -0.196 |
keys | -0.193 |
ades | -0.186 |
wife | -0.184 |
Token | was |
Token ID | 373 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
vern | +0.099 |
ves | +0.098 |
ades | +0.090 |
mercy | +0.089 |
backup | +0.089 |
Neg logit contributions | |
around | -0.074 |
air | -0.065 |
cy | -0.065 |
down | -0.064 |
et | -0.062 |
Token | different |
Token ID | 1180 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ves | +0.114 |
vern | +0.113 |
ades | +0.103 |
mercy | +0.102 |
backup | +0.101 |
Neg logit contributions | |
around | -0.086 |
cy | -0.081 |
air | -0.078 |
down | -0.076 |
| | -0.075 |