Token | park |
Token ID | 3952 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
aroo | +0.189 |
ter | +0.171 |
apped | +0.160 |
ovable | +0.157 |
itte | +0.156 |
Neg logit contributions | |
mess | -0.115 |
wra | -0.091 |
aj | -0.091 |
pic | -0.088 |
slippery | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
mess | +0.060 |
aj | +0.050 |
wra | +0.049 |
onna | +0.047 |
slippery | +0.047 |
Neg logit contributions | |
aroo | -0.071 |
ter | -0.064 |
itte | -0.057 |
ovable | -0.056 |
crow | -0.056 |
Token | The |
Token ID | 383 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
aroo | +0.102 |
ter | +0.089 |
crow | +0.077 |
apped | +0.076 |
itte | +0.073 |
Neg logit contributions | |
mess | -0.136 |
aj | -0.123 |
wra | -0.117 |
onna | -0.116 |
pic | -0.114 |
Token | k |
Token ID | 479 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aroo | +0.465 |
ovable | +0.460 |
onel | +0.455 |
itte | +0.442 |
apped | +0.436 |
Neg logit contributions | |
mess | -0.370 |
slippery | -0.305 |
wra | -0.283 |
fun | -0.280 |
steep | -0.276 |
Token | ang |
Token ID | 648 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
aroo | +0.140 |
ter | +0.132 |
ovable | +0.119 |
itte | +0.118 |
citizens | +0.117 |
Neg logit contributions | |
mess | -0.272 |
aj | -0.252 |
wra | -0.249 |
liv | -0.247 |
slippery | -0.243 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
onel | +0.114 |
ter | +0.105 |
crew | +0.096 |
ovable | +0.093 |
citizens | +0.092 |
Neg logit contributions | |
mess | -0.895 |
slippery | -0.856 |
liv | -0.855 |
steep | -0.838 |
wra | -0.837 |
Token | is |
Token ID | 318 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
aroo | +1.436 |
ter | +1.286 |
crow | +1.195 |
apped | +1.164 |
itte | +1.149 |
Neg logit contributions | |
mess | -0.896 |
aj | -0.810 |
wra | -0.737 |
onna | -0.729 |
fault | -0.717 |
Token | big |
Token ID | 1263 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
mess | +0.220 |
aj | +0.197 |
wra | +0.184 |
onna | +0.181 |
pic | +0.177 |
Neg logit contributions | |
aroo | -0.266 |
ter | -0.240 |
crow | -0.212 |
apped | -0.211 |
itte | -0.206 |
Token | and |
Token ID | 290 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
mess | +0.124 |
aj | +0.118 |
liv | +0.112 |
onna | +0.111 |
aman | +0.107 |
Neg logit contributions | |
aroo | -0.141 |
ter | -0.131 |
crow | -0.115 |
apped | -0.110 |
member | -0.110 |
Token | brown |
Token ID | 7586 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
mess | +0.097 |
aj | +0.090 |
aman | +0.083 |
fault | +0.083 |
onna | +0.080 |
Neg logit contributions | |
aroo | -0.121 |
ter | -0.106 |
crow | -0.096 |
itte | -0.092 |
apped | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
mess | +0.089 |
aj | +0.076 |
wra | +0.076 |
onna | +0.072 |
fault | +0.071 |
Neg logit contributions | |
aroo | -0.108 |
ter | -0.095 |
itte | -0.087 |
crow | -0.085 |
apped | -0.085 |
Token | they |
Token ID | 484 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
aroo | +0.051 |
ter | +0.046 |
apped | +0.040 |
crow | +0.038 |
member | +0.037 |
Neg logit contributions | |
mess | -0.057 |
aj | -0.052 |
onna | -0.050 |
fault | -0.048 |
icol | -0.047 |
Token | see |
Token ID | 766 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
aroo | +0.015 |
ter | +0.013 |
apped | +0.011 |
crow | +0.011 |
ovable | +0.011 |
Neg logit contributions | |
mess | -0.013 |
pic | -0.011 |
slippery | -0.010 |
wra | -0.010 |
pays | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
aroo | +0.251 |
ter | +0.224 |
crow | +0.200 |
apped | +0.197 |
itte | +0.194 |
Neg logit contributions | |
mess | -0.222 |
aj | -0.197 |
wra | -0.187 |
onna | -0.182 |
pic | -0.179 |
Token | k |
Token ID | 479 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
aroo | +0.079 |
ter | +0.072 |
crow | +0.064 |
apped | +0.062 |
itte | +0.062 |
Neg logit contributions | |
mess | -0.060 |
aj | -0.055 |
onna | -0.050 |
wra | -0.050 |
fault | -0.049 |
Token | ang |
Token ID | 648 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
aroo | +0.142 |
ter | +0.130 |
ovable | +0.122 |
citizens | +0.120 |
sailors | +0.120 |
Neg logit contributions | |
mess | -0.268 |
wra | -0.246 |
aj | -0.241 |
liv | -0.237 |
slippery | -0.233 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
citizens | +0.197 |
onel | +0.171 |
crew | +0.155 |
sailors | +0.150 |
ovable | +0.148 |
Neg logit contributions | |
mess | -0.765 |
snowball | -0.761 |
slippery | -0.760 |
liv | -0.742 |
gh | -0.731 |
Token | in |
Token ID | 287 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
aroo | +1.302 |
ter | +1.158 |
itte | +1.128 |
ovable | +1.118 |
citizens | +1.099 |
Neg logit contributions | |
mess | -1.012 |
wra | -0.773 |
slippery | -0.763 |
aj | -0.736 |
onna | -0.731 |
Token | the |
Token ID | 262 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
aroo | +0.496 |
ter | +0.425 |
crow | +0.383 |
member | +0.349 |
apped | +0.346 |
Neg logit contributions | |
mess | -0.647 |
aj | -0.622 |
onna | -0.567 |
wra | -0.564 |
icol | -0.551 |
Token | park |
Token ID | 3952 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
aroo | +0.189 |
ter | +0.171 |
apped | +0.160 |
ovable | +0.157 |
itte | +0.156 |
Neg logit contributions | |
mess | -0.115 |
wra | -0.091 |
aj | -0.091 |
pic | -0.088 |
slippery | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
mess | +0.060 |
aj | +0.050 |
wra | +0.049 |
onna | +0.047 |
slippery | +0.047 |
Neg logit contributions | |
aroo | -0.071 |
ter | -0.064 |
itte | -0.057 |
ovable | -0.056 |
crow | -0.056 |
Token | The |
Token ID | 383 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
aroo | +0.102 |
ter | +0.089 |
crow | +0.077 |
apped | +0.076 |
itte | +0.073 |
Neg logit contributions | |
mess | -0.136 |
aj | -0.123 |
wra | -0.117 |
onna | -0.116 |
pic | -0.114 |
Token | find |
Token ID | 1064 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
mess | +0.109 |
aj | +0.101 |
wra | +0.095 |
onna | +0.092 |
liv | +0.091 |
Neg logit contributions | |
aroo | -0.097 |
ter | -0.086 |
crow | -0.074 |
apped | -0.072 |
member | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
aroo | +0.373 |
ter | +0.345 |
apped | +0.326 |
ive | +0.310 |
itte | +0.309 |
Neg logit contributions | |
mess | -0.220 |
slippery | -0.188 |
wra | -0.178 |
fun | -0.177 |
scar | -0.177 |
Token | big |
Token ID | 1263 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
aroo | +0.173 |
ter | +0.153 |
apped | +0.141 |
crow | +0.138 |
itte | +0.136 |
Neg logit contributions | |
mess | -0.149 |
aj | -0.127 |
wra | -0.122 |
onna | -0.119 |
fault | -0.118 |
Token | k |
Token ID | 479 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
mess | +0.113 |
aj | +0.106 |
wra | +0.096 |
liv | +0.096 |
onna | +0.095 |
Neg logit contributions | |
aroo | -0.139 |
ter | -0.127 |
crow | -0.113 |
apped | -0.108 |
member | -0.107 |
Token | ang |
Token ID | 648 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
aroo | +0.146 |
sailors | +0.139 |
citizens | +0.136 |
ter | +0.136 |
Queen | +0.135 |
Neg logit contributions | |
mess | -0.226 |
aj | -0.224 |
zan | -0.218 |
wra | -0.216 |
onna | -0.216 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
citizens | +0.136 |
apped | +0.133 |
sailors | +0.124 |
married | +0.116 |
ovable | +0.108 |
Neg logit contributions | |
slippery | -0.782 |
onna | -0.764 |
steep | -0.759 |
mess | -0.759 |
gh | -0.752 |
Token | and |
Token ID | 290 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
aroo | +1.450 |
ter | +1.297 |
apped | +1.222 |
crow | +1.220 |
itte | +1.203 |
Neg logit contributions | |
mess | -0.923 |
aj | -0.737 |
wra | -0.720 |
slippery | -0.702 |
onna | -0.701 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
mess | +0.094 |
aj | +0.080 |
wra | +0.078 |
onna | +0.077 |
slippery | +0.077 |
Neg logit contributions | |
aroo | -0.115 |
ter | -0.104 |
crow | -0.095 |
apped | -0.094 |
itte | -0.092 |
Token | for |
Token ID | 329 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
aroo | +0.288 |
ter | +0.255 |
apped | +0.238 |
crow | +0.236 |
itte | +0.234 |
Neg logit contributions | |
mess | -0.179 |
wra | -0.144 |
onna | -0.143 |
mistake | -0.142 |
pays | -0.141 |
Token | his |
Token ID | 465 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
aroo | +0.109 |
ter | +0.098 |
apped | +0.092 |
itte | +0.089 |
crow | +0.088 |
Neg logit contributions | |
mess | -0.135 |
wra | -0.119 |
slippery | -0.118 |
pic | -0.118 |
fun | -0.117 |
Token | help |
Token ID | 1037 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
mess | +0.065 |
aj | +0.059 |
fault | +0.057 |
wra | +0.056 |
onna | +0.056 |
Neg logit contributions | |
aroo | -0.048 |
ter | -0.043 |
apped | -0.038 |
crow | -0.038 |
itte | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
aroo | +0.087 |
ter | +0.080 |
apped | +0.071 |
crow | +0.070 |
itte | +0.070 |
Neg logit contributions | |
mess | -0.058 |
aj | -0.050 |
onna | -0.049 |
wra | -0.048 |
pic | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
aroo | +0.056 |
ter | +0.050 |
crow | +0.045 |
apped | +0.044 |
itte | +0.043 |
Neg logit contributions | |
mess | -0.052 |
aj | -0.046 |
wra | -0.043 |
onna | -0.043 |
pic | -0.042 |
Token | The |
Token ID | 464 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
aroo | +0.055 |
ter | +0.051 |
apped | +0.046 |
ovable | +0.045 |
itte | +0.045 |
Neg logit contributions | |
mess | -0.049 |
aj | -0.043 |
wra | -0.042 |
slippery | -0.041 |
onna | -0.041 |
Token | k |
Token ID | 479 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
aroo | +0.203 |
ter | +0.184 |
apped | +0.179 |
ovable | +0.178 |
onel | +0.175 |
Neg logit contributions | |
mess | -0.188 |
slippery | -0.155 |
wra | -0.146 |
steep | -0.144 |
aj | -0.143 |
Token | ang |
Token ID | 648 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ter | +0.146 |
aroo | +0.145 |
citizens | +0.142 |
ovable | +0.141 |
itte | +0.139 |
Neg logit contributions | |
mess | -0.227 |
aj | -0.210 |
wra | -0.210 |
snowball | -0.208 |
slippery | -0.206 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
onel | +0.154 |
citizens | +0.144 |
ovable | +0.135 |
crew | +0.126 |
sailors | +0.119 |
Neg logit contributions | |
mess | -0.817 |
slippery | -0.803 |
wob | -0.799 |
snowball | -0.797 |
liv | -0.779 |
Token | nods |
Token ID | 34833 |
Feature activation | +3.24e-03 |
Pos logit contributions | |
aroo | +1.432 |
ter | +1.286 |
crow | +1.206 |
apped | +1.172 |
itte | +1.157 |
Neg logit contributions | |
mess | -0.854 |
aj | -0.779 |
wra | -0.710 |
liv | -0.702 |
onna | -0.699 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
aroo | +0.007 |
ter | +0.006 |
crow | +0.005 |
apped | +0.005 |
itte | +0.005 |
Neg logit contributions | |
mess | -0.006 |
aj | -0.006 |
wra | -0.005 |
onna | -0.005 |
pic | -0.005 |
Token | It |
Token ID | 632 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
aroo | +0.120 |
ter | +0.112 |
member | +0.099 |
crow | +0.096 |
pilot | +0.095 |
Neg logit contributions | |
mess | -0.090 |
onna | -0.083 |
aj | -0.083 |
wra | -0.076 |
pic | -0.076 |
Token | hops |
Token ID | 29438 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
aroo | +0.215 |
ter | +0.193 |
crow | +0.176 |
apped | +0.173 |
itte | +0.172 |
Neg logit contributions | |
mess | -0.145 |
aj | -0.129 |
wra | -0.119 |
aman | -0.116 |
onna | -0.116 |
Token | towards |
Token ID | 3371 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
aroo | +0.020 |
ter | +0.018 |
itte | +0.015 |
crow | +0.015 |
apped | +0.015 |
Neg logit contributions | |
mess | -0.021 |
aj | -0.019 |
wra | -0.018 |
onna | -0.018 |
slippery | -0.018 |
Token | runs |
Token ID | 4539 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
aroo | +0.094 |
ter | +0.082 |
apped | +0.076 |
itte | +0.076 |
crow | +0.074 |
Neg logit contributions | |
mess | -0.066 |
aj | -0.059 |
onna | -0.056 |
liv | -0.055 |
fault | -0.054 |
Token | after |
Token ID | 706 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
mess | +0.187 |
aj | +0.172 |
onna | +0.157 |
wra | +0.157 |
fault | +0.156 |
Neg logit contributions | |
aroo | -0.184 |
ter | -0.162 |
crow | -0.147 |
apped | -0.139 |
member | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
aroo | +0.178 |
ter | +0.164 |
itte | +0.153 |
apped | +0.152 |
ovable | +0.151 |
Neg logit contributions | |
mess | -0.121 |
wra | -0.098 |
onna | -0.096 |
aj | -0.096 |
pic | -0.096 |
Token | k |
Token ID | 479 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
aroo | +0.146 |
ter | +0.135 |
apped | +0.132 |
ovable | +0.131 |
itte | +0.130 |
Neg logit contributions | |
mess | -0.136 |
slippery | -0.114 |
wra | -0.110 |
steep | -0.105 |
fuss | -0.104 |
Token | ang |
Token ID | 648 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ter | +0.142 |
aroo | +0.141 |
Queen | +0.138 |
itte | +0.136 |
ovable | +0.135 |
Neg logit contributions | |
mess | -0.231 |
aj | -0.225 |
liv | -0.220 |
wra | -0.219 |
slippery | -0.214 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
onel | +0.150 |
citizens | +0.149 |
ovable | +0.140 |
crew | +0.121 |
sailors | +0.118 |
Neg logit contributions | |
slippery | -0.798 |
mess | -0.789 |
liv | -0.784 |
snowball | -0.778 |
wob | -0.775 |
Token | , |
Token ID | 11 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
aroo | +1.425 |
ter | +1.294 |
crow | +1.175 |
itte | +1.175 |
apped | +1.173 |
Neg logit contributions | |
mess | -0.921 |
aj | -0.776 |
wra | -0.746 |
onna | -0.731 |
pic | -0.709 |
Token | but |
Token ID | 475 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
aroo | +0.068 |
ter | +0.062 |
crow | +0.054 |
apped | +0.052 |
member | +0.052 |
Neg logit contributions | |
mess | -0.046 |
aj | -0.043 |
icol | -0.038 |
wra | -0.037 |
onna | -0.037 |
Token | it |
Token ID | 340 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
mess | +0.283 |
aj | +0.247 |
wra | +0.236 |
slippery | +0.233 |
onna | +0.229 |
Neg logit contributions | |
aroo | -0.354 |
ter | -0.318 |
crow | -0.289 |
apped | -0.288 |
itte | -0.286 |
Token | is |
Token ID | 318 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
mess | +0.096 |
aj | +0.094 |
aman | +0.084 |
icol | +0.083 |
onna | +0.083 |
Neg logit contributions | |
aroo | -0.160 |
ter | -0.141 |
crow | -0.132 |
itte | -0.126 |
apped | -0.125 |
Token | too |
Token ID | 1165 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
icol | +0.269 |
aman | +0.258 |
aj | +0.256 |
mess | +0.252 |
array | +0.243 |
Neg logit contributions | |
aroo | -0.215 |
ter | -0.198 |
protector | -0.154 |
hero | -0.145 |
apped | -0.145 |
Token | boys |
Token ID | 6510 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
aroo | +0.209 |
ter | +0.178 |
itte | +0.176 |
apped | +0.175 |
ovable | +0.174 |
Neg logit contributions | |
mess | -0.235 |
wra | -0.201 |
aj | -0.200 |
slippery | -0.195 |
aman | -0.194 |
Token | ," |
Token ID | 553 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
aroo | +0.425 |
apped | +0.375 |
ter | +0.373 |
itte | +0.372 |
ovable | +0.354 |
Neg logit contributions | |
mess | -0.266 |
wra | -0.192 |
onna | -0.188 |
fuss | -0.182 |
aj | -0.182 |
Token | the |
Token ID | 262 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
aroo | +0.136 |
ter | +0.123 |
apped | +0.114 |
crow | +0.111 |
itte | +0.111 |
Neg logit contributions | |
mess | -0.101 |
aj | -0.084 |
wra | -0.083 |
onna | -0.083 |
pic | -0.082 |
Token | k |
Token ID | 479 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
aroo | +0.135 |
ter | +0.124 |
apped | +0.120 |
ovable | +0.117 |
ive | +0.117 |
Neg logit contributions | |
mess | -0.129 |
slippery | -0.109 |
aj | -0.105 |
wra | -0.104 |
aman | -0.102 |
Token | ang |
Token ID | 648 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ter | +0.157 |
citizens | +0.153 |
aroo | +0.149 |
itte | +0.146 |
crew | +0.145 |
Neg logit contributions | |
mess | -0.211 |
aj | -0.203 |
snowball | -0.203 |
liv | -0.200 |
slippery | -0.200 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
onel | +0.145 |
citizens | +0.138 |
ive | +0.124 |
alien | +0.117 |
ter | +0.113 |
Neg logit contributions | |
mess | -0.786 |
slippery | -0.771 |
snowball | -0.766 |
wob | -0.759 |
liv | -0.754 |
Token | says |
Token ID | 1139 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aroo | +1.403 |
ter | +1.262 |
crow | +1.194 |
apped | +1.131 |
itte | +1.128 |
Neg logit contributions | |
mess | -0.906 |
aj | -0.819 |
wra | -0.754 |
onna | -0.740 |
liv | -0.728 |
Token | . |
Token ID | 13 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
mess | +0.210 |
aj | +0.179 |
onna | +0.173 |
wra | +0.170 |
fault | +0.162 |
Neg logit contributions | |
aroo | -0.315 |
ter | -0.277 |
crow | -0.259 |
itte | -0.254 |
member | -0.245 |
Token | " |
Token ID | 366 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
aroo | +0.117 |
ter | +0.105 |
crow | +0.093 |
apped | +0.092 |
itte | +0.089 |
Neg logit contributions | |
mess | -0.115 |
aj | -0.102 |
wra | -0.097 |
onna | -0.095 |
pic | -0.093 |
Token | I |
Token ID | 40 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
aroo | +0.105 |
ter | +0.092 |
ovable | +0.092 |
itte | +0.089 |
apped | +0.088 |
Neg logit contributions | |
mess | -0.088 |
wra | -0.078 |
onna | -0.075 |
slippery | -0.072 |
aj | -0.070 |
Token | am |
Token ID | 716 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
aroo | +0.455 |
ter | +0.406 |
apped | +0.358 |
crow | +0.355 |
itte | +0.344 |
Neg logit contributions | |
mess | -0.441 |
aj | -0.382 |
onna | -0.371 |
wra | -0.362 |
fault | -0.356 |
Token | go |
Token ID | 467 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
mess | +0.052 |
pic | +0.044 |
slippery | +0.043 |
aj | +0.042 |
onna | +0.041 |
Neg logit contributions | |
aroo | -0.057 |
ter | -0.052 |
apped | -0.049 |
itte | -0.046 |
ovable | -0.046 |
Token | catch |
Token ID | 4929 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
aroo | +0.216 |
ter | +0.197 |
apped | +0.181 |
crow | +0.179 |
itte | +0.178 |
Neg logit contributions | |
mess | -0.170 |
aj | -0.147 |
onna | -0.139 |
slippery | -0.136 |
pic | -0.134 |
Token | the |
Token ID | 262 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
aroo | +0.198 |
ter | +0.177 |
apped | +0.164 |
itte | +0.164 |
ovable | +0.161 |
Neg logit contributions | |
mess | -0.163 |
aj | -0.135 |
wra | -0.133 |
pic | -0.129 |
slippery | -0.128 |
Token | k |
Token ID | 479 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
aroo | +0.152 |
apped | +0.138 |
itte | +0.137 |
ovable | +0.137 |
ive | +0.132 |
Neg logit contributions | |
mess | -0.128 |
slippery | -0.104 |
wra | -0.102 |
steep | -0.099 |
fun | -0.098 |
Token | ang |
Token ID | 648 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ovable | +0.146 |
citizens | +0.143 |
itte | +0.142 |
Queen | +0.140 |
crew | +0.139 |
Neg logit contributions | |
mess | -0.212 |
wra | -0.207 |
aj | -0.204 |
liv | -0.201 |
corn | -0.197 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
onel | +0.202 |
ovable | +0.195 |
citizens | +0.183 |
itte | +0.156 |
sailors | +0.151 |
Neg logit contributions | |
mess | -0.750 |
slippery | -0.742 |
snowball | -0.737 |
wra | -0.717 |
liv | -0.716 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
aroo | +1.567 |
ter | +1.414 |
itte | +1.364 |
apped | +1.348 |
crow | +1.344 |
Neg logit contributions | |
mess | -0.786 |
aj | -0.614 |
wra | -0.569 |
onna | -0.560 |
slippery | -0.547 |
Token | Ben |
Token ID | 3932 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
mess | +0.201 |
aj | +0.176 |
wra | +0.162 |
onna | +0.160 |
fault | +0.155 |
Neg logit contributions | |
aroo | -0.309 |
ter | -0.280 |
crow | -0.255 |
apped | -0.252 |
itte | -0.247 |
Token | says |
Token ID | 1139 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
mess | +0.109 |
aj | +0.099 |
icol | +0.095 |
onna | +0.092 |
aman | +0.092 |
Neg logit contributions | |
aroo | -0.139 |
ter | -0.122 |
crow | -0.118 |
member | -0.112 |
apped | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
mess | +0.230 |
aj | +0.201 |
onna | +0.195 |
wra | +0.189 |
fault | +0.183 |
Neg logit contributions | |
aroo | -0.296 |
ter | -0.268 |
crow | -0.242 |
itte | -0.234 |
pilot | -0.228 |
Token | He |
Token ID | 679 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
aroo | +0.132 |
ter | +0.124 |
ovable | +0.108 |
itte | +0.106 |
crow | +0.106 |
Neg logit contributions | |
mess | -0.097 |
onna | -0.086 |
aj | -0.086 |
wra | -0.082 |
pic | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
aroo | +0.036 |
ter | +0.032 |
crow | +0.029 |
apped | +0.028 |
itte | +0.028 |
Neg logit contributions | |
mess | -0.034 |
aj | -0.031 |
wra | -0.029 |
onna | -0.028 |
pic | -0.028 |
Token | The |
Token ID | 464 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
aroo | +0.035 |
ter | +0.032 |
crow | +0.027 |
apped | +0.027 |
itte | +0.027 |
Neg logit contributions | |
mess | -0.038 |
aj | -0.034 |
wra | -0.033 |
onna | -0.032 |
pic | -0.031 |
Token | baby |
Token ID | 5156 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
aroo | +0.199 |
apped | +0.189 |
ter | +0.184 |
ive | +0.181 |
onel | +0.180 |
Neg logit contributions | |
mess | -0.205 |
mistake | -0.168 |
slippery | -0.166 |
wra | -0.161 |
fun | -0.159 |
Token | k |
Token ID | 479 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
aroo | +0.348 |
ovable | +0.327 |
onel | +0.321 |
apped | +0.318 |
itte | +0.317 |
Neg logit contributions | |
mess | -0.426 |
wra | -0.390 |
scar | -0.378 |
aj | -0.370 |
wob | -0.362 |
Token | ang |
Token ID | 648 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
sailors | +0.160 |
citizens | +0.159 |
crew | +0.158 |
rest | +0.156 |
ter | +0.155 |
Neg logit contributions | |
aj | -0.203 |
liv | -0.194 |
wra | -0.189 |
mess | -0.188 |
snowball | -0.180 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
citizens | +0.125 |
onel | +0.122 |
sailors | +0.119 |
crew | +0.112 |
ovable | +0.099 |
Neg logit contributions | |
liv | -0.823 |
wob | -0.804 |
mess | -0.788 |
wra | -0.777 |
slippery | -0.775 |
Token | made |
Token ID | 925 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
aroo | +1.414 |
ter | +1.289 |
crow | +1.176 |
apped | +1.152 |
itte | +1.146 |
Neg logit contributions | |
mess | -0.931 |
aj | -0.797 |
wra | -0.764 |
onna | -0.731 |
pic | -0.715 |
Token | a |
Token ID | 257 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
mess | +0.082 |
aj | +0.074 |
wra | +0.069 |
onna | +0.069 |
pic | +0.067 |
Neg logit contributions | |
aroo | -0.088 |
ter | -0.079 |
crow | -0.071 |
apped | -0.070 |
itte | -0.068 |
Token | soft |
Token ID | 2705 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
aroo | +0.068 |
ter | +0.060 |
apped | +0.054 |
pilot | +0.054 |
hero | +0.054 |
Neg logit contributions | |
aj | -0.053 |
mess | -0.051 |
pic | -0.048 |
liv | -0.048 |
fault | -0.048 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
mess | +0.226 |
aj | +0.216 |
wra | +0.203 |
pic | +0.199 |
fault | +0.198 |
Neg logit contributions | |
aroo | -0.225 |
ter | -0.200 |
apped | -0.175 |
crow | -0.173 |
member | -0.162 |
Token | and |
Token ID | 290 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
mess | +0.216 |
wra | +0.168 |
onna | +0.167 |
aj | +0.166 |
slippery | +0.160 |
Neg logit contributions | |
aroo | -0.328 |
ter | -0.288 |
crow | -0.269 |
itte | -0.268 |
apped | -0.262 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
aroo | +0.033 |
ter | +0.029 |
crow | +0.027 |
ive | +0.026 |
ovable | +0.025 |
Neg logit contributions | |
mess | -0.026 |
wra | -0.022 |
aj | -0.021 |
slippery | -0.021 |
pic | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
aroo | +0.106 |
ter | +0.094 |
crow | +0.084 |
apped | +0.084 |
itte | +0.083 |
Neg logit contributions | |
mess | -0.086 |
aj | -0.073 |
wra | -0.072 |
pic | -0.069 |
slippery | -0.068 |
Token | big |
Token ID | 1263 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
aroo | +0.084 |
ter | +0.075 |
crow | +0.066 |
member | +0.065 |
pilot | +0.064 |
Neg logit contributions | |
mess | -0.066 |
aj | -0.063 |
fault | -0.058 |
onna | -0.058 |
wra | -0.056 |
Token | k |
Token ID | 479 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
mess | +0.124 |
aj | +0.117 |
onna | +0.108 |
fault | +0.107 |
wra | +0.106 |
Neg logit contributions | |
aroo | -0.135 |
ter | -0.121 |
crow | -0.107 |
apped | -0.103 |
member | -0.102 |
Token | ang |
Token ID | 648 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
aroo | +0.136 |
ter | +0.125 |
ovable | +0.117 |
itte | +0.113 |
citizens | +0.111 |
Neg logit contributions | |
mess | -0.273 |
aj | -0.254 |
wra | -0.252 |
liv | -0.242 |
slippery | -0.239 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
onel | +0.130 |
citizens | +0.125 |
ovable | +0.115 |
crew | +0.091 |
sailors | +0.085 |
Neg logit contributions | |
mess | -0.858 |
liv | -0.828 |
slippery | -0.821 |
snowball | -0.815 |
wra | -0.803 |
Token | hopping |
Token ID | 47153 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
aroo | +1.233 |
ter | +1.103 |
ovable | +1.049 |
itte | +1.048 |
crow | +1.040 |
Neg logit contributions | |
mess | -1.075 |
wra | -0.870 |
aj | -0.867 |
slippery | -0.835 |
onna | -0.827 |
Token | near |
Token ID | 1474 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
aroo | +0.136 |
ter | +0.120 |
ovable | +0.112 |
pilot | +0.110 |
itte | +0.109 |
Neg logit contributions | |
mess | -0.169 |
slippery | -0.151 |
steep | -0.148 |
wra | -0.147 |
aj | -0.140 |
Token | the |
Token ID | 262 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
aroo | +0.429 |
ter | +0.383 |
crow | +0.337 |
apped | +0.323 |
member | +0.315 |
Neg logit contributions | |
mess | -0.488 |
aj | -0.461 |
onna | -0.427 |
wra | -0.421 |
liv | -0.412 |
Token | trees |
Token ID | 7150 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
aroo | +0.175 |
apped | +0.151 |
ter | +0.148 |
ovable | +0.147 |
itte | +0.145 |
Neg logit contributions | |
mess | -0.139 |
slippery | -0.111 |
wra | -0.111 |
steep | -0.106 |
aj | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
aroo | +0.109 |
ter | +0.097 |
crow | +0.088 |
apped | +0.086 |
itte | +0.086 |
Neg logit contributions | |
mess | -0.097 |
aj | -0.084 |
wra | -0.081 |
onna | -0.080 |
pic | -0.077 |
Token | play |
Token ID | 711 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
mess | +0.005 |
onna | +0.004 |
pic | +0.004 |
aj | +0.004 |
wra | +0.004 |
Neg logit contributions | |
aroo | -0.005 |
ter | -0.005 |
apped | -0.004 |
crow | -0.004 |
itte | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
aroo | +0.300 |
ter | +0.260 |
itte | +0.250 |
crow | +0.246 |
ovable | +0.239 |
Neg logit contributions | |
mess | -0.259 |
pic | -0.216 |
flips | -0.211 |
fun | -0.210 |
wra | -0.206 |
Token | the |
Token ID | 262 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
aroo | +0.276 |
ter | +0.248 |
itte | +0.226 |
apped | +0.225 |
crow | +0.221 |
Neg logit contributions | |
mess | -0.224 |
wra | -0.189 |
aj | -0.188 |
pic | -0.183 |
slippery | -0.179 |
Token | k |
Token ID | 479 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
aroo | +0.132 |
ter | +0.115 |
apped | +0.114 |
itte | +0.112 |
ovable | +0.111 |
Neg logit contributions | |
mess | -0.131 |
slippery | -0.106 |
wra | -0.105 |
fault | -0.103 |
steep | -0.101 |
Token | ang |
Token ID | 648 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
aroo | +0.140 |
ter | +0.134 |
itte | +0.132 |
Queen | +0.130 |
citizens | +0.127 |
Neg logit contributions | |
mess | -0.234 |
aj | -0.226 |
wra | -0.219 |
slippery | -0.215 |
liv | -0.215 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
onel | +0.154 |
citizens | +0.147 |
ovable | +0.130 |
ive | +0.123 |
itte | +0.117 |
Neg logit contributions | |
snowball | -0.776 |
slippery | -0.776 |
mess | -0.769 |
liv | -0.768 |
onna | -0.741 |
Token | until |
Token ID | 1566 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
aroo | +1.449 |
ter | +1.275 |
itte | +1.257 |
crow | +1.221 |
apped | +1.173 |
Neg logit contributions | |
mess | -0.920 |
aj | -0.703 |
wra | -0.695 |
pic | -0.695 |
fault | -0.692 |
Token | it |
Token ID | 340 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
mess | +0.127 |
wra | +0.097 |
pic | +0.092 |
slippery | +0.092 |
onna | +0.089 |
Neg logit contributions | |
aroo | -0.236 |
ter | -0.212 |
itte | -0.204 |
ovable | -0.203 |
crow | -0.198 |
Token | is |
Token ID | 318 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
mess | +0.108 |
aj | +0.101 |
wra | +0.093 |
aman | +0.092 |
liv | +0.091 |
Neg logit contributions | |
aroo | -0.158 |
ter | -0.143 |
crow | -0.135 |
apped | -0.133 |
ive | -0.126 |
Token | time |
Token ID | 640 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
mess | +0.200 |
wra | +0.192 |
liv | +0.187 |
aj | +0.186 |
icol | +0.184 |
Neg logit contributions | |
ter | -0.279 |
aroo | -0.279 |
apped | -0.239 |
sailors | -0.233 |
pilot | -0.226 |
Token | to |
Token ID | 284 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
mess | +0.455 |
aj | +0.406 |
wra | +0.400 |
liv | +0.395 |
aman | +0.390 |
Neg logit contributions | |
aroo | -0.445 |
ter | -0.398 |
apped | -0.368 |
member | -0.347 |
crow | -0.346 |
Token | them |
Token ID | 606 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
aroo | +0.436 |
ter | +0.394 |
crow | +0.353 |
apped | +0.346 |
itte | +0.339 |
Neg logit contributions | |
mess | -0.362 |
aj | -0.322 |
wra | -0.300 |
onna | -0.298 |
fault | -0.288 |
Token | to |
Token ID | 284 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
mess | +0.076 |
wra | +0.065 |
aj | +0.063 |
slippery | +0.063 |
pic | +0.061 |
Neg logit contributions | |
aroo | -0.103 |
ter | -0.090 |
apped | -0.084 |
pilot | -0.082 |
itte | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
mess | +0.103 |
aj | +0.087 |
wra | +0.085 |
onna | +0.083 |
pic | +0.083 |
Neg logit contributions | |
aroo | -0.120 |
ter | -0.105 |
apped | -0.098 |
itte | -0.096 |
crow | -0.096 |
Token | k |
Token ID | 479 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
aroo | +0.157 |
apped | +0.137 |
itte | +0.131 |
ovable | +0.130 |
ter | +0.129 |
Neg logit contributions | |
mess | -0.162 |
slippery | -0.132 |
wra | -0.130 |
aman | -0.127 |
fun | -0.124 |
Token | ang |
Token ID | 648 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
aroo | +0.141 |
ter | +0.134 |
itte | +0.122 |
citizens | +0.121 |
ovable | +0.118 |
Neg logit contributions | |
aj | -0.256 |
mess | -0.256 |
liv | -0.242 |
wra | -0.236 |
aman | -0.234 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
citizens | +0.145 |
onel | +0.141 |
sailors | +0.138 |
ovable | +0.112 |
astronaut | +0.099 |
Neg logit contributions | |
liv | -0.816 |
slippery | -0.791 |
mess | -0.785 |
aman | -0.778 |
snowball | -0.769 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
aroo | +1.475 |
ter | +1.327 |
apped | +1.251 |
itte | +1.243 |
crow | +1.219 |
Neg logit contributions | |
mess | -0.867 |
aj | -0.716 |
onna | -0.682 |
wra | -0.652 |
slippery | -0.640 |
Token | he |
Token ID | 339 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
aroo | +0.074 |
ter | +0.067 |
apped | +0.065 |
ive | +0.063 |
crow | +0.063 |
Neg logit contributions | |
mess | -0.048 |
wra | -0.042 |
slippery | -0.038 |
pic | -0.036 |
aj | -0.036 |
Token | struggled |
Token ID | 11615 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aroo | +0.090 |
ter | +0.081 |
crow | +0.074 |
apped | +0.072 |
itte | +0.071 |
Neg logit contributions | |
mess | -0.066 |
aj | -0.057 |
wra | -0.054 |
onna | -0.052 |
pic | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
mess | +0.217 |
aj | +0.205 |
pic | +0.195 |
icol | +0.193 |
aman | +0.191 |
Neg logit contributions | |
aroo | -0.197 |
ter | -0.183 |
apped | -0.157 |
member | -0.154 |
crow | -0.150 |
Token | eat |
Token ID | 4483 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
mess | +0.109 |
aj | +0.098 |
wra | +0.093 |
onna | +0.092 |
pic | +0.089 |
Neg logit contributions | |
aroo | -0.104 |
ter | -0.093 |
crow | -0.082 |
apped | -0.080 |
itte | -0.079 |
Token | play |
Token ID | 711 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
mess | +0.123 |
onna | +0.102 |
wra | +0.100 |
slippery | +0.099 |
aj | +0.098 |
Neg logit contributions | |
aroo | -0.159 |
ter | -0.146 |
crow | -0.131 |
itte | -0.131 |
apped | -0.129 |
Token | with |
Token ID | 351 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
aroo | +0.314 |
itte | +0.267 |
ter | +0.265 |
ovable | +0.259 |
pilot | +0.253 |
Neg logit contributions | |
mess | -0.271 |
pic | -0.219 |
fun | -0.218 |
wra | -0.211 |
flips | -0.208 |
Token | the |
Token ID | 262 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
aroo | +0.314 |
ter | +0.287 |
onel | +0.271 |
itte | +0.270 |
apped | +0.266 |
Neg logit contributions | |
mess | -0.184 |
slippery | -0.153 |
pic | -0.146 |
fun | -0.142 |
wra | -0.141 |
Token | k |
Token ID | 479 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
aroo | +0.136 |
ter | +0.119 |
apped | +0.114 |
itte | +0.112 |
ovable | +0.111 |
Neg logit contributions | |
mess | -0.145 |
slippery | -0.119 |
wra | -0.118 |
aj | -0.117 |
fault | -0.113 |
Token | ang |
Token ID | 648 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
Queen | +0.149 |
itte | +0.148 |
aroo | +0.147 |
ovable | +0.144 |
citizens | +0.143 |
Neg logit contributions | |
mess | -0.223 |
aj | -0.219 |
liv | -0.214 |
slippery | -0.214 |
wra | -0.213 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
onel | +0.179 |
citizens | +0.166 |
ovable | +0.164 |
ive | +0.155 |
alien | +0.147 |
Neg logit contributions | |
slippery | -0.753 |
snowball | -0.742 |
liv | -0.740 |
mess | -0.740 |
onna | -0.727 |
Token | . |
Token ID | 13 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
aroo | +1.478 |
itte | +1.306 |
ter | +1.300 |
crow | +1.261 |
ovable | +1.201 |
Neg logit contributions | |
mess | -0.892 |
wra | -0.679 |
slippery | -0.665 |
fault | -0.662 |
pic | -0.648 |
Token | They |
Token ID | 1119 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
aroo | +0.100 |
ter | +0.089 |
crow | +0.079 |
apped | +0.078 |
itte | +0.077 |
Neg logit contributions | |
mess | -0.093 |
aj | -0.083 |
wra | -0.078 |
onna | -0.078 |
pic | -0.076 |
Token | have |
Token ID | 423 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
aroo | +0.002 |
ter | +0.002 |
apped | +0.002 |
crow | +0.002 |
itte | +0.002 |
Neg logit contributions | |
mess | -0.002 |
onna | -0.002 |
wra | -0.002 |
slippery | -0.002 |
aj | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
aroo | +0.272 |
ter | +0.263 |
sailors | +0.243 |
apped | +0.229 |
citizens | +0.229 |
Neg logit contributions | |
mess | -0.237 |
aj | -0.233 |
aman | -0.225 |
icol | -0.214 |
liv | -0.208 |
Token | lot |
Token ID | 1256 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
aroo | +0.064 |
ter | +0.055 |
hero | +0.053 |
pilot | +0.053 |
member | +0.053 |
Neg logit contributions | |
aj | -0.052 |
mess | -0.051 |
liv | -0.048 |
array | -0.048 |
onna | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
mess | +0.245 |
aj | +0.216 |
wra | +0.209 |
onna | +0.204 |
fault | +0.198 |
Neg logit contributions | |
aroo | -0.304 |
ter | -0.268 |
crow | -0.247 |
itte | -0.244 |
ovable | -0.234 |
Token | " |
Token ID | 366 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
aroo | +0.098 |
ter | +0.089 |
itte | +0.080 |
crow | +0.080 |
member | +0.080 |
Neg logit contributions | |
mess | -0.068 |
onna | -0.058 |
aj | -0.058 |
wra | -0.057 |
fault | -0.053 |
Token | The |
Token ID | 464 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
aroo | +0.085 |
ter | +0.073 |
apped | +0.072 |
ovable | +0.071 |
itte | +0.070 |
Neg logit contributions | |
mess | -0.085 |
wra | -0.075 |
slippery | -0.072 |
onna | -0.067 |
aj | -0.067 |
Token | k |
Token ID | 479 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
aroo | +0.200 |
apped | +0.176 |
itte | +0.175 |
ovable | +0.174 |
ter | +0.172 |
Neg logit contributions | |
mess | -0.210 |
slippery | -0.166 |
wra | -0.165 |
steep | -0.163 |
mistake | -0.163 |
Token | ang |
Token ID | 648 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
aroo | +0.147 |
itte | +0.146 |
ovable | +0.143 |
citizens | +0.143 |
Queen | +0.142 |
Neg logit contributions | |
mess | -0.217 |
aj | -0.208 |
wra | -0.205 |
slippery | -0.200 |
liv | -0.199 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
onel | +0.148 |
ovable | +0.137 |
apped | +0.133 |
citizens | +0.129 |
ive | +0.117 |
Neg logit contributions | |
mess | -0.804 |
slippery | -0.782 |
snowball | -0.756 |
steep | -0.753 |
liv | -0.750 |
Token | is |
Token ID | 318 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aroo | +1.598 |
ter | +1.477 |
apped | +1.363 |
itte | +1.350 |
crow | +1.346 |
Neg logit contributions | |
mess | -0.772 |
aj | -0.597 |
wra | -0.558 |
onna | -0.543 |
slippery | -0.528 |
Token | not |
Token ID | 407 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
mess | +0.217 |
aj | +0.195 |
wra | +0.181 |
onna | +0.177 |
aman | +0.173 |
Neg logit contributions | |
aroo | -0.302 |
ter | -0.275 |
crow | -0.246 |
apped | -0.241 |
itte | -0.238 |
Token | from |
Token ID | 422 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
mess | +0.430 |
aj | +0.360 |
wra | +0.341 |
onna | +0.338 |
fault | +0.330 |
Neg logit contributions | |
aroo | -0.578 |
ter | -0.516 |
apped | -0.478 |
crow | -0.474 |
itte | -0.468 |
Token | the |
Token ID | 262 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
aroo | +0.398 |
ter | +0.351 |
apped | +0.341 |
itte | +0.338 |
crow | +0.330 |
Neg logit contributions | |
mess | -0.317 |
aj | -0.255 |
pic | -0.250 |
slippery | -0.248 |
wra | -0.246 |
Token | park |
Token ID | 3952 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
aroo | +0.137 |
apped | +0.119 |
ter | +0.117 |
itte | +0.117 |
ovable | +0.113 |
Neg logit contributions | |
mess | -0.137 |
steep | -0.110 |
slippery | -0.110 |
wra | -0.110 |
fault | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
aroo | +0.113 |
ter | +0.102 |
crow | +0.090 |
apped | +0.088 |
itte | +0.087 |
Neg logit contributions | |
mess | -0.107 |
aj | -0.097 |
onna | -0.091 |
wra | -0.091 |
pic | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
aroo | +0.051 |
ter | +0.042 |
crow | +0.039 |
apped | +0.038 |
itte | +0.037 |
Neg logit contributions | |
mess | -0.066 |
aj | -0.059 |
wra | -0.058 |
fault | -0.057 |
icol | -0.054 |
Token | The |
Token ID | 464 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
aroo | +0.062 |
ter | +0.058 |
apped | +0.053 |
ovable | +0.050 |
crow | +0.049 |
Neg logit contributions | |
mess | -0.054 |
aj | -0.047 |
wra | -0.045 |
onna | -0.044 |
slippery | -0.044 |
Token | k |
Token ID | 479 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
aroo | +0.229 |
ovable | +0.213 |
apped | +0.211 |
ter | +0.207 |
onel | +0.207 |
Neg logit contributions | |
mess | -0.213 |
slippery | -0.175 |
mistake | -0.158 |
steep | -0.157 |
wra | -0.157 |
Token | ang |
Token ID | 648 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
aroo | +0.150 |
ter | +0.146 |
ovable | +0.146 |
Queen | +0.144 |
citizens | +0.144 |
Neg logit contributions | |
mess | -0.229 |
aj | -0.217 |
wra | -0.211 |
liv | -0.209 |
slippery | -0.209 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ovable | +0.123 |
onel | +0.120 |
citizens | +0.116 |
sailors | +0.106 |
married | +0.095 |
Neg logit contributions | |
mess | -0.822 |
slippery | -0.817 |
wob | -0.808 |
liv | -0.799 |
snowball | -0.792 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
aroo | +1.355 |
ter | +1.226 |
crow | +1.109 |
apped | +1.097 |
ovable | +1.081 |
Neg logit contributions | |
mess | -0.992 |
aj | -0.850 |
wra | -0.800 |
onna | -0.780 |
pic | -0.760 |
Token | embarrassed |
Token ID | 21100 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
aroo | +0.052 |
ter | +0.046 |
apped | +0.042 |
member | +0.041 |
ive | +0.041 |
Neg logit contributions | |
mess | -0.037 |
slippery | -0.030 |
fun | -0.029 |
wra | -0.028 |
onna | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
aroo | +0.147 |
ter | +0.134 |
crow | +0.118 |
apped | +0.117 |
itte | +0.113 |
Neg logit contributions | |
mess | -0.140 |
aj | -0.128 |
wra | -0.119 |
onna | -0.118 |
pic | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
aroo | +0.071 |
ter | +0.067 |
crow | +0.059 |
apped | +0.055 |
pilot | +0.055 |
Neg logit contributions | |
aj | -0.055 |
mess | -0.053 |
onna | -0.048 |
liv | -0.047 |
fault | -0.047 |
Token | quickly |
Token ID | 2952 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
mess | +0.093 |
slippery | +0.074 |
wra | +0.074 |
aj | +0.072 |
fuss | +0.069 |
Neg logit contributions | |
aroo | -0.127 |
ter | -0.112 |
apped | -0.105 |
itte | -0.104 |
crow | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
aroo | +0.131 |
ter | +0.119 |
crow | +0.105 |
apped | +0.104 |
itte | +0.103 |
Neg logit contributions | |
mess | -0.097 |
aj | -0.087 |
onna | -0.081 |
wra | -0.080 |
pic | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
aroo | +0.051 |
ter | +0.041 |
crow | +0.038 |
apped | +0.037 |
member | +0.037 |
Neg logit contributions | |
mess | -0.066 |
aj | -0.060 |
wra | -0.059 |
fault | -0.056 |
icol | -0.056 |
Token | The |
Token ID | 464 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
aroo | +0.074 |
ter | +0.068 |
crow | +0.062 |
apped | +0.061 |
itte | +0.060 |
Neg logit contributions | |
mess | -0.044 |
aj | -0.038 |
wra | -0.035 |
onna | -0.034 |
pic | -0.033 |
Token | k |
Token ID | 479 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
aroo | +0.255 |
ovable | +0.246 |
apped | +0.245 |
onel | +0.238 |
itte | +0.233 |
Neg logit contributions | |
mess | -0.189 |
slippery | -0.153 |
fun | -0.145 |
scar | -0.140 |
wra | -0.139 |
Token | ang |
Token ID | 648 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
aroo | +0.155 |
ovable | +0.154 |
ter | +0.151 |
messenger | +0.150 |
Queen | +0.149 |
Neg logit contributions | |
mess | -0.218 |
wra | -0.203 |
aj | -0.202 |
slippery | -0.200 |
liv | -0.200 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
ovable | +0.182 |
onel | +0.171 |
alien | +0.150 |
sailors | +0.147 |
ative | +0.146 |
Neg logit contributions | |
slippery | -0.755 |
mess | -0.749 |
wob | -0.735 |
liv | -0.731 |
snowball | -0.719 |
Token | was |
Token ID | 373 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
aroo | +1.395 |
ter | +1.250 |
crow | +1.142 |
ovable | +1.106 |
apped | +1.095 |
Neg logit contributions | |
mess | -0.992 |
aj | -0.823 |
wra | -0.765 |
onna | -0.755 |
slippery | -0.751 |
Token | so |
Token ID | 523 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
mess | +0.017 |
aj | +0.015 |
wra | +0.014 |
onna | +0.014 |
slippery | +0.013 |
Neg logit contributions | |
aroo | -0.022 |
ter | -0.019 |
crow | -0.018 |
apped | -0.017 |
itte | -0.017 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
mess | +0.111 |
aj | +0.096 |
onna | +0.093 |
slippery | +0.091 |
wra | +0.090 |
Neg logit contributions | |
aroo | -0.122 |
ter | -0.110 |
crow | -0.105 |
ive | -0.099 |
member | -0.093 |
Token | with |
Token ID | 351 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
aroo | +0.215 |
ter | +0.195 |
apped | +0.169 |
crow | +0.168 |
member | +0.164 |
Neg logit contributions | |
mess | -0.199 |
aj | -0.182 |
wra | -0.170 |
onna | -0.167 |
liv | -0.163 |
Token | the |
Token ID | 262 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
aroo | +0.282 |
ter | +0.255 |
crow | +0.229 |
apped | +0.226 |
itte | +0.222 |
Neg logit contributions | |
mess | -0.223 |
aj | -0.197 |
wra | -0.184 |
onna | -0.182 |
pic | -0.177 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
citizens | +0.109 |
pilot | +0.108 |
itte | +0.107 |
crew | +0.106 |
sailors | +0.104 |
Neg logit contributions | |
mess | -0.815 |
gh | -0.800 |
slippery | -0.795 |
liv | -0.793 |
wra | -0.776 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
aroo | +1.581 |
ter | +1.441 |
apped | +1.372 |
itte | +1.369 |
crow | +1.359 |
Neg logit contributions | |
mess | -0.747 |
aj | -0.602 |
wra | -0.542 |
onna | -0.535 |
pic | -0.524 |
Token | The |
Token ID | 383 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
mess | +0.178 |
aj | +0.166 |
icol | +0.149 |
aman | +0.148 |
pic | +0.147 |
Neg logit contributions | |
aroo | -0.274 |
ter | -0.244 |
crow | -0.225 |
itte | -0.223 |
ovable | -0.221 |
Token | k |
Token ID | 479 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
aroo | +0.474 |
ter | +0.431 |
ovable | +0.430 |
apped | +0.430 |
ive | +0.428 |
Neg logit contributions | |
mess | -0.382 |
slippery | -0.318 |
fun | -0.294 |
wra | -0.290 |
steep | -0.284 |
Token | ang |
Token ID | 648 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
citizens | +0.157 |
crew | +0.156 |
sailors | +0.152 |
ter | +0.149 |
messenger | +0.149 |
Neg logit contributions | |
mess | -0.215 |
liv | -0.209 |
wra | -0.206 |
slippery | -0.205 |
aj | -0.205 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
sailors | +0.171 |
crew | +0.168 |
citizens | +0.166 |
onel | +0.153 |
ovable | +0.140 |
Neg logit contributions | |
liv | -0.780 |
slippery | -0.767 |
wob | -0.751 |
mess | -0.750 |
snowball | -0.742 |
Token | sque |
Token ID | 35776 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
aroo | +1.357 |
ter | +1.237 |
crow | +1.121 |
apped | +1.095 |
itte | +1.083 |
Neg logit contributions | |
mess | -0.975 |
aj | -0.855 |
wra | -0.793 |
onna | -0.788 |
pic | -0.763 |
Token | aked |
Token ID | 4335 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
mess | +0.064 |
aj | +0.059 |
wra | +0.055 |
onna | +0.054 |
liv | +0.053 |
Neg logit contributions | |
aroo | -0.055 |
ter | -0.048 |
pilot | -0.041 |
crow | -0.040 |
member | -0.039 |
Token | in |
Token ID | 287 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
aroo | +0.298 |
ter | +0.267 |
crow | +0.239 |
apped | +0.235 |
itte | +0.232 |
Neg logit contributions | |
mess | -0.256 |
aj | -0.226 |
wra | -0.214 |
onna | -0.210 |
pic | -0.205 |
Token | response |
Token ID | 2882 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
aroo | +0.531 |
ter | +0.470 |
crow | +0.410 |
apped | +0.404 |
member | +0.392 |
Neg logit contributions | |
mess | -0.616 |
aj | -0.566 |
wra | -0.532 |
onna | -0.528 |
fault | -0.516 |
Token | , |
Token ID | 11 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
aroo | +0.209 |
ter | +0.186 |
crow | +0.172 |
itte | +0.171 |
apped | +0.167 |
Neg logit contributions | |
mess | -0.138 |
aj | -0.118 |
wra | -0.112 |
onna | -0.112 |
pic | -0.106 |
Token | there |
Token ID | 612 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
aroo | +0.055 |
ter | +0.049 |
crow | +0.046 |
member | +0.044 |
citizens | +0.044 |
Neg logit contributions | |
mess | -0.050 |
aj | -0.043 |
slippery | -0.041 |
wra | -0.041 |
onna | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
aroo | +0.235 |
ter | +0.210 |
crow | +0.188 |
apped | +0.187 |
itte | +0.180 |
Neg logit contributions | |
mess | -0.214 |
aj | -0.198 |
wra | -0.181 |
onna | -0.179 |
fault | -0.175 |
Token | a |
Token ID | 257 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
mess | +0.029 |
aj | +0.026 |
onna | +0.025 |
wra | +0.024 |
fuss | +0.024 |
Neg logit contributions | |
aroo | -0.024 |
ter | -0.022 |
apped | -0.019 |
crow | -0.018 |
itte | -0.018 |
Token | k |
Token ID | 479 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
aroo | +0.075 |
ter | +0.067 |
crow | +0.064 |
apped | +0.063 |
ovable | +0.061 |
Neg logit contributions | |
mess | -0.072 |
aj | -0.058 |
wra | -0.056 |
slippery | -0.056 |
pic | -0.055 |
Token | ang |
Token ID | 648 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
citizens | +0.153 |
sailors | +0.151 |
rest | +0.150 |
onel | +0.150 |
ter | +0.149 |
Neg logit contributions | |
mess | -0.213 |
wra | -0.194 |
slippery | -0.191 |
snowball | -0.190 |
steep | -0.188 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
citizens | +0.184 |
sailors | +0.182 |
onel | +0.170 |
apped | +0.160 |
married | +0.146 |
Neg logit contributions | |
slippery | -0.747 |
snowball | -0.729 |
liv | -0.725 |
gh | -0.717 |
mess | -0.714 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
aroo | +0.926 |
onel | +0.898 |
folk | +0.895 |
ter | +0.879 |
itte | +0.859 |
Neg logit contributions | |
mess | -1.136 |
onna | -0.980 |
ine | -0.978 |
slippery | -0.971 |
snowball | -0.965 |
Token | He |
Token ID | 679 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
aroo | +0.112 |
ter | +0.104 |
onel | +0.093 |
member | +0.093 |
itte | +0.092 |
Neg logit contributions | |
mess | -0.097 |
onna | -0.091 |
aj | -0.088 |
steep | -0.087 |
pic | -0.087 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
aroo | +0.077 |
ter | +0.071 |
crow | +0.063 |
apped | +0.062 |
member | +0.061 |
Neg logit contributions | |
mess | -0.082 |
aj | -0.072 |
wra | -0.072 |
pic | -0.070 |
slippery | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
aroo | +0.384 |
ter | +0.346 |
crow | +0.309 |
apped | +0.302 |
member | +0.296 |
Neg logit contributions | |
mess | -0.300 |
aj | -0.272 |
wra | -0.248 |
onna | -0.244 |
liv | -0.243 |
Token | paint |
Token ID | 7521 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
mess | +0.095 |
pic | +0.082 |
onna | +0.082 |
slippery | +0.079 |
aj | +0.077 |
Neg logit contributions | |
aroo | -0.109 |
ter | -0.102 |
apped | -0.096 |
itte | -0.093 |
ovable | -0.090 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
citizens | +0.168 |
onel | +0.133 |
ovable | +0.123 |
crew | +0.119 |
sailors | +0.116 |
Neg logit contributions | |
mess | -0.814 |
snowball | -0.783 |
slippery | -0.776 |
liv | -0.774 |
onna | -0.774 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
aroo | +1.285 |
ter | +1.144 |
itte | +1.112 |
ovable | +1.104 |
citizens | +1.085 |
Neg logit contributions | |
mess | -1.000 |
wra | -0.785 |
slippery | -0.756 |
aj | -0.754 |
onna | -0.733 |
Token | The |
Token ID | 383 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
aroo | +0.106 |
ter | +0.096 |
ovable | +0.082 |
itte | +0.081 |
onel | +0.080 |
Neg logit contributions | |
mess | -0.108 |
aj | -0.099 |
onna | -0.097 |
pic | -0.094 |
wra | -0.094 |
Token | k |
Token ID | 479 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
aroo | +0.438 |
onel | +0.423 |
ovable | +0.422 |
itte | +0.410 |
ter | +0.410 |
Neg logit contributions | |
mess | -0.374 |
slippery | -0.318 |
steep | -0.293 |
fun | -0.293 |
wra | -0.292 |
Token | ang |
Token ID | 648 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
aroo | +0.130 |
ter | +0.123 |
citizens | +0.115 |
ovable | +0.115 |
itte | +0.114 |
Neg logit contributions | |
mess | -0.251 |
wra | -0.231 |
aj | -0.230 |
liv | -0.227 |
slippery | -0.227 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
onel | +0.110 |
citizens | +0.098 |
ter | +0.092 |
crew | +0.088 |
ovable | +0.086 |
Neg logit contributions | |
mess | -0.877 |
liv | -0.848 |
slippery | -0.843 |
snowball | -0.829 |
wob | -0.821 |
Token | is |
Token ID | 318 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
aroo | +1.418 |
ter | +1.269 |
crow | +1.180 |
apped | +1.153 |
itte | +1.139 |
Neg logit contributions | |
mess | -0.884 |
aj | -0.800 |
wra | -0.729 |
onna | -0.718 |
fault | -0.710 |
Token | hopping |
Token ID | 47153 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
mess | +0.229 |
aj | +0.205 |
wra | +0.192 |
onna | +0.188 |
pic | +0.184 |
Neg logit contributions | |
aroo | -0.281 |
ter | -0.254 |
crow | -0.225 |
apped | -0.224 |
itte | -0.218 |
Token | and |
Token ID | 290 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
aroo | +0.128 |
ter | +0.110 |
itte | +0.093 |
apped | +0.093 |
crow | +0.092 |
Neg logit contributions | |
mess | -0.181 |
aj | -0.159 |
wra | -0.158 |
slippery | -0.156 |
steep | -0.153 |
Token | eating |
Token ID | 6600 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
mess | +0.101 |
aj | +0.090 |
wra | +0.083 |
onna | +0.082 |
fault | +0.080 |
Neg logit contributions | |
aroo | -0.138 |
ter | -0.125 |
crow | -0.112 |
apped | -0.111 |
itte | -0.108 |
Token | grass |
Token ID | 8701 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
mess | +0.162 |
aj | +0.152 |
onna | +0.138 |
liv | +0.136 |
fault | +0.135 |
Neg logit contributions | |
aroo | -0.163 |
ter | -0.147 |
crow | -0.128 |
apped | -0.125 |
member | -0.120 |
Token | careful |
Token ID | 8161 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
aroo | +0.003 |
ter | +0.003 |
crow | +0.002 |
apped | +0.002 |
itte | +0.002 |
Neg logit contributions | |
mess | -0.002 |
aj | -0.002 |
slippery | -0.002 |
wra | -0.002 |
fault | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
aroo | +0.054 |
ter | +0.048 |
crow | +0.043 |
apped | +0.042 |
itte | +0.041 |
Neg logit contributions | |
mess | -0.055 |
aj | -0.049 |
wra | -0.047 |
onna | -0.046 |
pic | -0.045 |
Token | The |
Token ID | 383 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
aroo | +0.077 |
ter | +0.067 |
member | +0.062 |
apped | +0.058 |
itte | +0.057 |
Neg logit contributions | |
mess | -0.072 |
aj | -0.071 |
onna | -0.065 |
fault | -0.064 |
pic | -0.063 |
Token | k |
Token ID | 479 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
aroo | +0.420 |
ter | +0.377 |
apped | +0.369 |
ovable | +0.358 |
itte | +0.355 |
Neg logit contributions | |
mess | -0.420 |
slippery | -0.338 |
fault | -0.326 |
steep | -0.325 |
mistake | -0.325 |
Token | ang |
Token ID | 648 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
aroo | +0.143 |
ter | +0.141 |
Queen | +0.137 |
itte | +0.134 |
ovable | +0.134 |
Neg logit contributions | |
mess | -0.223 |
aj | -0.207 |
slippery | -0.197 |
liv | -0.196 |
wra | -0.195 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
onel | +0.125 |
ovable | +0.114 |
citizens | +0.110 |
crew | +0.101 |
sailors | +0.100 |
Neg logit contributions | |
mess | -0.845 |
slippery | -0.800 |
liv | -0.781 |
mistake | -0.767 |
wob | -0.761 |
Token | is |
Token ID | 318 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
aroo | +1.618 |
ter | +1.502 |
apped | +1.380 |
itte | +1.360 |
crow | +1.347 |
Neg logit contributions | |
mess | -0.755 |
aj | -0.586 |
wra | -0.541 |
onna | -0.515 |
pays | -0.515 |
Token | not |
Token ID | 407 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
mess | +0.194 |
aj | +0.166 |
wra | +0.153 |
onna | +0.150 |
pic | +0.144 |
Neg logit contributions | |
aroo | -0.349 |
ter | -0.319 |
crow | -0.291 |
apped | -0.288 |
itte | -0.284 |
Token | a |
Token ID | 257 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
mess | +0.455 |
aj | +0.368 |
slippery | +0.358 |
onna | +0.356 |
fault | +0.355 |
Neg logit contributions | |
aroo | -0.577 |
ter | -0.507 |
apped | -0.482 |
itte | -0.474 |
crow | -0.474 |
Token | toy |
Token ID | 13373 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
aroo | +0.047 |
ter | +0.042 |
apped | +0.040 |
itte | +0.038 |
crow | +0.037 |
Neg logit contributions | |
mess | -0.047 |
fault | -0.038 |
onna | -0.037 |
wra | -0.037 |
aj | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
aroo | +0.086 |
itte | +0.083 |
apped | +0.081 |
year | +0.078 |
appers | +0.075 |
Neg logit contributions | |
mess | -0.046 |
wra | -0.037 |
fault | -0.035 |
mistake | -0.031 |
onna | -0.030 |
Token | " |
Token ID | 1 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
aroo | +0.043 |
ter | +0.039 |
apped | +0.034 |
crow | +0.033 |
ovable | +0.033 |
Neg logit contributions | |
mess | -0.044 |
aj | -0.040 |
wra | -0.038 |
onna | -0.037 |
pic | -0.036 |
Token | Hello |
Token ID | 15496 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
aroo | +0.180 |
ter | +0.161 |
apped | +0.148 |
ovable | +0.145 |
itte | +0.144 |
Neg logit contributions | |
mess | -0.180 |
wra | -0.157 |
aj | -0.152 |
slippery | -0.150 |
onna | -0.149 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
aroo | +0.495 |
ter | +0.442 |
apped | +0.412 |
crow | +0.411 |
itte | +0.409 |
Neg logit contributions | |
mess | -0.370 |
aj | -0.324 |
wra | -0.299 |
pic | -0.291 |
onna | -0.286 |
Token | k |
Token ID | 479 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
aroo | +0.030 |
apped | +0.030 |
citizens | +0.027 |
ovable | +0.027 |
ive | +0.026 |
Neg logit contributions | |
mess | -0.032 |
slippery | -0.027 |
wra | -0.027 |
scar | -0.026 |
aman | -0.025 |
Token | ang |
Token ID | 648 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
aroo | +0.132 |
itte | +0.127 |
citizens | +0.127 |
ter | +0.126 |
ovable | +0.126 |
Neg logit contributions | |
mess | -0.223 |
wra | -0.213 |
aj | -0.209 |
liv | -0.208 |
slippery | -0.206 |
Token | aroo |
Token ID | 38049 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
apped | +0.132 |
onel | +0.123 |
citizens | +0.122 |
ovable | +0.109 |
protector | +0.098 |
Neg logit contributions | |
mess | -0.852 |
slippery | -0.819 |
liv | -0.811 |
gh | -0.794 |
wra | -0.792 |
Token | ," |
Token ID | 553 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
aroo | +1.433 |
ter | +1.306 |
apped | +1.299 |
itte | +1.272 |
ovable | +1.229 |
Neg logit contributions | |
mess | -0.879 |
onna | -0.664 |
aj | -0.661 |
slippery | -0.629 |
wra | -0.626 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
aroo | +0.149 |
ter | +0.141 |
apped | +0.129 |
onel | +0.128 |
ovable | +0.128 |
Neg logit contributions | |
mess | -0.068 |
wra | -0.052 |
pic | -0.050 |
aj | -0.049 |
onna | -0.049 |
Token | says |
Token ID | 1139 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
mess | +0.187 |
aj | +0.166 |
wra | +0.154 |
liv | +0.154 |
onna | +0.151 |
Neg logit contributions | |
aroo | -0.265 |
ter | -0.241 |
crow | -0.225 |
apped | -0.218 |
member | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
mess | +0.216 |
aj | +0.188 |
onna | +0.184 |
wra | +0.181 |
fault | +0.172 |
Neg logit contributions | |
aroo | -0.320 |
ter | -0.282 |
crow | -0.266 |
itte | -0.260 |
ovable | -0.247 |
Token | " |
Token ID | 366 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
aroo | +0.116 |
ter | +0.108 |
member | +0.096 |
crow | +0.096 |
ovable | +0.096 |
Neg logit contributions | |
mess | -0.073 |
onna | -0.066 |
wra | -0.063 |
aj | -0.062 |
pic | -0.059 |
Token | get |
Token ID | 651 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
aroo | +0.156 |
ter | +0.141 |
crow | +0.127 |
apped | +0.126 |
itte | +0.123 |
Neg logit contributions | |
mess | -0.135 |
aj | -0.114 |
onna | -0.111 |
wra | -0.107 |
fault | -0.105 |
Token | hurt |
Token ID | 5938 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
mess | +0.067 |
aj | +0.055 |
wra | +0.054 |
slippery | +0.053 |
onna | +0.052 |
Neg logit contributions | |
aroo | -0.082 |
ter | -0.071 |
itte | -0.066 |
crow | -0.066 |
apped | -0.065 |
Token | or |
Token ID | 393 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
mess | +0.155 |
aj | +0.131 |
wra | +0.127 |
onna | +0.125 |
fault | +0.122 |
Neg logit contributions | |
aroo | -0.180 |
ter | -0.157 |
apped | -0.146 |
itte | -0.146 |
crow | -0.142 |
Token | make |
Token ID | 787 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
mess | +0.259 |
aj | +0.211 |
wra | +0.205 |
onna | +0.202 |
slippery | +0.200 |
Neg logit contributions | |
aroo | -0.324 |
ter | -0.287 |
apped | -0.269 |
itte | -0.266 |
crow | -0.266 |
Token | a |
Token ID | 257 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
mess | +0.048 |
aj | +0.043 |
wra | +0.040 |
onna | +0.040 |
pic | +0.039 |
Neg logit contributions | |
aroo | -0.057 |
ter | -0.051 |
crow | -0.046 |
apped | -0.045 |
itte | -0.044 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
mess | +0.072 |
aj | +0.070 |
liv | +0.061 |
wra | +0.061 |
pic | +0.059 |
Neg logit contributions | |
aroo | -0.172 |
ter | -0.159 |
crow | -0.146 |
pilot | -0.144 |
member | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
mess | +1.187 |
aj | +0.963 |
wra | +0.963 |
onna | +0.915 |
slippery | +0.890 |
Neg logit contributions | |
aroo | -1.294 |
ter | -1.097 |
crow | -1.026 |
apped | -1.021 |
itte | -1.012 |
Token | And |
Token ID | 843 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
mess | +0.071 |
aj | +0.065 |
onna | +0.061 |
wra | +0.059 |
pic | +0.058 |
Neg logit contributions | |
aroo | -0.087 |
ter | -0.080 |
crow | -0.069 |
apped | -0.069 |
member | -0.068 |
Token | you |
Token ID | 345 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
aroo | +0.106 |
ter | +0.093 |
crow | +0.086 |
apped | +0.085 |
itte | +0.085 |
Neg logit contributions | |
mess | -0.089 |
aj | -0.074 |
onna | -0.073 |
wra | -0.072 |
pic | -0.071 |
Token | 're |
Token ID | 821 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
mess | +0.037 |
wra | +0.029 |
onna | +0.029 |
aj | +0.029 |
slippery | +0.029 |
Neg logit contributions | |
aroo | -0.041 |
ter | -0.036 |
apped | -0.033 |
crow | -0.032 |
itte | -0.031 |
Token | making |
Token ID | 1642 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
aroo | +0.019 |
ter | +0.016 |
crow | +0.016 |
ive | +0.016 |
apped | +0.016 |
Neg logit contributions | |
mess | -0.013 |
slippery | -0.010 |
aj | -0.010 |
fault | -0.009 |
fun | -0.009 |
Token | they |
Token ID | 484 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
aroo | +0.101 |
ter | +0.092 |
apped | +0.084 |
crow | +0.084 |
itte | +0.081 |
Neg logit contributions | |
mess | -0.056 |
aj | -0.046 |
wra | -0.043 |
pays | -0.042 |
onna | -0.040 |
Token | also |
Token ID | 635 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
mess | +0.108 |
slippery | +0.081 |
onna | +0.081 |
aj | +0.079 |
pic | +0.079 |
Neg logit contributions | |
aroo | -0.162 |
ter | -0.146 |
crow | -0.130 |
eros | -0.126 |
ative | -0.126 |
Token | made |
Token ID | 925 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
mess | +0.219 |
aj | +0.182 |
onna | +0.170 |
wra | +0.167 |
fault | +0.167 |
Neg logit contributions | |
aroo | -0.267 |
ter | -0.238 |
crow | -0.210 |
itte | -0.208 |
apped | -0.204 |
Token | a |
Token ID | 257 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
mess | +0.282 |
aj | +0.248 |
wra | +0.233 |
onna | +0.229 |
pic | +0.225 |
Neg logit contributions | |
aroo | -0.329 |
ter | -0.294 |
crow | -0.263 |
apped | -0.259 |
itte | -0.256 |
Token | big |
Token ID | 1263 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
mess | +0.103 |
aj | +0.103 |
liv | +0.095 |
wra | +0.092 |
onna | +0.090 |
Neg logit contributions | |
aroo | -0.159 |
ter | -0.143 |
pilot | -0.131 |
member | -0.130 |
crow | -0.127 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
mess | +0.286 |
aj | +0.257 |
wra | +0.237 |
onna | +0.235 |
pic | +0.227 |
Neg logit contributions | |
aroo | -0.400 |
ter | -0.362 |
crow | -0.326 |
apped | -0.322 |
member | -0.315 |
Token | . |
Token ID | 13 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
mess | +1.142 |
wra | +0.932 |
aj | +0.913 |
onna | +0.867 |
slippery | +0.846 |
Neg logit contributions | |
aroo | -1.321 |
ter | -1.096 |
crow | -1.069 |
itte | -1.043 |
apped | -1.029 |
Token | They |
Token ID | 1119 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
mess | +0.086 |
aj | +0.079 |
onna | +0.074 |
wra | +0.072 |
pic | +0.071 |
Neg logit contributions | |
aroo | -0.108 |
ter | -0.098 |
crow | -0.087 |
apped | -0.085 |
member | -0.084 |
Token | threw |
Token ID | 9617 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
mess | +0.148 |
aj | +0.121 |
wra | +0.120 |
onna | +0.114 |
slippery | +0.113 |
Neg logit contributions | |
aroo | -0.197 |
ter | -0.176 |
crow | -0.160 |
apped | -0.156 |
ive | -0.152 |
Token | their |
Token ID | 511 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
mess | +0.252 |
aj | +0.247 |
onna | +0.229 |
liv | +0.224 |
aman | +0.220 |
Neg logit contributions | |
aroo | -0.233 |
ter | -0.211 |
crow | -0.188 |
apped | -0.181 |
member | -0.173 |
Token | toys |
Token ID | 14958 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
mess | +0.306 |
aj | +0.264 |
wra | +0.251 |
onna | +0.239 |
fault | +0.235 |
Neg logit contributions | |
aroo | -0.421 |
ter | -0.383 |
crow | -0.348 |
apped | -0.344 |
itte | -0.339 |
Token | too |
Token ID | 1165 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
mess | +0.226 |
aj | +0.203 |
wra | +0.192 |
onna | +0.190 |
pic | +0.184 |
Neg logit contributions | |
aroo | -0.241 |
ter | -0.219 |
crow | -0.192 |
apped | -0.190 |
itte | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
mess | +0.316 |
aj | +0.297 |
wra | +0.286 |
liv | +0.280 |
icol | +0.278 |
Neg logit contributions | |
aroo | -0.236 |
ter | -0.208 |
apped | -0.176 |
crow | -0.176 |
member | -0.171 |
Token | After |
Token ID | 2293 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
mess | +0.064 |
aj | +0.062 |
onna | +0.057 |
pic | +0.055 |
wra | +0.054 |
Neg logit contributions | |
aroo | -0.092 |
ter | -0.084 |
member | -0.073 |
crow | -0.073 |
itte | -0.072 |
Token | all |
Token ID | 477 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
mess | +0.264 |
aj | +0.227 |
wra | +0.220 |
onna | +0.214 |
pic | +0.212 |
Neg logit contributions | |
aroo | -0.310 |
ter | -0.278 |
crow | -0.252 |
apped | -0.246 |
itte | -0.246 |
Token | the |
Token ID | 262 |
Feature activation | -5.70e-03 |
Pos logit contributions | |
aroo | +0.101 |
ter | +0.091 |
apped | +0.083 |
itte | +0.081 |
ovable | +0.081 |
Neg logit contributions | |
mess | -0.087 |
aj | -0.068 |
wra | -0.067 |
slippery | -0.067 |
pic | -0.066 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
mess | +0.010 |
aj | +0.008 |
wra | +0.008 |
pic | +0.008 |
onna | +0.008 |
Neg logit contributions | |
aroo | -0.013 |
ter | -0.012 |
apped | -0.011 |
crow | -0.011 |
itte | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
mess | +1.046 |
aj | +0.893 |
wra | +0.861 |
onna | +0.825 |
fault | +0.792 |
Neg logit contributions | |
aroo | -1.373 |
ter | -1.210 |
crow | -1.120 |
itte | -1.090 |
apped | -1.088 |
Token | made |
Token ID | 925 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
mess | +0.156 |
aj | +0.145 |
wra | +0.138 |
icol | +0.137 |
pic | +0.134 |
Neg logit contributions | |
aroo | -0.206 |
ter | -0.191 |
apped | -0.169 |
member | -0.166 |
crow | -0.166 |
Token | , |
Token ID | 11 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
mess | +0.264 |
aj | +0.238 |
wra | +0.224 |
onna | +0.221 |
pic | +0.216 |
Neg logit contributions | |
aroo | -0.271 |
ter | -0.242 |
crow | -0.214 |
apped | -0.212 |
itte | -0.207 |
Token | Sophia |
Token ID | 39953 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
mess | +0.081 |
aj | +0.074 |
onna | +0.068 |
wra | +0.068 |
fault | +0.066 |
Neg logit contributions | |
aroo | -0.096 |
ter | -0.088 |
crow | -0.077 |
apped | -0.076 |
itte | -0.074 |
Token | used |
Token ID | 973 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
mess | +0.361 |
aj | +0.308 |
wra | +0.285 |
onna | +0.284 |
fault | +0.269 |
Neg logit contributions | |
aroo | -0.497 |
ter | -0.448 |
crow | -0.405 |
apped | -0.397 |
itte | -0.390 |
Token | dad |
Token ID | 9955 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
mess | +0.291 |
aj | +0.251 |
wra | +0.239 |
onna | +0.233 |
pic | +0.230 |
Neg logit contributions | |
aroo | -0.343 |
ter | -0.308 |
crow | -0.276 |
apped | -0.274 |
itte | -0.272 |
Token | came |
Token ID | 1625 |
Feature activation | -8.78e-03 |
Pos logit contributions | |
aroo | +0.053 |
ter | +0.046 |
crow | +0.043 |
itte | +0.042 |
ive | +0.041 |
Neg logit contributions | |
mess | -0.036 |
aj | -0.030 |
pays | -0.028 |
wra | -0.028 |
onna | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
mess | +0.016 |
aj | +0.014 |
wra | +0.013 |
onna | +0.013 |
slippery | +0.013 |
Neg logit contributions | |
aroo | -0.019 |
ter | -0.016 |
crow | -0.015 |
itte | -0.015 |
apped | -0.015 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
mess | +0.289 |
aj | +0.247 |
wra | +0.241 |
onna | +0.226 |
slippery | +0.220 |
Neg logit contributions | |
aroo | -0.381 |
ter | -0.336 |
crow | -0.317 |
ovable | -0.312 |
apped | -0.308 |
Token | the |
Token ID | 262 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
mess | +0.101 |
aj | +0.085 |
wra | +0.084 |
onna | +0.079 |
pic | +0.079 |
Neg logit contributions | |
aroo | -0.119 |
ter | -0.106 |
apped | -0.096 |
crow | -0.095 |
itte | -0.094 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
mess | +0.057 |
aj | +0.047 |
wra | +0.046 |
fault | +0.044 |
slippery | +0.043 |
Neg logit contributions | |
aroo | -0.062 |
ter | -0.054 |
apped | -0.050 |
crow | -0.050 |
itte | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
mess | +1.152 |
wra | +0.962 |
aj | +0.937 |
onna | +0.881 |
slippery | +0.878 |
Neg logit contributions | |
aroo | -1.300 |
ter | -1.108 |
crow | -1.039 |
itte | -1.017 |
apped | -1.005 |
Token | They |
Token ID | 1119 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
mess | +0.085 |
aj | +0.076 |
wra | +0.072 |
onna | +0.072 |
pic | +0.069 |
Neg logit contributions | |
aroo | -0.094 |
ter | -0.084 |
crow | -0.074 |
apped | -0.073 |
itte | -0.072 |
Token | were |
Token ID | 547 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
mess | +0.174 |
wra | +0.144 |
aj | +0.140 |
slippery | +0.134 |
onna | +0.132 |
Neg logit contributions | |
aroo | -0.197 |
ter | -0.172 |
crow | -0.159 |
apped | -0.153 |
ive | -0.152 |
Token | not |
Token ID | 407 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
aroo | +0.084 |
ter | +0.075 |
crow | +0.069 |
apped | +0.067 |
itte | +0.065 |
Neg logit contributions | |
mess | -0.065 |
aj | -0.055 |
wra | -0.052 |
onna | -0.050 |
slippery | -0.049 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
mess | +0.701 |
aj | +0.602 |
wra | +0.576 |
onna | +0.556 |
fault | +0.550 |
Neg logit contributions | |
aroo | -0.698 |
ter | -0.596 |
crow | -0.557 |
itte | -0.528 |
apped | -0.528 |
Token | it |
Token ID | 340 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
mess | +0.291 |
aj | +0.252 |
wra | +0.240 |
onna | +0.235 |
pic | +0.234 |
Neg logit contributions | |
aroo | -0.314 |
ter | -0.279 |
crow | -0.249 |
apped | -0.247 |
itte | -0.242 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
mess | +0.267 |
aj | +0.227 |
wra | +0.215 |
onna | +0.212 |
pic | +0.205 |
Neg logit contributions | |
aroo | -0.369 |
ter | -0.332 |
crow | -0.301 |
apped | -0.298 |
itte | -0.293 |
Token | like |
Token ID | 588 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
mess | +0.384 |
aj | +0.347 |
wra | +0.326 |
onna | +0.323 |
liv | +0.314 |
Neg logit contributions | |
aroo | -0.452 |
ter | -0.413 |
crow | -0.366 |
apped | -0.365 |
itte | -0.357 |
Token | a |
Token ID | 257 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
mess | +0.056 |
aj | +0.050 |
wra | +0.047 |
onna | +0.046 |
pic | +0.045 |
Neg logit contributions | |
aroo | -0.069 |
ter | -0.062 |
crow | -0.055 |
apped | -0.055 |
itte | -0.054 |
Token | big |
Token ID | 1263 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
mess | +0.122 |
aj | +0.110 |
wra | +0.102 |
onna | +0.101 |
liv | +0.098 |
Neg logit contributions | |
aroo | -0.141 |
ter | -0.127 |
crow | -0.113 |
apped | -0.111 |
itte | -0.109 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
mess | +0.318 |
aj | +0.276 |
wra | +0.263 |
onna | +0.259 |
pic | +0.253 |
Neg logit contributions | |
aroo | -0.354 |
ter | -0.317 |
crow | -0.284 |
apped | -0.282 |
itte | -0.277 |
Token | . |
Token ID | 13 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
mess | +1.130 |
wra | +0.936 |
aj | +0.910 |
onna | +0.876 |
slippery | +0.843 |
Neg logit contributions | |
aroo | -1.319 |
ter | -1.111 |
crow | -1.048 |
itte | -1.043 |
apped | -1.042 |
Token | The |
Token ID | 383 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
mess | +0.081 |
aj | +0.074 |
onna | +0.069 |
wra | +0.068 |
pic | +0.067 |
Neg logit contributions | |
aroo | -0.101 |
ter | -0.091 |
crow | -0.080 |
apped | -0.080 |
itte | -0.078 |
Token | little |
Token ID | 1310 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
aroo | +0.258 |
ter | +0.225 |
apped | +0.222 |
ovable | +0.209 |
crow | +0.206 |
Neg logit contributions | |
mess | -0.282 |
wra | -0.231 |
aj | -0.223 |
slippery | -0.217 |
mistake | -0.215 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
aroo | +0.042 |
ovable | +0.035 |
apped | +0.034 |
ter | +0.034 |
itte | +0.034 |
Neg logit contributions | |
mess | -0.069 |
wra | -0.059 |
aj | -0.058 |
slippery | -0.056 |
scar | -0.056 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
aroo | +0.253 |
ter | +0.232 |
crow | +0.209 |
apped | +0.204 |
itte | +0.201 |
Neg logit contributions | |
mess | -0.174 |
aj | -0.144 |
wra | -0.138 |
onna | -0.134 |
slippery | -0.129 |
Token | ceiling |
Token ID | 13387 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
mess | +0.016 |
aj | +0.013 |
wra | +0.013 |
fault | +0.012 |
slippery | +0.012 |
Neg logit contributions | |
aroo | -0.016 |
ter | -0.014 |
apped | -0.013 |
ovable | -0.012 |
crow | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
mess | +0.212 |
aj | +0.185 |
onna | +0.175 |
wra | +0.174 |
fault | +0.167 |
Neg logit contributions | |
aroo | -0.236 |
ter | -0.209 |
crow | -0.189 |
apped | -0.186 |
itte | -0.184 |
Token |
|
Token ID | 198 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
mess | +0.049 |
aj | +0.049 |
onna | +0.045 |
pic | +0.044 |
aman | +0.043 |
Neg logit contributions | |
aroo | -0.079 |
ter | -0.072 |
ovable | -0.063 |
crow | -0.063 |
member | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
mess | +0.102 |
aj | +0.093 |
onna | +0.086 |
pic | +0.084 |
liv | +0.084 |
Neg logit contributions | |
aroo | -0.118 |
ter | -0.110 |
apped | -0.093 |
crow | -0.093 |
itte | -0.091 |
Token | The |
Token ID | 464 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
mess | +0.082 |
aj | +0.075 |
liv | +0.071 |
pic | +0.068 |
aman | +0.067 |
Neg logit contributions | |
aroo | -0.139 |
ter | -0.136 |
apped | -0.118 |
crow | -0.115 |
ovable | -0.114 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
aroo | +0.044 |
apped | +0.039 |
ter | +0.039 |
crow | +0.038 |
ovable | +0.036 |
Neg logit contributions | |
mess | -0.049 |
wra | -0.039 |
mistake | -0.038 |
slippery | -0.038 |
aj | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
mess | +0.996 |
aj | +0.755 |
wra | +0.751 |
pays | +0.718 |
slippery | +0.704 |
Neg logit contributions | |
aroo | -1.451 |
ter | -1.280 |
crow | -1.200 |
itte | -1.163 |
ovable | -1.154 |
Token | so |
Token ID | 523 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
mess | +0.158 |
aj | +0.150 |
wra | +0.136 |
pic | +0.134 |
onna | +0.134 |
Neg logit contributions | |
aroo | -0.233 |
ter | -0.217 |
apped | -0.191 |
crow | -0.189 |
member | -0.187 |
Token | big |
Token ID | 1263 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
mess | +0.215 |
aj | +0.180 |
wra | +0.166 |
onna | +0.164 |
slippery | +0.155 |
Neg logit contributions | |
aroo | -0.386 |
ter | -0.353 |
crow | -0.322 |
apped | -0.316 |
itte | -0.312 |
Token | that |
Token ID | 326 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
mess | +0.306 |
aj | +0.291 |
onna | +0.271 |
liv | +0.267 |
wra | +0.266 |
Neg logit contributions | |
aroo | -0.276 |
ter | -0.251 |
crow | -0.216 |
apped | -0.208 |
member | -0.204 |
Token | it |
Token ID | 340 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
aroo | +0.143 |
ter | +0.128 |
crow | +0.116 |
apped | +0.115 |
itte | +0.114 |
Neg logit contributions | |
mess | -0.116 |
aj | -0.096 |
wra | -0.094 |
onna | -0.092 |
pic | -0.092 |
Token | she |
Token ID | 673 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
mess | +0.110 |
aj | +0.099 |
wra | +0.094 |
onna | +0.093 |
pic | +0.091 |
Neg logit contributions | |
aroo | -0.090 |
ter | -0.079 |
crow | -0.069 |
apped | -0.069 |
itte | -0.067 |
Token | had |
Token ID | 550 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
mess | +0.092 |
aj | +0.075 |
wra | +0.072 |
onna | +0.070 |
fault | +0.068 |
Neg logit contributions | |
aroo | -0.130 |
ter | -0.115 |
crow | -0.105 |
apped | -0.102 |
itte | -0.100 |
Token | made |
Token ID | 925 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
mess | +0.159 |
aj | +0.149 |
wra | +0.135 |
onna | +0.133 |
aman | +0.133 |
Neg logit contributions | |
aroo | -0.203 |
ter | -0.189 |
crow | -0.169 |
apped | -0.168 |
member | -0.166 |
Token | a |
Token ID | 257 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
mess | +0.289 |
aj | +0.270 |
wra | +0.252 |
onna | +0.251 |
pic | +0.243 |
Neg logit contributions | |
aroo | -0.276 |
ter | -0.251 |
crow | -0.220 |
apped | -0.212 |
member | -0.210 |
Token | big |
Token ID | 1263 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
mess | +0.074 |
aj | +0.073 |
liv | +0.064 |
wra | +0.063 |
onna | +0.062 |
Neg logit contributions | |
aroo | -0.142 |
ter | -0.129 |
member | -0.119 |
crow | -0.118 |
pilot | -0.118 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
mess | +0.250 |
aj | +0.226 |
wra | +0.206 |
onna | +0.203 |
liv | +0.197 |
Neg logit contributions | |
aroo | -0.403 |
ter | -0.367 |
crow | -0.333 |
apped | -0.327 |
member | -0.324 |
Token | ! |
Token ID | 0 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
mess | +1.235 |
wra | +1.035 |
aj | +1.020 |
onna | +0.987 |
slippery | +0.957 |
Neg logit contributions | |
aroo | -1.206 |
ter | -1.008 |
crow | -0.946 |
apped | -0.930 |
itte | -0.919 |
Token | Leaves |
Token ID | 46597 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
mess | +0.407 |
aj | +0.373 |
onna | +0.351 |
wra | +0.336 |
pic | +0.333 |
Neg logit contributions | |
aroo | -0.575 |
ter | -0.523 |
apped | -0.454 |
crow | -0.452 |
pilot | -0.450 |
Token | were |
Token ID | 547 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
mess | +0.070 |
aj | +0.064 |
wra | +0.059 |
onna | +0.059 |
pic | +0.058 |
Neg logit contributions | |
aroo | -0.069 |
ter | -0.061 |
crow | -0.054 |
apped | -0.053 |
itte | -0.052 |
Token | all |
Token ID | 477 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
aroo | +0.093 |
ter | +0.088 |
crow | +0.076 |
apped | +0.075 |
itte | +0.074 |
Neg logit contributions | |
mess | -0.058 |
aj | -0.055 |
liv | -0.050 |
icol | -0.049 |
pic | -0.049 |
Token | over |
Token ID | 625 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
aroo | +0.094 |
ter | +0.089 |
crow | +0.078 |
apped | +0.078 |
member | +0.077 |
Neg logit contributions | |
mess | -0.058 |
aj | -0.056 |
pic | -0.051 |
icol | -0.050 |
wra | -0.049 |
Token | odge |
Token ID | 9728 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
aroo | +0.045 |
ter | +0.037 |
pilot | +0.037 |
member | +0.036 |
messenger | +0.035 |
Neg logit contributions | |
mess | -0.039 |
aj | -0.038 |
onna | -0.034 |
wra | -0.034 |
liv | -0.033 |
Token | began |
Token ID | 2540 |
Feature activation | +2.06e-03 |
Pos logit contributions | |
mess | +0.189 |
slippery | +0.153 |
wra | +0.149 |
flips | +0.149 |
onna | +0.148 |
Neg logit contributions | |
aroo | -0.211 |
ter | -0.193 |
ive | -0.177 |
itte | -0.176 |
apped | -0.174 |
Token | to |
Token ID | 284 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aroo | +0.005 |
ter | +0.004 |
crow | +0.004 |
apped | +0.004 |
itte | +0.004 |
Neg logit contributions | |
mess | -0.003 |
aj | -0.003 |
wra | -0.003 |
onna | -0.003 |
pic | -0.003 |
Token | spread |
Token ID | 4104 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
mess | +0.278 |
aj | +0.229 |
onna | +0.223 |
wra | +0.219 |
slippery | +0.218 |
Neg logit contributions | |
aroo | -0.303 |
ter | -0.269 |
apped | -0.246 |
crow | -0.239 |
itte | -0.238 |
Token | his |
Token ID | 465 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
mess | +0.079 |
aj | +0.068 |
wra | +0.066 |
onna | +0.064 |
slippery | +0.064 |
Neg logit contributions | |
aroo | -0.092 |
ter | -0.081 |
itte | -0.073 |
apped | -0.072 |
crow | -0.072 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
mess | +0.216 |
aj | +0.192 |
wra | +0.174 |
slippery | +0.169 |
fault | +0.168 |
Neg logit contributions | |
aroo | -0.291 |
ter | -0.269 |
crow | -0.242 |
apped | -0.240 |
itte | -0.238 |
Token | again |
Token ID | 757 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
mess | +1.198 |
aj | +1.067 |
wra | +1.013 |
onna | +0.996 |
pic | +0.966 |
Neg logit contributions | |
aroo | -1.201 |
ter | -1.061 |
crow | -0.948 |
apped | -0.931 |
itte | -0.915 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
mess | +0.238 |
aj | +0.210 |
wra | +0.198 |
onna | +0.196 |
pic | +0.191 |
Neg logit contributions | |
aroo | -0.262 |
ter | -0.234 |
crow | -0.209 |
apped | -0.207 |
itte | -0.203 |
Token | He |
Token ID | 679 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
mess | +0.054 |
aj | +0.051 |
onna | +0.048 |
wra | +0.046 |
pic | +0.046 |
Neg logit contributions | |
aroo | -0.073 |
ter | -0.067 |
crow | -0.059 |
apped | -0.059 |
member | -0.058 |
Token | jumped |
Token ID | 11687 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
mess | +0.085 |
aj | +0.071 |
wra | +0.068 |
onna | +0.067 |
slippery | +0.065 |
Neg logit contributions | |
aroo | -0.112 |
ter | -0.101 |
crow | -0.092 |
apped | -0.090 |
itte | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
mess | +0.313 |
aj | +0.293 |
pic | +0.272 |
wra | +0.270 |
liv | +0.268 |
Neg logit contributions | |
aroo | -0.258 |
ter | -0.232 |
apped | -0.196 |
crow | -0.196 |
itte | -0.188 |
Token | week |
Token ID | 1285 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
aroo | +0.022 |
ter | +0.020 |
apped | +0.018 |
itte | +0.017 |
crow | +0.017 |
Neg logit contributions | |
mess | -0.020 |
aj | -0.017 |
onna | -0.016 |
pic | -0.016 |
wra | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
mess | +0.296 |
aj | +0.256 |
wra | +0.244 |
onna | +0.238 |
pic | +0.236 |
Neg logit contributions | |
aroo | -0.356 |
ter | -0.316 |
crow | -0.286 |
itte | -0.281 |
apped | -0.280 |
Token | making |
Token ID | 1642 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
mess | +0.320 |
aj | +0.276 |
wra | +0.261 |
onna | +0.256 |
pic | +0.254 |
Neg logit contributions | |
aroo | -0.366 |
ter | -0.325 |
crow | -0.292 |
apped | -0.284 |
itte | -0.283 |
Token | a |
Token ID | 257 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
mess | +0.327 |
aj | +0.301 |
wra | +0.281 |
onna | +0.279 |
liv | +0.269 |
Neg logit contributions | |
aroo | -0.368 |
ter | -0.333 |
crow | -0.295 |
apped | -0.291 |
member | -0.284 |
Token | huge |
Token ID | 3236 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
mess | +0.107 |
aj | +0.095 |
wra | +0.088 |
onna | +0.087 |
pic | +0.084 |
Neg logit contributions | |
aroo | -0.152 |
ter | -0.138 |
crow | -0.125 |
apped | -0.123 |
itte | -0.121 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
mess | +0.277 |
aj | +0.227 |
wra | +0.217 |
onna | +0.214 |
pic | +0.210 |
Neg logit contributions | |
aroo | -0.351 |
ter | -0.316 |
crow | -0.287 |
apped | -0.284 |
itte | -0.282 |
Token | . |
Token ID | 13 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
mess | +1.199 |
wra | +0.989 |
aj | +0.981 |
onna | +0.943 |
slippery | +0.911 |
Neg logit contributions | |
aroo | -1.248 |
ter | -1.041 |
crow | -0.986 |
apped | -0.965 |
itte | -0.963 |
Token | It |
Token ID | 632 |
Feature activation | +1.24e-03 |
Pos logit contributions | |
mess | +0.089 |
aj | +0.081 |
onna | +0.076 |
wra | +0.074 |
pic | +0.074 |
Neg logit contributions | |
aroo | -0.116 |
ter | -0.106 |
crow | -0.093 |
apped | -0.091 |
itte | -0.091 |
Token | was |
Token ID | 373 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aroo | +0.003 |
ter | +0.002 |
crow | +0.002 |
itte | +0.002 |
apped | +0.002 |
Neg logit contributions | |
mess | -0.002 |
aj | -0.002 |
wra | -0.002 |
aman | -0.002 |
onna | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
mess | +0.177 |
aj | +0.172 |
icol | +0.157 |
wra | +0.155 |
liv | +0.155 |
Neg logit contributions | |
aroo | -0.226 |
ter | -0.213 |
apped | -0.183 |
crow | -0.179 |
itte | -0.178 |
Token | sm |
Token ID | 895 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
mess | +0.206 |
aj | +0.181 |
wra | +0.166 |
onna | +0.162 |
pic | +0.160 |
Neg logit contributions | |
aroo | -0.364 |
ter | -0.333 |
apped | -0.303 |
crow | -0.303 |
itte | -0.298 |
Token | . |
Token ID | 13 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
mess | +0.343 |
aj | +0.297 |
onna | +0.286 |
fault | +0.273 |
wra | +0.269 |
Neg logit contributions | |
aroo | -0.496 |
ter | -0.444 |
itte | -0.411 |
crow | -0.403 |
apped | -0.402 |
Token | They |
Token ID | 1119 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
mess | +0.081 |
aj | +0.077 |
onna | +0.074 |
pic | +0.070 |
wra | +0.070 |
Neg logit contributions | |
aroo | -0.107 |
ter | -0.098 |
member | -0.085 |
crow | -0.085 |
apped | -0.084 |
Token | only |
Token ID | 691 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
mess | +0.178 |
wra | +0.147 |
aj | +0.144 |
onna | +0.143 |
slippery | +0.139 |
Neg logit contributions | |
aroo | -0.205 |
ter | -0.184 |
apped | -0.164 |
crow | -0.164 |
ive | -0.157 |
Token | had |
Token ID | 550 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
mess | +0.115 |
onna | +0.091 |
wra | +0.091 |
pays | +0.088 |
fuss | +0.088 |
Neg logit contributions | |
aroo | -0.146 |
ter | -0.131 |
crow | -0.114 |
apped | -0.114 |
itte | -0.111 |
Token | a |
Token ID | 257 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
mess | +0.170 |
aj | +0.152 |
wra | +0.141 |
onna | +0.140 |
liv | +0.137 |
Neg logit contributions | |
aroo | -0.195 |
ter | -0.176 |
crow | -0.157 |
apped | -0.155 |
member | -0.151 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
mess | +0.116 |
aj | +0.109 |
liv | +0.101 |
wra | +0.098 |
onna | +0.098 |
Neg logit contributions | |
aroo | -0.129 |
ter | -0.114 |
crow | -0.100 |
member | -0.099 |
pilot | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
mess | +1.131 |
wra | +0.967 |
aj | +0.929 |
onna | +0.876 |
slippery | +0.852 |
Neg logit contributions | |
aroo | -1.279 |
ter | -1.040 |
crow | -1.038 |
itte | -0.998 |
apped | -0.986 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
mess | +0.065 |
aj | +0.059 |
onna | +0.055 |
wra | +0.055 |
pic | +0.053 |
Neg logit contributions | |
aroo | -0.079 |
ter | -0.072 |
crow | -0.063 |
apped | -0.062 |
itte | -0.062 |
Token | S |
Token ID | 50 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
aroo | +0.043 |
ter | +0.039 |
crow | +0.034 |
itte | +0.034 |
apped | +0.033 |
Neg logit contributions | |
mess | -0.038 |
aj | -0.034 |
wra | -0.032 |
onna | -0.032 |
pic | -0.032 |
Token | ara |
Token ID | 3301 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
mess | +0.176 |
wra | +0.138 |
slippery | +0.136 |
fault | +0.135 |
aj | +0.133 |
Neg logit contributions | |
aroo | -0.289 |
ter | -0.268 |
member | -0.251 |
crow | -0.245 |
itte | -0.243 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
mess | +0.450 |
aj | +0.385 |
wra | +0.357 |
onna | +0.351 |
pic | +0.336 |
Neg logit contributions | |
aroo | -0.714 |
ter | -0.646 |
crow | -0.587 |
apped | -0.576 |
itte | -0.572 |
Token | microwave |
Token ID | 27000 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
mess | +0.102 |
aj | +0.092 |
onna | +0.087 |
fault | +0.086 |
wra | +0.085 |
Neg logit contributions | |
aroo | -0.101 |
ter | -0.091 |
apped | -0.079 |
crow | -0.079 |
itte | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
mess | +0.516 |
aj | +0.467 |
pic | +0.438 |
wra | +0.434 |
onna | +0.428 |
Neg logit contributions | |
aroo | -0.570 |
ter | -0.519 |
apped | -0.460 |
crow | -0.459 |
member | -0.436 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
mess | +0.283 |
aj | +0.239 |
wra | +0.237 |
onna | +0.225 |
slippery | +0.219 |
Neg logit contributions | |
aroo | -0.335 |
ter | -0.299 |
crow | -0.274 |
apped | -0.271 |
ovable | -0.268 |
Token | a |
Token ID | 257 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
mess | +0.099 |
aj | +0.088 |
wra | +0.083 |
onna | +0.082 |
pic | +0.080 |
Neg logit contributions | |
aroo | -0.108 |
ter | -0.097 |
crow | -0.086 |
apped | -0.085 |
itte | -0.083 |
Token | black |
Token ID | 2042 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
mess | +0.110 |
aj | +0.110 |
liv | +0.103 |
fault | +0.103 |
onna | +0.101 |
Neg logit contributions | |
aroo | -0.150 |
ter | -0.134 |
pilot | -0.124 |
member | -0.120 |
crow | -0.119 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
mess | +0.415 |
wra | +0.341 |
aj | +0.338 |
onna | +0.316 |
pic | +0.304 |
Neg logit contributions | |
aroo | -0.504 |
ter | -0.447 |
apped | -0.414 |
ovable | -0.413 |
itte | -0.411 |
Token | . |
Token ID | 13 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
mess | +1.267 |
wra | +1.075 |
aj | +1.062 |
onna | +1.004 |
slippery | +0.987 |
Neg logit contributions | |
aroo | -1.176 |
ter | -0.976 |
crow | -0.924 |
itte | -0.894 |
apped | -0.890 |
Token | Smoke |
Token ID | 25416 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
mess | +0.081 |
aj | +0.072 |
wra | +0.068 |
onna | +0.068 |
pic | +0.065 |
Neg logit contributions | |
aroo | -0.091 |
ter | -0.082 |
crow | -0.072 |
apped | -0.071 |
member | -0.071 |
Token | came |
Token ID | 1625 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
mess | +0.138 |
aj | +0.124 |
wra | +0.115 |
onna | +0.114 |
pic | +0.112 |
Neg logit contributions | |
aroo | -0.170 |
ter | -0.155 |
crow | -0.138 |
apped | -0.136 |
itte | -0.132 |
Token | out |
Token ID | 503 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
aroo | +0.005 |
ter | +0.004 |
crow | +0.003 |
apped | +0.003 |
itte | +0.003 |
Neg logit contributions | |
mess | -0.006 |
aj | -0.006 |
wra | -0.005 |
onna | -0.005 |
pic | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
aroo | +0.031 |
ter | +0.025 |
crow | +0.022 |
itte | +0.021 |
apped | +0.020 |
Neg logit contributions | |
mess | -0.060 |
aj | -0.051 |
onna | -0.051 |
wra | -0.051 |
slippery | -0.050 |
Token | loud |
Token ID | 7812 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
aroo | +0.304 |
ter | +0.274 |
crow | +0.250 |
apped | +0.250 |
itte | +0.247 |
Neg logit contributions | |
mess | -0.200 |
aj | -0.170 |
wra | -0.161 |
onna | -0.160 |
pic | -0.154 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
mess | +0.403 |
aj | +0.359 |
wra | +0.333 |
onna | +0.328 |
pic | +0.318 |
Neg logit contributions | |
aroo | -0.573 |
ter | -0.520 |
crow | -0.472 |
apped | -0.462 |
itte | -0.452 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
mess | +0.412 |
aj | +0.353 |
wra | +0.337 |
onna | +0.330 |
fault | +0.319 |
Neg logit contributions | |
aroo | -0.458 |
ter | -0.404 |
crow | -0.364 |
apped | -0.360 |
itte | -0.359 |
Token | a |
Token ID | 257 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
mess | +0.272 |
aj | +0.239 |
wra | +0.223 |
onna | +0.220 |
pic | +0.213 |
Neg logit contributions | |
aroo | -0.359 |
ter | -0.325 |
crow | -0.292 |
apped | -0.289 |
itte | -0.284 |
Token | big |
Token ID | 1263 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
mess | +0.102 |
aj | +0.094 |
wra | +0.085 |
onna | +0.084 |
pic | +0.083 |
Neg logit contributions | |
aroo | -0.147 |
ter | -0.132 |
crow | -0.120 |
apped | -0.117 |
member | -0.116 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
mess | +0.320 |
aj | +0.274 |
wra | +0.263 |
onna | +0.257 |
pic | +0.249 |
Neg logit contributions | |
aroo | -0.348 |
ter | -0.313 |
apped | -0.278 |
crow | -0.277 |
itte | -0.273 |
Token | . |
Token ID | 13 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
mess | +1.197 |
wra | +0.996 |
aj | +0.971 |
onna | +0.919 |
slippery | +0.908 |
Neg logit contributions | |
aroo | -1.233 |
ter | -1.041 |
crow | -0.980 |
apped | -0.968 |
itte | -0.967 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
mess | +0.079 |
aj | +0.072 |
onna | +0.067 |
wra | +0.067 |
pic | +0.065 |
Neg logit contributions | |
aroo | -0.091 |
ter | -0.082 |
crow | -0.071 |
apped | -0.071 |
member | -0.070 |
Token | was |
Token ID | 373 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
mess | +0.195 |
aj | +0.190 |
pic | +0.180 |
onna | +0.180 |
aman | +0.178 |
Neg logit contributions | |
aroo | -0.216 |
ter | -0.199 |
crow | -0.179 |
apped | -0.177 |
itte | -0.176 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
mess | +0.209 |
aj | +0.170 |
slippery | +0.162 |
wra | +0.161 |
onna | +0.159 |
Neg logit contributions | |
aroo | -0.247 |
ter | -0.219 |
crow | -0.201 |
ive | -0.195 |
apped | -0.195 |
Token | and |
Token ID | 290 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
aroo | +0.022 |
ter | +0.020 |
crow | +0.018 |
apped | +0.017 |
member | +0.017 |
Neg logit contributions | |
mess | -0.020 |
aj | -0.019 |
onna | -0.017 |
wra | -0.017 |
liv | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
mess | +0.218 |
aj | +0.213 |
onna | +0.203 |
liv | +0.199 |
aman | +0.199 |
Neg logit contributions | |
aroo | -0.193 |
ter | -0.176 |
apped | -0.153 |
crow | -0.152 |
itte | -0.150 |
Token | They |
Token ID | 1119 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
mess | +0.032 |
aj | +0.031 |
onna | +0.029 |
pic | +0.028 |
wra | +0.027 |
Neg logit contributions | |
aroo | -0.047 |
ter | -0.044 |
itte | -0.038 |
ovable | -0.038 |
member | -0.038 |
Token | look |
Token ID | 804 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
mess | +0.129 |
wra | +0.101 |
slippery | +0.100 |
aj | +0.098 |
onna | +0.096 |
Neg logit contributions | |
aroo | -0.166 |
ter | -0.150 |
apped | -0.134 |
crow | -0.130 |
ive | -0.129 |
Token | at |
Token ID | 379 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
mess | +0.462 |
aj | +0.414 |
wra | +0.395 |
onna | +0.387 |
pic | +0.382 |
Neg logit contributions | |
aroo | -0.345 |
ter | -0.298 |
crow | -0.258 |
apped | -0.251 |
itte | -0.244 |
Token | the |
Token ID | 262 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
aroo | +0.157 |
ter | +0.139 |
crow | +0.123 |
apped | +0.121 |
itte | +0.119 |
Neg logit contributions | |
mess | -0.163 |
aj | -0.145 |
wra | -0.138 |
onna | -0.136 |
pic | -0.133 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
mess | +0.062 |
aj | +0.052 |
wra | +0.051 |
onna | +0.048 |
pic | +0.047 |
Neg logit contributions | |
aroo | -0.071 |
ter | -0.063 |
apped | -0.057 |
crow | -0.057 |
itte | -0.056 |
Token | of |
Token ID | 286 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
mess | +1.130 |
aj | +0.995 |
wra | +0.945 |
onna | +0.926 |
pic | +0.896 |
Neg logit contributions | |
aroo | -1.264 |
ter | -1.124 |
crow | -1.010 |
apped | -0.992 |
itte | -0.979 |
Token | blocks |
Token ID | 7021 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
aroo | +0.540 |
ter | +0.488 |
crow | +0.426 |
apped | +0.421 |
member | +0.411 |
Neg logit contributions | |
mess | -0.498 |
aj | -0.460 |
onna | -0.425 |
wra | -0.421 |
liv | -0.413 |
Token | . |
Token ID | 13 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
mess | +0.340 |
aj | +0.316 |
pic | +0.290 |
icol | +0.290 |
onna | +0.290 |
Neg logit contributions | |
aroo | -0.343 |
ter | -0.312 |
crow | -0.270 |
apped | -0.269 |
member | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
mess | +0.100 |
aj | +0.090 |
onna | +0.084 |
wra | +0.084 |
pic | +0.082 |
Neg logit contributions | |
aroo | -0.119 |
ter | -0.107 |
crow | -0.094 |
apped | -0.093 |
itte | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
mess | +0.170 |
aj | +0.151 |
wra | +0.147 |
fault | +0.144 |
icol | +0.143 |
Neg logit contributions | |
aroo | -0.139 |
ter | -0.114 |
crow | -0.108 |
apped | -0.104 |
itte | -0.102 |
Token | he |
Token ID | 339 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
aroo | +0.188 |
ovable | +0.173 |
onel | +0.173 |
rest | +0.167 |
apped | +0.166 |
Neg logit contributions | |
mess | -0.272 |
scar | -0.233 |
wra | -0.231 |
snowball | -0.225 |
slippery | -0.224 |
Token | would |
Token ID | 561 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
mess | +0.066 |
aj | +0.055 |
onna | +0.052 |
wra | +0.051 |
slippery | +0.050 |
Neg logit contributions | |
aroo | -0.084 |
ter | -0.076 |
crow | -0.067 |
apped | -0.066 |
itte | -0.065 |
Token | make |
Token ID | 787 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
mess | +0.284 |
onna | +0.234 |
aj | +0.234 |
pic | +0.224 |
slippery | +0.222 |
Neg logit contributions | |
aroo | -0.306 |
ter | -0.276 |
crow | -0.249 |
apped | -0.246 |
itte | -0.240 |
Token | a |
Token ID | 257 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
mess | +0.038 |
aj | +0.035 |
wra | +0.032 |
onna | +0.032 |
pic | +0.031 |
Neg logit contributions | |
aroo | -0.043 |
ter | -0.038 |
crow | -0.034 |
apped | -0.034 |
itte | -0.033 |
Token | huge |
Token ID | 3236 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
mess | +0.094 |
aj | +0.086 |
wra | +0.080 |
onna | +0.078 |
liv | +0.077 |
Neg logit contributions | |
aroo | -0.129 |
ter | -0.116 |
crow | -0.104 |
apped | -0.103 |
member | -0.102 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
mess | +0.285 |
aj | +0.232 |
wra | +0.221 |
onna | +0.219 |
pic | +0.214 |
Neg logit contributions | |
aroo | -0.350 |
ter | -0.315 |
crow | -0.287 |
apped | -0.283 |
itte | -0.282 |
Token | in |
Token ID | 287 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
mess | +1.183 |
aj | +0.987 |
wra | +0.981 |
onna | +0.952 |
slippery | +0.916 |
Neg logit contributions | |
aroo | -1.233 |
ter | -1.050 |
crow | -0.981 |
apped | -0.965 |
itte | -0.957 |
Token | his |
Token ID | 465 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
aroo | +0.326 |
ter | +0.294 |
crow | +0.252 |
member | +0.247 |
person | +0.235 |
Neg logit contributions | |
aj | -0.395 |
mess | -0.378 |
zan | -0.357 |
icol | -0.356 |
liv | -0.354 |
Token | house |
Token ID | 2156 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
mess | +0.215 |
aj | +0.188 |
wra | +0.173 |
onna | +0.167 |
pic | +0.167 |
Neg logit contributions | |
aroo | -0.295 |
ter | -0.269 |
crow | -0.242 |
apped | -0.238 |
itte | -0.235 |
Token | , |
Token ID | 11 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
aroo | +0.049 |
ter | +0.044 |
crow | +0.039 |
apped | +0.038 |
itte | +0.038 |
Neg logit contributions | |
mess | -0.048 |
aj | -0.043 |
wra | -0.041 |
onna | -0.040 |
pic | -0.039 |
Token | but |
Token ID | 475 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
mess | +0.118 |
aj | +0.105 |
wra | +0.097 |
onna | +0.096 |
liv | +0.093 |
Neg logit contributions | |
aroo | -0.159 |
ter | -0.145 |
crow | -0.129 |
apped | -0.128 |
itte | -0.125 |
Token | he |
Token ID | 339 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
aroo | +0.124 |
ter | +0.111 |
apped | +0.103 |
crow | +0.101 |
itte | +0.101 |
Neg logit contributions | |
mess | -0.099 |
wra | -0.081 |
aj | -0.081 |
onna | -0.078 |
pic | -0.078 |
Token | couldn |
Token ID | 3521 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
mess | +0.107 |
aj | +0.085 |
wra | +0.084 |
onna | +0.081 |
slippery | +0.081 |
Neg logit contributions | |
aroo | -0.146 |
ter | -0.132 |
apped | -0.121 |
crow | -0.120 |
itte | -0.112 |
Token | 't |
Token ID | 470 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
mess | +0.128 |
onna | +0.103 |
aj | +0.099 |
wra | +0.099 |
liv | +0.095 |
Neg logit contributions | |
aroo | -0.220 |
ter | -0.204 |
apped | -0.188 |
crow | -0.183 |
sailors | -0.181 |
Token | clear |
Token ID | 1598 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
mess | +0.193 |
onna | +0.155 |
wob | +0.148 |
unw | +0.146 |
slippery | +0.141 |
Neg logit contributions | |
aroo | -0.248 |
apped | -0.239 |
ter | -0.226 |
itte | -0.209 |
crow | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
mess | +0.307 |
aj | +0.292 |
liv | +0.269 |
wra | +0.267 |
onna | +0.266 |
Neg logit contributions | |
aroo | -0.344 |
ter | -0.315 |
crow | -0.281 |
member | -0.262 |
apped | -0.261 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
mess | +0.024 |
aj | +0.020 |
wra | +0.020 |
onna | +0.019 |
fault | +0.019 |
Neg logit contributions | |
aroo | -0.031 |
ter | -0.028 |
apped | -0.026 |
crow | -0.025 |
itte | -0.025 |
Token | by |
Token ID | 416 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
mess | +1.176 |
wra | +1.000 |
aj | +0.990 |
onna | +0.946 |
slippery | +0.926 |
Neg logit contributions | |
aroo | -1.224 |
ter | -1.041 |
crow | -0.969 |
apped | -0.966 |
itte | -0.938 |
Token | himself |
Token ID | 2241 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
aroo | +0.059 |
ter | +0.053 |
crow | +0.047 |
apped | +0.045 |
itte | +0.045 |
Neg logit contributions | |
mess | -0.053 |
aj | -0.049 |
wra | -0.046 |
onna | -0.045 |
pic | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
mess | +0.089 |
aj | +0.079 |
wra | +0.074 |
onna | +0.073 |
fault | +0.071 |
Neg logit contributions | |
aroo | -0.096 |
ter | -0.085 |
crow | -0.076 |
apped | -0.075 |
itte | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
mess | +0.050 |
aj | +0.044 |
wra | +0.041 |
onna | +0.041 |
pic | +0.040 |
Neg logit contributions | |
aroo | -0.059 |
ter | -0.053 |
crow | -0.047 |
apped | -0.046 |
itte | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
mess | +0.094 |
aj | +0.085 |
onna | +0.079 |
wra | +0.079 |
pic | +0.077 |
Neg logit contributions | |
aroo | -0.101 |
ter | -0.091 |
crow | -0.080 |
apped | -0.080 |
itte | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
aroo | +0.031 |
ter | +0.027 |
apped | +0.025 |
crow | +0.024 |
itte | +0.024 |
Neg logit contributions | |
mess | -0.025 |
fun | -0.021 |
slippery | -0.021 |
aj | -0.020 |
die | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
mess | +0.092 |
aj | +0.079 |
wra | +0.074 |
onna | +0.073 |
pic | +0.072 |
Neg logit contributions | |
aroo | -0.116 |
ter | -0.103 |
apped | -0.096 |
crow | -0.095 |
itte | -0.094 |
Token | garden |
Token ID | 11376 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
mess | +0.026 |
aj | +0.021 |
wra | +0.021 |
slippery | +0.020 |
mistake | +0.020 |
Neg logit contributions | |
aroo | -0.022 |
ter | -0.019 |
apped | -0.018 |
ovable | -0.017 |
itte | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
mess | +0.162 |
aj | +0.137 |
wra | +0.131 |
onna | +0.127 |
pic | +0.124 |
Neg logit contributions | |
aroo | -0.232 |
ter | -0.208 |
crow | -0.189 |
apped | -0.186 |
itte | -0.185 |
Token | a |
Token ID | 257 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
mess | +0.213 |
aj | +0.202 |
wra | +0.188 |
icol | +0.185 |
fault | +0.182 |
Neg logit contributions | |
aroo | -0.212 |
ter | -0.194 |
crow | -0.166 |
apped | -0.164 |
member | -0.161 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
mess | +0.104 |
aj | +0.092 |
wra | +0.086 |
onna | +0.085 |
pic | +0.082 |
Neg logit contributions | |
aroo | -0.134 |
ter | -0.121 |
crow | -0.109 |
apped | -0.108 |
itte | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
mess | +1.105 |
aj | +0.910 |
wra | +0.909 |
onna | +0.863 |
slippery | +0.838 |
Neg logit contributions | |
aroo | -1.317 |
ter | -1.141 |
crow | -1.065 |
apped | -1.052 |
itte | -1.039 |
Token | Polly |
Token ID | 36898 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
mess | +0.070 |
aj | +0.066 |
onna | +0.062 |
pic | +0.060 |
wra | +0.059 |
Neg logit contributions | |
aroo | -0.094 |
ter | -0.085 |
member | -0.074 |
crow | -0.074 |
apped | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
mess | +0.259 |
aj | +0.230 |
wra | +0.216 |
onna | +0.213 |
pic | +0.207 |
Neg logit contributions | |
aroo | -0.301 |
ter | -0.270 |
crow | -0.241 |
apped | -0.238 |
itte | -0.234 |
Token | her |
Token ID | 607 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
mess | +0.216 |
aj | +0.174 |
wra | +0.171 |
onna | +0.164 |
pic | +0.163 |
Neg logit contributions | |
aroo | -0.376 |
ter | -0.339 |
apped | -0.311 |
crow | -0.308 |
itte | -0.303 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
mess | +0.271 |
aj | +0.237 |
wra | +0.226 |
fault | +0.223 |
pic | +0.211 |
Neg logit contributions | |
aroo | -0.213 |
ter | -0.187 |
crow | -0.173 |
itte | -0.158 |
apped | -0.156 |
Token | throwing |
Token ID | 9644 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
aj | +0.129 |
mess | +0.126 |
onna | +0.126 |
aman | +0.121 |
liv | +0.121 |
Neg logit contributions | |
aroo | -0.122 |
ter | -0.120 |
crow | -0.095 |
sailors | -0.091 |
al | -0.090 |
Token | blocks |
Token ID | 7021 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
mess | +0.355 |
aj | +0.324 |
onna | +0.298 |
wra | +0.297 |
pic | +0.288 |
Neg logit contributions | |
aroo | -0.413 |
ter | -0.372 |
crow | -0.335 |
apped | -0.326 |
itte | -0.316 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
mess | +0.334 |
aj | +0.299 |
wra | +0.285 |
onna | +0.281 |
pic | +0.273 |
Neg logit contributions | |
aroo | -0.298 |
ter | -0.263 |
crow | -0.232 |
apped | -0.228 |
itte | -0.224 |
Token | making |
Token ID | 1642 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
mess | +0.261 |
aj | +0.247 |
aman | +0.224 |
liv | +0.223 |
onna | +0.220 |
Neg logit contributions | |
aroo | -0.382 |
ter | -0.354 |
crow | -0.313 |
apped | -0.312 |
member | -0.301 |
Token | a |
Token ID | 257 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
aj | +0.299 |
mess | +0.298 |
liv | +0.274 |
onna | +0.270 |
aman | +0.268 |
Neg logit contributions | |
aroo | -0.332 |
ter | -0.306 |
crow | -0.266 |
apped | -0.265 |
sailors | -0.257 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
aj | +0.086 |
mess | +0.081 |
liv | +0.076 |
wra | +0.072 |
aman | +0.072 |
Neg logit contributions | |
aroo | -0.171 |
ter | -0.159 |
pilot | -0.146 |
crow | -0.144 |
apped | -0.143 |
Token | ? |
Token ID | 30 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
mess | +1.161 |
wra | +0.941 |
aj | +0.939 |
onna | +0.897 |
slippery | +0.864 |
Neg logit contributions | |
aroo | -1.292 |
ter | -1.092 |
crow | -1.026 |
itte | -1.000 |
apped | -0.996 |
Token | Why |
Token ID | 4162 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
mess | +0.241 |
aj | +0.219 |
onna | +0.210 |
wra | +0.204 |
fault | +0.195 |
Neg logit contributions | |
aroo | -0.327 |
ter | -0.288 |
crow | -0.257 |
pilot | -0.254 |
member | -0.250 |
Token | are |
Token ID | 389 |
Feature activation | +9.95e-03 |
Pos logit contributions | |
aroo | +0.212 |
ter | +0.194 |
apped | +0.165 |
itte | +0.165 |
crow | +0.165 |
Neg logit contributions | |
mess | -0.202 |
aj | -0.193 |
icol | -0.180 |
aman | -0.179 |
wra | -0.178 |
Token | you |
Token ID | 345 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
aroo | +0.021 |
ter | +0.018 |
crow | +0.017 |
apped | +0.016 |
ive | +0.016 |
Neg logit contributions | |
mess | -0.019 |
aj | -0.017 |
wra | -0.016 |
onna | -0.015 |
pic | -0.015 |
Token | being |
Token ID | 852 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
mess | +0.023 |
aj | +0.021 |
wra | +0.020 |
pic | +0.020 |
onna | +0.020 |
Neg logit contributions | |
aroo | -0.031 |
ter | -0.029 |
apped | -0.025 |
itte | -0.025 |
member | -0.025 |
Token | woke |
Token ID | 19092 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
aroo | +0.390 |
ter | +0.343 |
crow | +0.310 |
ative | +0.302 |
itte | +0.298 |
Neg logit contributions | |
mess | -0.379 |
aj | -0.336 |
onna | -0.310 |
wra | -0.304 |
pic | -0.298 |
Token | up |
Token ID | 510 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
mess | +0.155 |
aj | +0.140 |
wra | +0.133 |
onna | +0.130 |
pic | +0.127 |
Neg logit contributions | |
aroo | -0.203 |
ter | -0.187 |
crow | -0.163 |
apped | -0.163 |
itte | -0.159 |
Token | to |
Token ID | 284 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
mess | +0.281 |
aj | +0.245 |
wra | +0.230 |
onna | +0.227 |
pic | +0.220 |
Neg logit contributions | |
aroo | -0.367 |
ter | -0.330 |
crow | -0.298 |
apped | -0.293 |
itte | -0.290 |
Token | a |
Token ID | 257 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
mess | +0.270 |
pic | +0.214 |
fuss | +0.213 |
onna | +0.211 |
aj | +0.208 |
Neg logit contributions | |
aroo | -0.327 |
ter | -0.287 |
apped | -0.269 |
itte | -0.262 |
ovable | -0.257 |
Token | big |
Token ID | 1263 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
mess | +0.116 |
aj | +0.097 |
wra | +0.094 |
onna | +0.091 |
slippery | +0.089 |
Neg logit contributions | |
aroo | -0.137 |
ter | -0.124 |
apped | -0.114 |
crow | -0.111 |
itte | -0.109 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
mess | +0.331 |
aj | +0.263 |
wra | +0.259 |
onna | +0.251 |
fuss | +0.250 |
Neg logit contributions | |
aroo | -0.355 |
ter | -0.322 |
apped | -0.299 |
ovable | -0.289 |
itte | -0.288 |
Token | . |
Token ID | 13 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
mess | +1.206 |
wra | +1.007 |
aj | +0.987 |
onna | +0.938 |
slippery | +0.920 |
Neg logit contributions | |
aroo | -1.202 |
ter | -1.016 |
apped | -0.950 |
itte | -0.943 |
crow | -0.942 |
Token | The |
Token ID | 383 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
mess | +0.063 |
aj | +0.058 |
onna | +0.054 |
wra | +0.052 |
aman | +0.052 |
Neg logit contributions | |
aroo | -0.084 |
ter | -0.075 |
apped | -0.065 |
crow | -0.065 |
member | -0.065 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
aroo | +0.265 |
ter | +0.227 |
apped | +0.226 |
ovable | +0.211 |
crow | +0.210 |
Neg logit contributions | |
mess | -0.263 |
wra | -0.212 |
aj | -0.207 |
slippery | -0.199 |
mistake | -0.197 |
Token | in |
Token ID | 259 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
aroo | +0.183 |
ter | +0.167 |
ovable | +0.154 |
apped | +0.153 |
crow | +0.151 |
Neg logit contributions | |
mess | -0.304 |
wra | -0.254 |
mistake | -0.238 |
corn | -0.236 |
aj | -0.232 |
Token | oc |
Token ID | 420 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
aroo | +0.391 |
ter | +0.359 |
apped | +0.322 |
crow | +0.315 |
ovable | +0.313 |
Neg logit contributions | |
mess | -0.421 |
aj | -0.361 |
wra | -0.347 |
onna | -0.332 |
slippery | -0.325 |
Token | it |
Token ID | 340 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
mess | +0.277 |
aj | +0.243 |
wra | +0.225 |
onna | +0.222 |
pic | +0.215 |
Neg logit contributions | |
aroo | -0.403 |
ter | -0.365 |
crow | -0.330 |
apped | -0.326 |
itte | -0.321 |
Token | was |
Token ID | 373 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
mess | +0.260 |
aj | +0.225 |
wra | +0.210 |
onna | +0.206 |
pic | +0.199 |
Neg logit contributions | |
aroo | -0.392 |
ter | -0.356 |
crow | -0.323 |
apped | -0.319 |
itte | -0.314 |
Token | making |
Token ID | 1642 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
mess | +0.192 |
aj | +0.183 |
wra | +0.167 |
icol | +0.167 |
liv | +0.166 |
Neg logit contributions | |
aroo | -0.236 |
ter | -0.217 |
crow | -0.184 |
apped | -0.181 |
member | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
mess | +0.306 |
aj | +0.293 |
onna | +0.270 |
wra | +0.265 |
liv | +0.263 |
Neg logit contributions | |
aroo | -0.344 |
ter | -0.318 |
crow | -0.280 |
apped | -0.272 |
member | -0.263 |
Token | big |
Token ID | 1263 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
aj | +0.086 |
mess | +0.081 |
liv | +0.076 |
wra | +0.073 |
onna | +0.072 |
Neg logit contributions | |
aroo | -0.146 |
ter | -0.136 |
pilot | -0.123 |
crow | -0.119 |
hero | -0.119 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
aj | +0.207 |
mess | +0.192 |
liv | +0.178 |
onna | +0.172 |
wra | +0.172 |
Neg logit contributions | |
aroo | -0.429 |
ter | -0.401 |
crow | -0.356 |
pilot | -0.354 |
apped | -0.352 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
mess | +1.147 |
wra | +0.942 |
aj | +0.933 |
onna | +0.903 |
slippery | +0.873 |
Neg logit contributions | |
aroo | -1.267 |
ter | -1.074 |
crow | -1.014 |
apped | -1.009 |
itte | -0.994 |
Token | So |
Token ID | 1406 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
mess | +0.074 |
aj | +0.069 |
onna | +0.064 |
pic | +0.062 |
wra | +0.062 |
Neg logit contributions | |
aroo | -0.098 |
ter | -0.090 |
crow | -0.078 |
apped | -0.078 |
member | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
mess | +0.162 |
aj | +0.138 |
wra | +0.131 |
pic | +0.129 |
onna | +0.127 |
Neg logit contributions | |
aroo | -0.226 |
ter | -0.202 |
itte | -0.186 |
crow | -0.186 |
apped | -0.185 |
Token | he |
Token ID | 339 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
mess | +0.084 |
pic | +0.071 |
wra | +0.069 |
slippery | +0.065 |
scar | +0.064 |
Neg logit contributions | |
aroo | -0.144 |
apped | -0.129 |
ter | -0.129 |
itte | -0.128 |
ovable | -0.128 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
mess | +0.080 |
aj | +0.069 |
wra | +0.066 |
onna | +0.065 |
pic | +0.063 |
Neg logit contributions | |
aroo | -0.089 |
ter | -0.079 |
crow | -0.071 |
apped | -0.070 |
ovable | -0.068 |
Token | went |
Token ID | 1816 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
mess | +0.066 |
aj | +0.055 |
onna | +0.052 |
wra | +0.051 |
slippery | +0.050 |
Neg logit contributions | |
aroo | -0.084 |
ter | -0.076 |
crow | -0.067 |
apped | -0.066 |
itte | -0.065 |
Token | he |
Token ID | 339 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
aroo | +0.170 |
ter | +0.151 |
crow | +0.134 |
apped | +0.132 |
itte | +0.129 |
Neg logit contributions | |
mess | -0.172 |
aj | -0.154 |
wra | -0.146 |
onna | -0.143 |
pic | -0.141 |
Token | made |
Token ID | 925 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
mess | +0.091 |
aj | +0.078 |
onna | +0.073 |
slippery | +0.073 |
wra | +0.072 |
Neg logit contributions | |
aroo | -0.118 |
ter | -0.105 |
crow | -0.096 |
apped | -0.095 |
itte | -0.094 |
Token | a |
Token ID | 257 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
mess | +0.255 |
aj | +0.225 |
wra | +0.212 |
onna | +0.209 |
pic | +0.203 |
Neg logit contributions | |
aroo | -0.306 |
ter | -0.276 |
crow | -0.247 |
apped | -0.244 |
itte | -0.239 |
Token | huge |
Token ID | 3236 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
mess | +0.092 |
aj | +0.089 |
liv | +0.081 |
wra | +0.080 |
onna | +0.079 |
Neg logit contributions | |
aroo | -0.132 |
ter | -0.119 |
pilot | -0.106 |
member | -0.106 |
crow | -0.106 |
Token | mess |
Token ID | 2085 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
mess | +0.273 |
aj | +0.232 |
wra | +0.220 |
onna | +0.217 |
pic | +0.211 |
Neg logit contributions | |
aroo | -0.333 |
ter | -0.300 |
crow | -0.271 |
apped | -0.268 |
itte | -0.264 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
mess | +1.139 |
wra | +0.944 |
aj | +0.925 |
onna | +0.904 |
slippery | +0.870 |
Neg logit contributions | |
aroo | -1.265 |
ter | -1.077 |
crow | -1.027 |
apped | -1.006 |
itte | -1.002 |
Token | One |
Token ID | 1881 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
mess | +0.063 |
aj | +0.060 |
onna | +0.056 |
pic | +0.054 |
wra | +0.053 |
Neg logit contributions | |
aroo | -0.088 |
ter | -0.080 |
crow | -0.070 |
ovable | -0.069 |
apped | -0.069 |
Token | day |
Token ID | 1110 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
mess | +0.278 |
slippery | +0.234 |
aj | +0.225 |
steep | +0.222 |
onna | +0.217 |
Neg logit contributions | |
aroo | -0.255 |
ter | -0.235 |
apped | -0.209 |
ovable | -0.203 |
crow | -0.198 |
Token | his |
Token ID | 465 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
aroo | +0.122 |
ter | +0.111 |
ovable | +0.100 |
crow | +0.100 |
apped | +0.100 |
Neg logit contributions | |
mess | -0.084 |
wra | -0.071 |
aj | -0.071 |
onna | -0.068 |
pic | -0.067 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
mess | +0.234 |
aj | +0.211 |
fault | +0.197 |
wra | +0.193 |
pic | +0.192 |
Neg logit contributions | |
aroo | -0.221 |
ter | -0.199 |
crow | -0.189 |
apped | -0.173 |
itte | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
mess | +0.271 |
aj | +0.241 |
wra | +0.227 |
onna | +0.224 |
fault | +0.217 |
Neg logit contributions | |
aroo | -0.291 |
ter | -0.258 |
crow | -0.231 |
apped | -0.228 |
itte | -0.224 |
Token | That |
Token ID | 1320 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
aroo | +0.117 |
ter | +0.100 |
member | +0.098 |
pilot | +0.095 |
crow | +0.094 |
Neg logit contributions | |
aj | -0.089 |
onna | -0.085 |
mess | -0.083 |
pays | -0.083 |
icol | -0.082 |
Token | is |
Token ID | 318 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aroo | +0.178 |
ter | +0.167 |
crow | +0.151 |
member | +0.149 |
pilot | +0.146 |
Neg logit contributions | |
mess | -0.138 |
aj | -0.137 |
onna | -0.132 |
wra | -0.120 |
icol | -0.117 |
Token | very |
Token ID | 845 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
mess | +0.249 |
aj | +0.224 |
wra | +0.209 |
onna | +0.207 |
fault | +0.199 |
Neg logit contributions | |
aroo | -0.276 |
ter | -0.250 |
crow | -0.219 |
apped | -0.216 |
itte | -0.213 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
mess | +0.030 |
aj | +0.026 |
wra | +0.024 |
onna | +0.024 |
pic | +0.024 |
Neg logit contributions | |
aroo | -0.041 |
ter | -0.037 |
crow | -0.033 |
apped | -0.033 |
member | -0.032 |
Token | of |
Token ID | 286 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
aroo | +0.275 |
ter | +0.222 |
itte | +0.200 |
ovable | +0.184 |
apped | +0.184 |
Neg logit contributions | |
mess | -0.490 |
aj | -0.436 |
wra | -0.426 |
onna | -0.423 |
fault | -0.422 |
Token | you |
Token ID | 345 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
aroo | +0.795 |
apped | +0.695 |
ter | +0.692 |
itte | +0.663 |
ive | +0.642 |
Neg logit contributions | |
mess | -0.630 |
wra | -0.518 |
pic | -0.512 |
aj | -0.505 |
slippery | -0.504 |
Token | ." |
Token ID | 526 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
aroo | +0.156 |
ter | +0.130 |
crow | +0.130 |
itte | +0.123 |
apped | +0.122 |
Neg logit contributions | |
mess | -0.097 |
aj | -0.082 |
pays | -0.077 |
wra | -0.073 |
fault | -0.072 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
aroo | +0.162 |
ter | +0.147 |
apped | +0.132 |
crow | +0.132 |
itte | +0.127 |
Neg logit contributions | |
mess | -0.124 |
aj | -0.108 |
wra | -0.101 |
onna | -0.100 |
fault | -0.097 |
Token | my |
Token ID | 1820 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
mess | +0.025 |
pic | +0.022 |
wra | +0.022 |
onna | +0.022 |
icol | +0.022 |
Neg logit contributions | |
aroo | -0.030 |
ter | -0.029 |
member | -0.026 |
apped | -0.025 |
crow | -0.024 |
Token | carried |
Token ID | 5281 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
mess | +0.262 |
aj | +0.233 |
wra | +0.221 |
onna | +0.219 |
fault | +0.214 |
Neg logit contributions | |
aroo | -0.284 |
ter | -0.254 |
apped | -0.225 |
crow | -0.224 |
itte | -0.219 |
Token | art |
Token ID | 1242 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
mess | +0.247 |
aj | +0.205 |
wra | +0.202 |
onna | +0.201 |
fault | +0.198 |
Neg logit contributions | |
aroo | -0.218 |
ter | -0.190 |
apped | -0.177 |
itte | -0.176 |
ovable | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
mess | +0.261 |
wra | +0.206 |
aj | +0.200 |
onna | +0.194 |
pic | +0.192 |
Neg logit contributions | |
aroo | -0.311 |
ter | -0.277 |
apped | -0.258 |
itte | -0.252 |
ovable | -0.251 |
Token | It |
Token ID | 632 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
aroo | +0.006 |
ter | +0.006 |
member | +0.005 |
citizens | +0.005 |
pilot | +0.005 |
Neg logit contributions | |
mess | -0.004 |
aj | -0.004 |
onna | -0.004 |
wra | -0.004 |
fault | -0.004 |
Token | is |
Token ID | 318 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
aroo | +0.135 |
ter | +0.123 |
apped | +0.112 |
crow | +0.112 |
itte | +0.109 |
Neg logit contributions | |
mess | -0.079 |
aj | -0.066 |
wra | -0.062 |
onna | -0.061 |
fault | -0.058 |
Token | made |
Token ID | 925 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
mess | +0.279 |
aj | +0.254 |
wra | +0.232 |
onna | +0.228 |
liv | +0.227 |
Neg logit contributions | |
aroo | -0.389 |
ter | -0.358 |
crow | -0.317 |
apped | -0.311 |
itte | -0.307 |
Token | of |
Token ID | 286 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
mess | +0.219 |
aj | +0.190 |
wra | +0.184 |
onna | +0.184 |
pays | +0.183 |
Neg logit contributions | |
aroo | -0.120 |
ter | -0.096 |
itte | -0.083 |
crow | -0.083 |
ive | -0.078 |
Token | paper |
Token ID | 3348 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
aroo | +0.762 |
ter | +0.696 |
crow | +0.626 |
apped | +0.617 |
itte | +0.605 |
Neg logit contributions | |
mess | -0.529 |
aj | -0.470 |
wra | -0.432 |
onna | -0.429 |
liv | -0.414 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
mess | +0.446 |
aj | +0.383 |
wra | +0.361 |
onna | +0.350 |
pic | +0.340 |
Neg logit contributions | |
aroo | -0.581 |
ter | -0.514 |
crow | -0.468 |
apped | -0.467 |
itte | -0.464 |
Token | paint |
Token ID | 7521 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
mess | +0.164 |
aj | +0.144 |
wra | +0.131 |
onna | +0.131 |
liv | +0.126 |
Neg logit contributions | |
aroo | -0.260 |
ter | -0.238 |
crow | -0.215 |
apped | -0.213 |
itte | -0.208 |
Token | . |
Token ID | 13 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
aroo | +0.076 |
ter | +0.068 |
crow | +0.060 |
apped | +0.059 |
itte | +0.058 |
Neg logit contributions | |
mess | -0.076 |
aj | -0.068 |
wra | -0.065 |
onna | -0.064 |
pic | -0.062 |
Token | It |
Token ID | 632 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
aroo | +0.011 |
ter | +0.010 |
member | +0.009 |
pilot | +0.009 |
itte | +0.009 |
Neg logit contributions | |
mess | -0.008 |
aj | -0.008 |
onna | -0.008 |
pic | -0.008 |
wra | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
mess | +0.329 |
aj | +0.279 |
slippery | +0.278 |
pic | +0.268 |
fun | +0.267 |
Neg logit contributions | |
aroo | -0.345 |
ter | -0.326 |
crow | -0.277 |
apped | -0.274 |
itte | -0.268 |
Token | , |
Token ID | 11 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
aroo | +0.220 |
ter | +0.195 |
apped | +0.173 |
crow | +0.173 |
itte | +0.168 |
Neg logit contributions | |
mess | -0.212 |
aj | -0.188 |
wra | -0.178 |
onna | -0.176 |
pic | -0.172 |
Token | a |
Token ID | 257 |
Feature activation | +6.37e-03 |
Pos logit contributions | |
mess | +0.010 |
aj | +0.009 |
wra | +0.008 |
onna | +0.008 |
slippery | +0.008 |
Neg logit contributions | |
aroo | -0.013 |
ter | -0.012 |
crow | -0.011 |
ovable | -0.010 |
member | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
aroo | +0.014 |
ter | +0.013 |
apped | +0.012 |
crow | +0.012 |
onel | +0.012 |
Neg logit contributions | |
mess | -0.011 |
aj | -0.009 |
fun | -0.009 |
wra | -0.009 |
slippery | -0.009 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
aroo | +0.137 |
onel | +0.133 |
ovable | +0.133 |
rest | +0.123 |
ter | +0.119 |
Neg logit contributions | |
mess | -0.182 |
wra | -0.152 |
snowball | -0.151 |
slippery | -0.151 |
steep | -0.149 |
Token | named |
Token ID | 3706 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
aroo | +0.237 |
ter | +0.215 |
ative | +0.185 |
onel | +0.184 |
ovable | +0.180 |
Neg logit contributions | |
mess | -0.389 |
pic | -0.347 |
wra | -0.332 |
array | -0.319 |
icol | -0.317 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
aroo | +0.763 |
ter | +0.689 |
crow | +0.619 |
apped | +0.611 |
itte | +0.600 |
Neg logit contributions | |
mess | -0.601 |
aj | -0.530 |
wra | -0.496 |
onna | -0.489 |
pic | -0.475 |
Token | went |
Token ID | 1816 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
mess | +0.069 |
aj | +0.060 |
wra | +0.058 |
onna | +0.056 |
pic | +0.056 |
Neg logit contributions | |
aroo | -0.060 |
ter | -0.052 |
crow | -0.046 |
apped | -0.045 |
itte | -0.044 |
Token | for |
Token ID | 329 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
aroo | +0.354 |
ter | +0.324 |
crow | +0.298 |
itte | +0.290 |
apped | +0.289 |
Neg logit contributions | |
mess | -0.204 |
aj | -0.168 |
onna | -0.157 |
wra | -0.152 |
pic | -0.151 |
Token | a |
Token ID | 257 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
aroo | +0.053 |
ter | +0.048 |
crow | +0.040 |
apped | +0.039 |
itte | +0.039 |
Neg logit contributions | |
mess | -0.065 |
aj | -0.060 |
onna | -0.057 |
aman | -0.056 |
wra | -0.056 |
Token | walk |
Token ID | 2513 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
aroo | +0.017 |
ter | +0.015 |
crow | +0.014 |
member | +0.013 |
itte | +0.013 |
Neg logit contributions | |
mess | -0.016 |
aj | -0.015 |
wra | -0.014 |
onna | -0.014 |
fault | -0.013 |
Token | home |
Token ID | 1363 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
mess | +0.128 |
aj | +0.108 |
wra | +0.100 |
onna | +0.099 |
fault | +0.099 |
Neg logit contributions | |
aroo | -0.158 |
ter | -0.143 |
crow | -0.135 |
itte | -0.129 |
apped | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
aroo | +0.280 |
ter | +0.247 |
crow | +0.226 |
itte | +0.220 |
apped | +0.218 |
Neg logit contributions | |
mess | -0.245 |
aj | -0.210 |
wra | -0.201 |
onna | -0.200 |
slippery | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
aroo | +0.022 |
ter | +0.020 |
crow | +0.017 |
apped | +0.017 |
itte | +0.017 |
Neg logit contributions | |
mess | -0.019 |
aj | -0.017 |
onna | -0.016 |
wra | -0.016 |
pic | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
mess | +0.029 |
aj | +0.026 |
wra | +0.024 |
onna | +0.024 |
fault | +0.023 |
Neg logit contributions | |
aroo | -0.029 |
ter | -0.026 |
crow | -0.023 |
apped | -0.023 |
itte | -0.022 |
Token | L |
Token ID | 43 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
mess | +0.024 |
aj | +0.021 |
wra | +0.020 |
onna | +0.019 |
liv | +0.019 |
Neg logit contributions | |
aroo | -0.032 |
ter | -0.030 |
apped | -0.026 |
crow | -0.026 |
itte | -0.025 |
Token | ily |
Token ID | 813 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
mess | +0.212 |
aj | +0.196 |
wra | +0.189 |
onna | +0.187 |
fault | +0.185 |
Neg logit contributions | |
aroo | -0.075 |
ter | -0.057 |
crow | -0.043 |
apped | -0.041 |
member | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
aroo | +0.689 |
ter | +0.622 |
crow | +0.559 |
apped | +0.550 |
itte | +0.542 |
Neg logit contributions | |
mess | -0.545 |
aj | -0.479 |
wra | -0.449 |
onna | -0.441 |
pic | -0.429 |
Token | very |
Token ID | 845 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
mess | +0.095 |
aj | +0.080 |
slippery | +0.076 |
wra | +0.075 |
onna | +0.074 |
Neg logit contributions | |
aroo | -0.117 |
ter | -0.103 |
crow | -0.095 |
apped | -0.092 |
itte | -0.091 |
Token | brave |
Token ID | 14802 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
mess | +0.069 |
slippery | +0.057 |
aj | +0.057 |
onna | +0.054 |
steep | +0.052 |
Neg logit contributions | |
aroo | -0.080 |
ter | -0.074 |
crow | -0.067 |
ive | -0.064 |
member | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
aroo | +0.385 |
ter | +0.356 |
crow | +0.314 |
member | +0.307 |
apped | +0.304 |
Neg logit contributions | |
mess | -0.372 |
aj | -0.354 |
liv | -0.328 |
onna | -0.326 |
wra | -0.321 |
Token | smart |
Token ID | 4451 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
mess | +0.199 |
aj | +0.171 |
slippery | +0.170 |
wra | +0.170 |
onna | +0.166 |
Neg logit contributions | |
aroo | -0.201 |
ter | -0.180 |
crow | -0.162 |
apped | -0.155 |
member | -0.154 |
Token | the |
Token ID | 262 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
mess | +0.134 |
aj | +0.123 |
fault | +0.112 |
wra | +0.112 |
onna | +0.111 |
Neg logit contributions | |
aroo | -0.117 |
ter | -0.106 |
crow | -0.089 |
apped | -0.086 |
itte | -0.081 |
Token | ladder |
Token ID | 18002 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
aroo | +0.010 |
ter | +0.009 |
crow | +0.008 |
apped | +0.008 |
itte | +0.008 |
Neg logit contributions | |
mess | -0.009 |
aj | -0.008 |
wra | -0.007 |
onna | -0.007 |
pic | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
mess | +0.302 |
aj | +0.275 |
wra | +0.259 |
pic | +0.252 |
onna | +0.250 |
Neg logit contributions | |
aroo | -0.311 |
ter | -0.281 |
apped | -0.253 |
member | -0.246 |
crow | -0.246 |
Token | the |
Token ID | 262 |
Feature activation | +5.66e-03 |
Pos logit contributions | |
mess | +0.234 |
onna | +0.194 |
aj | +0.194 |
slippery | +0.190 |
wra | +0.189 |
Neg logit contributions | |
aroo | -0.254 |
ter | -0.226 |
apped | -0.213 |
crow | -0.207 |
itte | -0.203 |
Token | top |
Token ID | 1353 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
aroo | +0.013 |
apped | +0.012 |
ter | +0.012 |
ovable | +0.011 |
crow | +0.011 |
Neg logit contributions | |
mess | -0.010 |
slippery | -0.008 |
wra | -0.007 |
steep | -0.007 |
aj | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
mess | +0.440 |
aj | +0.414 |
wra | +0.399 |
onna | +0.393 |
fault | +0.389 |
Neg logit contributions | |
aroo | -0.134 |
ter | -0.102 |
crow | -0.075 |
apped | -0.069 |
member | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
aroo | +0.572 |
ter | +0.507 |
crow | +0.442 |
apped | +0.432 |
itte | +0.422 |
Neg logit contributions | |
mess | -0.629 |
aj | -0.575 |
wra | -0.537 |
onna | -0.533 |
fault | -0.519 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
aroo | +0.018 |
ter | +0.017 |
apped | +0.016 |
ovable | +0.015 |
crow | +0.015 |
Neg logit contributions | |
mess | -0.013 |
wra | -0.010 |
slippery | -0.010 |
aj | -0.010 |
steep | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aroo | +0.035 |
ter | +0.031 |
crow | +0.028 |
apped | +0.027 |
itte | +0.027 |
Neg logit contributions | |
mess | -0.029 |
aj | -0.026 |
wra | -0.024 |
onna | -0.024 |
pic | -0.023 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
mess | +0.223 |
aj | +0.190 |
wra | +0.184 |
onna | +0.180 |
slippery | +0.178 |
Neg logit contributions | |
aroo | -0.268 |
ter | -0.239 |
crow | -0.220 |
apped | -0.216 |
ovable | -0.214 |
Token | around |
Token ID | 1088 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
mess | +0.377 |
aj | +0.338 |
wra | +0.319 |
onna | +0.315 |
pic | +0.308 |
Neg logit contributions | |
aroo | -0.318 |
ter | -0.277 |
crow | -0.245 |
apped | -0.237 |
itte | -0.231 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
aroo | +0.137 |
ter | +0.125 |
apped | +0.111 |
crow | +0.111 |
member | +0.105 |
Neg logit contributions | |
mess | -0.182 |
aj | -0.171 |
onna | -0.164 |
fault | -0.155 |
liv | -0.155 |
Token | lot |
Token ID | 1256 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
aroo | +0.034 |
ter | +0.031 |
crow | +0.028 |
member | +0.027 |
pilot | +0.027 |
Neg logit contributions | |
mess | -0.026 |
aj | -0.025 |
wra | -0.023 |
onna | -0.023 |
fault | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
mess | +0.407 |
aj | +0.378 |
wra | +0.364 |
onna | +0.361 |
pic | +0.355 |
Neg logit contributions | |
aroo | -0.160 |
ter | -0.129 |
crow | -0.100 |
apped | -0.096 |
itte | -0.092 |
Token | trees |
Token ID | 7150 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
aroo | +0.787 |
ter | +0.713 |
crow | +0.670 |
member | +0.630 |
apped | +0.628 |
Neg logit contributions | |
mess | -0.540 |
aj | -0.515 |
onna | -0.491 |
liv | -0.460 |
fault | -0.453 |
Token | and |
Token ID | 290 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
aroo | +0.061 |
ter | +0.056 |
crow | +0.049 |
apped | +0.049 |
member | +0.048 |
Neg logit contributions | |
mess | -0.054 |
aj | -0.050 |
wra | -0.045 |
onna | -0.045 |
liv | -0.045 |
Token | flowers |
Token ID | 12734 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
mess | +0.161 |
aj | +0.140 |
wra | +0.138 |
pic | +0.134 |
slippery | +0.132 |
Neg logit contributions | |
aroo | -0.159 |
ter | -0.139 |
apped | -0.123 |
crow | -0.123 |
itte | -0.120 |
Token | along |
Token ID | 1863 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
aroo | +0.203 |
ter | +0.179 |
crow | +0.164 |
itte | +0.162 |
apped | +0.159 |
Neg logit contributions | |
mess | -0.173 |
aj | -0.147 |
wra | -0.145 |
onna | -0.142 |
pic | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
aroo | +0.591 |
ter | +0.522 |
itte | +0.470 |
crow | +0.457 |
apped | +0.455 |
Neg logit contributions | |
mess | -0.487 |
pic | -0.402 |
aj | -0.392 |
wra | -0.389 |
slippery | -0.386 |
Token | way |
Token ID | 835 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
aroo | +0.127 |
ter | +0.116 |
crow | +0.103 |
member | +0.099 |
pilot | +0.099 |
Neg logit contributions | |
mess | -0.103 |
aj | -0.097 |
onna | -0.089 |
wra | -0.088 |
liv | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
mess | +0.562 |
aj | +0.497 |
wra | +0.470 |
onna | +0.468 |
fault | +0.456 |
Neg logit contributions | |
aroo | -0.586 |
ter | -0.519 |
crow | -0.462 |
apped | -0.455 |
itte | -0.451 |
Token | As |
Token ID | 1081 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
aroo | +0.068 |
ter | +0.061 |
apped | +0.060 |
crow | +0.057 |
Everyone | +0.057 |
Neg logit contributions | |
mess | -0.076 |
aj | -0.066 |
wra | -0.065 |
fault | -0.062 |
onna | -0.061 |
Token | But |
Token ID | 887 |
Feature activation | -3.57e-04 |
Pos logit contributions | |
aroo | +0.083 |
ter | +0.070 |
member | +0.066 |
itte | +0.064 |
pilot | +0.063 |
Neg logit contributions | |
mess | -0.063 |
aj | -0.062 |
onna | -0.058 |
fault | -0.058 |
icol | -0.057 |
Token | you |
Token ID | 345 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
mess | +0.001 |
aj | +0.001 |
wra | +0.001 |
onna | +0.001 |
pic | +0.001 |
Neg logit contributions | |
aroo | -0.001 |
ter | -0.001 |
crow | -0.001 |
apped | -0.001 |
itte | -0.001 |
Token | have |
Token ID | 423 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
aroo | +0.110 |
ter | +0.096 |
crow | +0.083 |
apped | +0.081 |
itte | +0.079 |
Neg logit contributions | |
mess | -0.150 |
aj | -0.138 |
wra | -0.131 |
onna | -0.129 |
pic | -0.126 |
Token | to |
Token ID | 284 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
aroo | +0.309 |
ter | +0.282 |
crow | +0.253 |
apped | +0.251 |
member | +0.246 |
Neg logit contributions | |
mess | -0.242 |
aj | -0.214 |
wra | -0.200 |
icol | -0.195 |
liv | -0.194 |
Token | be |
Token ID | 307 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
mess | +0.126 |
aj | +0.117 |
wra | +0.110 |
onna | +0.107 |
pic | +0.106 |
Neg logit contributions | |
aroo | -0.108 |
ter | -0.097 |
crow | -0.085 |
apped | -0.081 |
member | -0.081 |
Token | patient |
Token ID | 5827 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
aroo | +0.008 |
ter | +0.007 |
crow | +0.006 |
apped | +0.006 |
itte | +0.006 |
Neg logit contributions | |
mess | -0.007 |
aj | -0.006 |
wra | -0.005 |
onna | -0.005 |
slippery | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
aroo | +0.228 |
ter | +0.206 |
crow | +0.183 |
apped | +0.181 |
itte | +0.176 |
Neg logit contributions | |
mess | -0.200 |
aj | -0.178 |
wra | -0.168 |
onna | -0.166 |
pic | -0.162 |
Token | Good |
Token ID | 4599 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
aroo | +0.087 |
ter | +0.074 |
member | +0.068 |
pilot | +0.066 |
apped | +0.065 |
Neg logit contributions | |
mess | -0.072 |
aj | -0.071 |
onna | -0.066 |
fault | -0.064 |
pic | -0.064 |
Token | things |
Token ID | 1243 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
aroo | +0.032 |
ter | +0.027 |
itte | +0.025 |
ovable | +0.025 |
crow | +0.024 |
Neg logit contributions | |
mess | -0.029 |
aj | -0.025 |
fuss | -0.023 |
wra | -0.022 |
mistake | -0.022 |
Token | take |
Token ID | 1011 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
aroo | +0.030 |
ter | +0.026 |
crow | +0.024 |
apped | +0.024 |
itte | +0.023 |
Neg logit contributions | |
mess | -0.029 |
wra | -0.024 |
aj | -0.024 |
onna | -0.023 |
slippery | -0.022 |
Token | time |
Token ID | 640 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
aroo | +0.204 |
ter | +0.183 |
crow | +0.163 |
apped | +0.161 |
itte | +0.158 |
Neg logit contributions | |
mess | -0.183 |
aj | -0.162 |
wra | -0.153 |
onna | -0.151 |
pic | -0.147 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
mess | +0.407 |
aj | +0.385 |
aman | +0.362 |
onna | +0.360 |
icol | +0.358 |
Neg logit contributions | |
aroo | -0.302 |
ter | -0.271 |
apped | -0.230 |
itte | -0.219 |
member | -0.217 |
Token | time |
Token ID | 640 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
wra | +0.003 |
mess | +0.003 |
equations | +0.003 |
drivers | +0.003 |
onna | +0.003 |
Neg logit contributions | |
aroo | -0.003 |
of | -0.003 |
member | -0.002 |
named | -0.002 |
itte | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
mess | +0.625 |
aj | +0.561 |
wra | +0.531 |
onna | +0.530 |
icol | +0.523 |
Neg logit contributions | |
aroo | -0.489 |
ter | -0.421 |
apped | -0.369 |
itte | -0.354 |
member | -0.347 |
Token | there |
Token ID | 612 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
mess | +0.020 |
aj | +0.018 |
wra | +0.017 |
onna | +0.017 |
slippery | +0.016 |
Neg logit contributions | |
aroo | -0.020 |
ter | -0.017 |
crow | -0.016 |
apped | -0.015 |
member | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
aroo | +0.143 |
ter | +0.126 |
apped | +0.112 |
crow | +0.111 |
member | +0.108 |
Neg logit contributions | |
mess | -0.152 |
aj | -0.147 |
onna | -0.132 |
wra | -0.132 |
icol | -0.131 |
Token | a |
Token ID | 257 |
Feature activation | +3.59e-04 |
Pos logit contributions | |
mess | +0.106 |
aj | +0.097 |
onna | +0.092 |
wra | +0.090 |
fuss | +0.087 |
Neg logit contributions | |
aroo | -0.094 |
ter | -0.084 |
apped | -0.073 |
itte | -0.071 |
crow | -0.071 |
Token | little |
Token ID | 1310 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
aroo | +0.001 |
ter | +0.001 |
crow | +0.001 |
apped | +0.001 |
ovable | +0.001 |
Neg logit contributions | |
mess | -0.001 |
aj | -0.001 |
wra | -0.001 |
pic | -0.001 |
slippery | -0.001 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
aroo | +0.120 |
ovable | +0.102 |
onel | +0.100 |
apped | +0.099 |
ter | +0.099 |
Neg logit contributions | |
mess | -0.189 |
wra | -0.160 |
scar | -0.157 |
slippery | -0.155 |
aj | -0.150 |
Token | named |
Token ID | 3706 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
aroo | +0.353 |
ter | +0.306 |
apped | +0.259 |
onel | +0.258 |
folk | +0.256 |
Neg logit contributions | |
mess | -0.614 |
aj | -0.549 |
pic | -0.524 |
onna | -0.516 |
wra | -0.515 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
aroo | +0.688 |
ter | +0.630 |
apped | +0.554 |
crow | +0.549 |
itte | +0.545 |
Neg logit contributions | |
mess | -0.609 |
aj | -0.550 |
wra | -0.521 |
fault | -0.508 |
onna | -0.508 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
mess | +0.094 |
aj | +0.082 |
wra | +0.078 |
onna | +0.077 |
pic | +0.075 |
Neg logit contributions | |
aroo | -0.099 |
ter | -0.088 |
crow | -0.079 |
apped | -0.078 |
itte | -0.076 |
Token | friends |
Token ID | 2460 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
mess | +0.075 |
aj | +0.066 |
fault | +0.061 |
onna | +0.060 |
wra | +0.060 |
Neg logit contributions | |
aroo | -0.085 |
ter | -0.075 |
crow | -0.069 |
itte | -0.067 |
apped | -0.066 |
Token | or |
Token ID | 393 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
aroo | +0.705 |
ter | +0.608 |
crow | +0.569 |
apped | +0.563 |
itte | +0.558 |
Neg logit contributions | |
mess | -0.561 |
aj | -0.453 |
onna | -0.433 |
wra | -0.432 |
fuss | -0.422 |
Token | playing |
Token ID | 2712 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
mess | +0.095 |
aj | +0.081 |
wra | +0.077 |
onna | +0.076 |
pic | +0.075 |
Neg logit contributions | |
aroo | -0.108 |
ter | -0.095 |
apped | -0.086 |
crow | -0.086 |
itte | -0.084 |
Token | games |
Token ID | 1830 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
aroo | +0.125 |
ter | +0.109 |
apped | +0.098 |
itte | +0.098 |
crow | +0.097 |
Neg logit contributions | |
mess | -0.121 |
aj | -0.101 |
wra | -0.100 |
pic | -0.097 |
slippery | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
mess | +0.052 |
aj | +0.045 |
wra | +0.043 |
onna | +0.042 |
pic | +0.041 |
Neg logit contributions | |
aroo | -0.059 |
ter | -0.052 |
crow | -0.047 |
apped | -0.047 |
itte | -0.046 |
Token | She |
Token ID | 1375 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
aroo | +0.109 |
ter | +0.098 |
crow | +0.087 |
apped | +0.086 |
itte | +0.084 |
Neg logit contributions | |
mess | -0.090 |
aj | -0.081 |
wra | -0.075 |
onna | -0.075 |
pic | -0.073 |
Token | would |
Token ID | 561 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
aroo | +0.053 |
ter | +0.048 |
crow | +0.043 |
apped | +0.042 |
itte | +0.041 |
Neg logit contributions | |
mess | -0.042 |
aj | -0.036 |
wra | -0.034 |
onna | -0.033 |
pic | -0.033 |
Token | always |
Token ID | 1464 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
mess | +0.147 |
aj | +0.126 |
onna | +0.123 |
wra | +0.120 |
pic | +0.118 |
Neg logit contributions | |
aroo | -0.158 |
ter | -0.142 |
crow | -0.126 |
apped | -0.124 |
itte | -0.122 |
Token | do |
Token ID | 466 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
aroo | +0.102 |
ter | +0.091 |
crow | +0.080 |
apped | +0.079 |
itte | +0.078 |
Neg logit contributions | |
mess | -0.104 |
aj | -0.092 |
wra | -0.087 |
onna | -0.086 |
pic | -0.084 |
Token | her |
Token ID | 607 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
aroo | +0.184 |
ter | +0.164 |
crow | +0.152 |
member | +0.147 |
apped | +0.146 |
Neg logit contributions | |
mess | -0.165 |
aj | -0.160 |
wra | -0.147 |
onna | -0.146 |
icol | -0.142 |
Token | best |
Token ID | 1266 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
mess | +0.075 |
aj | +0.068 |
wra | +0.065 |
onna | +0.064 |
aman | +0.062 |
Neg logit contributions | |
aroo | -0.069 |
ter | -0.061 |
crow | -0.053 |
apped | -0.053 |
member | -0.052 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
aroo | +0.017 |
ter | +0.015 |
crow | +0.014 |
apped | +0.014 |
itte | +0.013 |
Neg logit contributions | |
mess | -0.017 |
aj | -0.015 |
wra | -0.014 |
slippery | -0.013 |
onna | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
aroo | +0.031 |
ter | +0.027 |
crow | +0.025 |
apped | +0.024 |
itte | +0.024 |
Neg logit contributions | |
mess | -0.029 |
aj | -0.025 |
onna | -0.024 |
wra | -0.024 |
fault | -0.023 |
Token | He |
Token ID | 679 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
aroo | +0.085 |
ter | +0.076 |
crow | +0.068 |
apped | +0.067 |
itte | +0.064 |
Neg logit contributions | |
mess | -0.101 |
aj | -0.090 |
wra | -0.087 |
onna | -0.084 |
aman | -0.084 |
Token | does |
Token ID | 857 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
aroo | +0.075 |
ter | +0.067 |
crow | +0.063 |
itte | +0.061 |
ovable | +0.060 |
Neg logit contributions | |
mess | -0.056 |
aj | -0.051 |
onna | -0.048 |
aman | -0.048 |
liv | -0.048 |
Token | not |
Token ID | 407 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
mess | +0.269 |
aj | +0.263 |
aman | +0.255 |
wra | +0.253 |
pic | +0.239 |
Neg logit contributions | |
aroo | -0.538 |
ter | -0.487 |
pilot | -0.439 |
hero | -0.429 |
crow | -0.428 |
Token | see |
Token ID | 766 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
mess | +0.486 |
onna | +0.387 |
slippery | +0.381 |
fuss | +0.380 |
aj | +0.371 |
Neg logit contributions | |
aroo | -0.541 |
ter | -0.480 |
apped | -0.461 |
itte | -0.433 |
ovable | -0.417 |
Token | the |
Token ID | 262 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
aroo | +0.274 |
ter | +0.242 |
apped | +0.219 |
crow | +0.217 |
itte | +0.216 |
Neg logit contributions | |
mess | -0.238 |
aj | -0.204 |
wra | -0.195 |
onna | -0.190 |
fault | -0.189 |
Token | rock |
Token ID | 3881 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
aroo | +0.158 |
ter | +0.143 |
crow | +0.128 |
apped | +0.126 |
itte | +0.124 |
Neg logit contributions | |
mess | -0.123 |
aj | -0.109 |
wra | -0.102 |
onna | -0.101 |
pic | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
aroo | +0.097 |
ter | +0.086 |
apped | +0.080 |
itte | +0.079 |
crow | +0.078 |
Neg logit contributions | |
mess | -0.089 |
aj | -0.072 |
wra | -0.072 |
onna | -0.070 |
slippery | -0.070 |
Token | The |
Token ID | 383 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
aroo | +0.090 |
ter | +0.081 |
crow | +0.072 |
apped | +0.071 |
itte | +0.068 |
Neg logit contributions | |
mess | -0.104 |
aj | -0.092 |
wra | -0.089 |
onna | -0.086 |
aman | -0.085 |
Token | rock |
Token ID | 3881 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
aroo | +0.481 |
ter | +0.435 |
crow | +0.388 |
apped | +0.388 |
itte | +0.382 |
Neg logit contributions | |
mess | -0.396 |
aj | -0.333 |
wra | -0.321 |
onna | -0.309 |
slippery | -0.309 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
mess | +0.065 |
wra | +0.053 |
onna | +0.052 |
aj | +0.052 |
fuss | +0.052 |
Neg logit contributions | |
aroo | -0.046 |
ter | -0.040 |
apped | -0.036 |
itte | -0.035 |
ovable | -0.035 |
Token | calling |
Token ID | 4585 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
aroo | +0.365 |
ter | +0.327 |
apped | +0.312 |
itte | +0.300 |
ovable | +0.293 |
Neg logit contributions | |
mess | -0.268 |
aj | -0.213 |
wra | -0.206 |
fuss | -0.203 |
aman | -0.202 |
Token | his |
Token ID | 465 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
mess | +0.249 |
onna | +0.208 |
wra | +0.206 |
aj | +0.205 |
icol | +0.198 |
Neg logit contributions | |
aroo | -0.304 |
ter | -0.269 |
itte | -0.243 |
apped | -0.240 |
member | -0.235 |
Token | name |
Token ID | 1438 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
mess | +0.139 |
aj | +0.126 |
fault | +0.116 |
onna | +0.115 |
wra | +0.114 |
Neg logit contributions | |
aroo | -0.126 |
ter | -0.110 |
crow | -0.098 |
apped | -0.094 |
itte | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
aroo | +0.271 |
ter | +0.238 |
itte | +0.218 |
crow | +0.216 |
apped | +0.215 |
Neg logit contributions | |
mess | -0.200 |
wra | -0.167 |
aj | -0.163 |
aman | -0.157 |
onna | -0.156 |
Token | |
Token ID | 220 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
aroo | +0.037 |
ter | +0.033 |
crow | +0.029 |
apped | +0.029 |
itte | +0.028 |
Neg logit contributions | |
mess | -0.037 |
aj | -0.033 |
wra | -0.031 |
onna | -0.031 |
pic | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -4.12e-04 |
Pos logit contributions | |
mess | +0.273 |
aj | +0.242 |
wra | +0.232 |
onna | +0.225 |
pic | +0.223 |
Neg logit contributions | |
aroo | -0.266 |
ter | -0.236 |
crow | -0.210 |
apped | -0.209 |
itte | -0.204 |
Token |
|
Token ID | 198 |
Feature activation | +6.23e-04 |
Pos logit contributions | |
mess | +0.001 |
aj | +0.001 |
wra | +0.001 |
fault | +0.001 |
onna | +0.001 |
Neg logit contributions | |
aroo | -0.001 |
ter | -0.001 |
crow | -0.001 |
apped | -0.001 |
itte | -0.001 |
Token | ' |
Token ID | 6 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
aroo | +0.001 |
ter | +0.001 |
apped | +0.001 |
crow | +0.001 |
ovable | +0.001 |
Neg logit contributions | |
mess | -0.001 |
aj | -0.001 |
wra | -0.001 |
onna | -0.001 |
liv | -0.001 |
Token | Set |
Token ID | 7248 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
aroo | +0.506 |
ovable | +0.485 |
onel | +0.477 |
ter | +0.471 |
apped | +0.460 |
Neg logit contributions | |
aman | -0.286 |
liv | -0.284 |
Lisa | -0.284 |
aj | -0.272 |
mess | -0.257 |
Token | o |
Token ID | 78 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
aroo | +0.071 |
ter | +0.064 |
crow | +0.059 |
apped | +0.059 |
ovable | +0.057 |
Neg logit contributions | |
mess | -0.057 |
aj | -0.055 |
onna | -0.050 |
pays | -0.048 |
die | -0.048 |
Token | called |
Token ID | 1444 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
aroo | +0.337 |
ter | +0.294 |
folk | +0.264 |
onel | +0.262 |
apped | +0.256 |
Neg logit contributions | |
mess | -0.519 |
aj | -0.455 |
ine | -0.443 |
pic | -0.436 |
onna | -0.430 |
Token | Ell |
Token ID | 7122 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
aroo | +0.106 |
ter | +0.097 |
crow | +0.088 |
apped | +0.087 |
pilot | +0.086 |
Neg logit contributions | |
mess | -0.060 |
aj | -0.053 |
onna | -0.050 |
wra | -0.048 |
pic | -0.047 |
Token | a |
Token ID | 64 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
aroo | +0.056 |
crow | +0.048 |
ter | +0.047 |
Everyone | +0.044 |
ive | +0.042 |
Neg logit contributions | |
mess | -0.041 |
aj | -0.038 |
onna | -0.034 |
fault | -0.033 |
wra | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
aroo | +0.118 |
ter | +0.106 |
crow | +0.103 |
folk | +0.102 |
onel | +0.102 |
Neg logit contributions | |
mess | -0.055 |
aj | -0.046 |
mistake | -0.042 |
ine | -0.040 |
wra | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
mess | +0.024 |
onna | +0.022 |
aj | +0.022 |
wra | +0.021 |
pic | +0.019 |
Neg logit contributions | |
aroo | -0.036 |
ter | -0.031 |
crow | -0.029 |
member | -0.028 |
sailors | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
mess | +0.059 |
aj | +0.052 |
wra | +0.050 |
onna | +0.050 |
pic | +0.049 |
Neg logit contributions | |
aroo | -0.052 |
ter | -0.047 |
crow | -0.041 |
apped | -0.040 |
ive | -0.039 |
Token | three |
Token ID | 1115 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
mess | +0.102 |
slippery | +0.081 |
aj | +0.079 |
pic | +0.079 |
wra | +0.078 |
Neg logit contributions | |
aroo | -0.172 |
ter | -0.149 |
crow | -0.148 |
ive | -0.145 |
member | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
aroo | +0.586 |
ter | +0.537 |
apped | +0.479 |
crow | +0.477 |
itte | +0.463 |
Neg logit contributions | |
mess | -0.389 |
aj | -0.330 |
wra | -0.310 |
pic | -0.294 |
slippery | -0.285 |
Token | liked |
Token ID | 8288 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
mess | +0.237 |
aj | +0.207 |
wra | +0.203 |
liv | +0.202 |
slippery | +0.198 |
Neg logit contributions | |
aroo | -0.242 |
ter | -0.211 |
crow | -0.203 |
ive | -0.199 |
member | -0.185 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aroo | +0.184 |
ter | +0.167 |
crow | +0.146 |
apped | +0.146 |
member | +0.143 |
Neg logit contributions | |
mess | -0.146 |
aj | -0.133 |
wra | -0.121 |
onna | -0.120 |
liv | -0.119 |
Token | do |
Token ID | 466 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
mess | +0.200 |
onna | +0.163 |
pic | +0.163 |
aj | +0.160 |
slippery | +0.156 |
Neg logit contributions | |
aroo | -0.238 |
ter | -0.218 |
apped | -0.196 |
crow | -0.193 |
itte | -0.188 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
mess | +0.254 |
aj | +0.245 |
onna | +0.231 |
aman | +0.227 |
liv | +0.224 |
Neg logit contributions | |
aroo | -0.505 |
ter | -0.469 |
pilot | -0.412 |
sailors | -0.409 |
crow | -0.407 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
aroo | +0.145 |
ter | +0.129 |
itte | +0.112 |
crow | +0.112 |
apped | +0.112 |
Neg logit contributions | |
mess | -0.122 |
aj | -0.109 |
wra | -0.103 |
pic | -0.102 |
onna | -0.102 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
mess | +0.170 |
aj | +0.143 |
wra | +0.131 |
onna | +0.128 |
pic | +0.123 |
Neg logit contributions | |
aroo | -0.340 |
ter | -0.312 |
crow | -0.286 |
apped | -0.283 |
itte | -0.279 |
Token | a |
Token ID | 257 |
Feature activation | -6.85e-03 |
Pos logit contributions | |
mess | +0.407 |
aj | +0.382 |
onna | +0.355 |
wra | +0.353 |
aman | +0.352 |
Neg logit contributions | |
aroo | -0.316 |
ter | -0.282 |
apped | -0.236 |
itte | -0.231 |
crow | -0.231 |
Token | time |
Token ID | 640 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
mess | +0.011 |
wra | +0.011 |
onna | +0.010 |
aj | +0.010 |
idents | +0.010 |
Neg logit contributions | |
aroo | -0.013 |
member | -0.011 |
itte | -0.011 |
named | -0.011 |
hero | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
mess | +0.616 |
aj | +0.550 |
wra | +0.523 |
onna | +0.512 |
icol | +0.507 |
Neg logit contributions | |
aroo | -0.518 |
ter | -0.448 |
apped | -0.389 |
crow | -0.381 |
itte | -0.377 |
Token | there |
Token ID | 612 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
mess | +0.038 |
aj | +0.034 |
slippery | +0.032 |
onna | +0.032 |
wra | +0.032 |
Neg logit contributions | |
aroo | -0.041 |
ter | -0.036 |
crow | -0.034 |
member | -0.032 |
ive | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
aroo | +0.147 |
ter | +0.131 |
crow | +0.117 |
apped | +0.116 |
itte | +0.112 |
Neg logit contributions | |
mess | -0.136 |
aj | -0.128 |
wra | -0.116 |
onna | -0.115 |
icol | -0.113 |
Token | a |
Token ID | 257 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
mess | +0.113 |
aj | +0.102 |
onna | +0.095 |
wra | +0.095 |
fault | +0.092 |
Neg logit contributions | |
aroo | -0.111 |
ter | -0.100 |
crow | -0.087 |
apped | -0.087 |
itte | -0.085 |
Token | little |
Token ID | 1310 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
mess | +0.008 |
aj | +0.006 |
wra | +0.006 |
slippery | +0.006 |
pic | +0.006 |
Neg logit contributions | |
aroo | -0.009 |
ter | -0.008 |
crow | -0.007 |
apped | -0.007 |
ovable | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
aroo | +0.111 |
ovable | +0.098 |
onel | +0.097 |
apped | +0.096 |
rest | +0.092 |
Neg logit contributions | |
mess | -0.169 |
wra | -0.142 |
slippery | -0.140 |
scar | -0.140 |
snowball | -0.135 |
Token | little |
Token ID | 1310 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
mess | +0.092 |
aj | +0.074 |
wra | +0.072 |
slippery | +0.071 |
pic | +0.070 |
Neg logit contributions | |
aroo | -0.102 |
ter | -0.091 |
crow | -0.088 |
apped | -0.086 |
ovable | -0.082 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
aroo | +0.047 |
ovable | +0.041 |
onel | +0.041 |
apped | +0.040 |
rest | +0.039 |
Neg logit contributions | |
mess | -0.071 |
wra | -0.060 |
scar | -0.059 |
slippery | -0.059 |
snowball | -0.057 |
Token | named |
Token ID | 3706 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
aroo | +0.306 |
ter | +0.267 |
onel | +0.238 |
folk | +0.237 |
apped | +0.232 |
Neg logit contributions | |
mess | -0.465 |
aj | -0.411 |
ine | -0.404 |
pic | -0.399 |
onna | -0.390 |
Token | Lily |
Token ID | 20037 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
aroo | +0.627 |
ter | +0.568 |
crow | +0.506 |
apped | +0.503 |
itte | +0.497 |
Neg logit contributions | |
mess | -0.518 |
aj | -0.460 |
wra | -0.435 |
onna | -0.423 |
fault | -0.417 |
Token | . |
Token ID | 13 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
mess | +0.182 |
aj | +0.157 |
wra | +0.150 |
onna | +0.148 |
pic | +0.143 |
Neg logit contributions | |
aroo | -0.201 |
ter | -0.177 |
crow | -0.159 |
apped | -0.158 |
itte | -0.154 |
Token | She |
Token ID | 1375 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
mess | +0.073 |
aj | +0.065 |
wra | +0.062 |
onna | +0.060 |
fault | +0.060 |
Neg logit contributions | |
aroo | -0.070 |
ter | -0.063 |
apped | -0.056 |
crow | -0.055 |
itte | -0.053 |
Token | loved |
Token ID | 6151 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
mess | +0.091 |
aj | +0.080 |
wra | +0.077 |
onna | +0.076 |
pic | +0.074 |
Neg logit contributions | |
aroo | -0.077 |
ter | -0.069 |
crow | -0.061 |
apped | -0.059 |
ive | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
aroo | +0.214 |
ter | +0.193 |
crow | +0.170 |
apped | +0.168 |
member | +0.166 |
Neg logit contributions | |
mess | -0.172 |
aj | -0.157 |
wra | -0.143 |
onna | -0.142 |
liv | -0.141 |
Token | eat |
Token ID | 4483 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
mess | +0.247 |
aj | +0.212 |
onna | +0.210 |
pic | +0.209 |
wra | +0.199 |
Neg logit contributions | |
aroo | -0.273 |
ter | -0.253 |
crow | -0.226 |
apped | -0.223 |
itte | -0.217 |
Token | candy |
Token ID | 18550 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
aj | +0.081 |
fault | +0.081 |
mess | +0.081 |
liv | +0.079 |
onna | +0.074 |
Neg logit contributions | |
aroo | -0.094 |
ter | -0.089 |
crow | -0.075 |
ot | -0.071 |
of | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
mess | +0.458 |
aj | +0.439 |
fault | +0.415 |
icol | +0.413 |
onna | +0.404 |
Neg logit contributions | |
aroo | -0.346 |
ter | -0.317 |
member | -0.261 |
apped | -0.256 |
crow | -0.256 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
mess | +0.216 |
onna | +0.214 |
aj | +0.193 |
gh | +0.189 |
wra | +0.183 |
Neg logit contributions | |
aroo | -0.434 |
ter | -0.415 |
itte | -0.376 |
crow | -0.373 |
member | -0.371 |
Token | " |
Token ID | 366 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
mess | +0.032 |
onna | +0.030 |
aj | +0.028 |
wra | +0.027 |
pays | +0.024 |
Neg logit contributions | |
aroo | -0.058 |
ter | -0.053 |
crow | -0.051 |
ovable | -0.051 |
itte | -0.050 |
Token | My |
Token ID | 3666 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
aroo | +0.008 |
ter | +0.007 |
ovable | +0.006 |
itte | +0.006 |
onel | +0.006 |
Neg logit contributions | |
mess | -0.008 |
wra | -0.007 |
aj | -0.007 |
liv | -0.007 |
die | -0.007 |
Token | name |
Token ID | 1438 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
aroo | +0.314 |
ter | +0.275 |
itte | +0.249 |
crow | +0.247 |
ovable | +0.236 |
Neg logit contributions | |
mess | -0.347 |
aj | -0.316 |
fault | -0.298 |
wra | -0.287 |
pic | -0.280 |
Token | is |
Token ID | 318 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
aroo | +0.356 |
ter | +0.327 |
itte | +0.308 |
crow | +0.304 |
apped | +0.303 |
Neg logit contributions | |
mess | -0.135 |
wra | -0.100 |
aj | -0.098 |
onna | -0.088 |
pays | -0.088 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
mess | +0.211 |
aj | +0.188 |
pic | +0.177 |
wra | +0.165 |
liv | +0.165 |
Neg logit contributions | |
aroo | -0.439 |
ter | -0.399 |
apped | -0.377 |
crow | -0.370 |
ive | -0.369 |
Token | . |
Token ID | 13 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
mess | +0.362 |
aj | +0.321 |
wra | +0.300 |
onna | +0.294 |
fault | +0.289 |
Neg logit contributions | |
aroo | -0.426 |
ter | -0.374 |
crow | -0.342 |
apped | -0.337 |
itte | -0.335 |
Token | And |
Token ID | 843 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
aroo | +0.009 |
ter | +0.008 |
member | +0.007 |
itte | +0.007 |
onel | +0.007 |
Neg logit contributions | |
onna | -0.006 |
aj | -0.006 |
mess | -0.006 |
icol | -0.006 |
fault | -0.006 |
Token | this |
Token ID | 428 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
aroo | +0.208 |
ter | +0.189 |
apped | +0.178 |
crow | +0.174 |
itte | +0.171 |
Neg logit contributions | |
mess | -0.178 |
aj | -0.159 |
wra | -0.154 |
pic | -0.151 |
onna | -0.150 |
Token | is |
Token ID | 318 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
mess | +0.085 |
aj | +0.074 |
wra | +0.068 |
onna | +0.067 |
pic | +0.063 |
Neg logit contributions | |
aroo | -0.153 |
ter | -0.139 |
crow | -0.128 |
apped | -0.125 |
member | -0.123 |
Token | Spot |
Token ID | 15899 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
mess | +0.288 |
aj | +0.254 |
wra | +0.238 |
onna | +0.233 |
pic | +0.225 |
Neg logit contributions | |
aroo | -0.384 |
ter | -0.349 |
crow | -0.312 |
apped | -0.307 |
itte | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
mess | +0.219 |
aj | +0.208 |
icol | +0.196 |
wra | +0.194 |
liv | +0.192 |
Neg logit contributions | |
aroo | -0.179 |
ter | -0.159 |
apped | -0.139 |
member | -0.138 |
crow | -0.136 |
Token | They |
Token ID | 1119 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
aroo | +0.029 |
ter | +0.026 |
crow | +0.023 |
itte | +0.022 |
member | +0.022 |
Neg logit contributions | |
mess | -0.023 |
aj | -0.021 |
onna | -0.019 |
wra | -0.019 |
pic | -0.019 |
Token | had |
Token ID | 550 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
mess | +0.055 |
wra | +0.046 |
onna | +0.043 |
aj | +0.042 |
slippery | +0.041 |
Neg logit contributions | |
aroo | -0.077 |
ter | -0.068 |
crow | -0.065 |
ive | -0.061 |
apped | -0.060 |
Token | completed |
Token ID | 5668 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
mess | +0.052 |
aj | +0.049 |
aman | +0.045 |
icol | +0.045 |
liv | +0.044 |
Neg logit contributions | |
aroo | -0.058 |
ter | -0.055 |
apped | -0.049 |
member | -0.048 |
sailors | -0.047 |
Token | their |
Token ID | 511 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
aj | +0.176 |
mess | +0.173 |
liv | +0.165 |
icol | +0.163 |
array | +0.158 |
Neg logit contributions | |
aroo | -0.139 |
ter | -0.130 |
apped | -0.109 |
sailors | -0.108 |
member | -0.107 |
Token | fun |
Token ID | 1257 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
mess | +0.188 |
aj | +0.175 |
liv | +0.163 |
onna | +0.162 |
aman | +0.160 |
Neg logit contributions | |
aroo | -0.281 |
ter | -0.249 |
member | -0.230 |
apped | -0.227 |
crow | -0.224 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
mess | +0.786 |
aj | +0.746 |
wra | +0.696 |
onna | +0.695 |
liv | +0.692 |
Neg logit contributions | |
aroo | -0.627 |
ter | -0.541 |
apped | -0.476 |
member | -0.471 |
crow | -0.466 |
Token | They |
Token ID | 1119 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
aroo | +0.036 |
ter | +0.032 |
crow | +0.029 |
apped | +0.028 |
itte | +0.028 |
Neg logit contributions | |
mess | -0.030 |
aj | -0.027 |
onna | -0.025 |
wra | -0.025 |
pic | -0.025 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
mess | +0.050 |
wra | +0.041 |
onna | +0.039 |
aj | +0.038 |
slippery | +0.037 |
Neg logit contributions | |
aroo | -0.069 |
ter | -0.061 |
crow | -0.058 |
ive | -0.054 |
apped | -0.054 |
Token | at |
Token ID | 379 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
mess | +0.039 |
aj | +0.034 |
fault | +0.030 |
fun | +0.029 |
wra | +0.028 |
Neg logit contributions | |
aroo | -0.067 |
crow | -0.056 |
ter | -0.055 |
itte | -0.052 |
aro | -0.052 |
Token | each |
Token ID | 1123 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
aroo | +0.329 |
ter | +0.288 |
ive | +0.274 |
crow | +0.271 |
itte | +0.264 |
Neg logit contributions | |
mess | -0.252 |
aj | -0.211 |
wra | -0.196 |
pic | -0.195 |
mistake | -0.194 |
Token | . |
Token ID | 13 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
aroo | +0.140 |
ter | +0.126 |
crow | +0.111 |
apped | +0.110 |
itte | +0.107 |
Neg logit contributions | |
mess | -0.132 |
aj | -0.118 |
wra | -0.111 |
onna | -0.110 |
pic | -0.106 |
Token | They |
Token ID | 1119 |
Feature activation | +7.95e-03 |
Pos logit contributions | |
aroo | +0.105 |
ter | +0.093 |
crow | +0.081 |
itte | +0.078 |
apped | +0.078 |
Neg logit contributions | |
mess | -0.107 |
aj | -0.097 |
onna | -0.091 |
wra | -0.091 |
pic | -0.091 |
Token | had |
Token ID | 550 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
aroo | +0.018 |
ter | +0.016 |
crow | +0.015 |
ive | +0.014 |
itte | +0.014 |
Neg logit contributions | |
mess | -0.014 |
wra | -0.011 |
scar | -0.011 |
slippery | -0.011 |
pic | -0.011 |
Token | lots |
Token ID | 6041 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
mess | +0.005 |
aj | +0.005 |
aman | +0.005 |
onna | +0.005 |
wra | +0.005 |
Neg logit contributions | |
aroo | -0.004 |
ter | -0.004 |
apped | -0.003 |
sailors | -0.003 |
member | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
mess | +0.188 |
aj | +0.173 |
pic | +0.169 |
wra | +0.168 |
onna | +0.165 |
Neg logit contributions | |
aroo | -0.060 |
ter | -0.049 |
crow | -0.033 |
apped | -0.032 |
itte | -0.031 |
Token | fun |
Token ID | 1257 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
aroo | +1.039 |
ter | +0.946 |
sailors | +0.920 |
member | +0.906 |
ovable | +0.901 |
Neg logit contributions | |
mess | -0.308 |
onna | -0.272 |
aj | -0.264 |
aman | -0.256 |
liv | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
mess | +0.676 |
aj | +0.620 |
onna | +0.583 |
wra | +0.580 |
aman | +0.561 |
Neg logit contributions | |
aroo | -0.679 |
ter | -0.602 |
apped | -0.532 |
crow | -0.523 |
member | -0.514 |
Token | laughter |
Token ID | 20263 |
Feature activation | -1.02e-03 |
Pos logit contributions | |
mess | +0.125 |
aj | +0.114 |
wra | +0.106 |
onna | +0.106 |
aman | +0.102 |
Neg logit contributions | |
aroo | -0.120 |
ter | -0.107 |
crow | -0.094 |
apped | -0.094 |
itte | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
mess | +0.002 |
wra | +0.001 |
aj | +0.001 |
onna | +0.001 |
pic | +0.001 |
Neg logit contributions | |
aroo | -0.002 |
ter | -0.002 |
crow | -0.002 |
itte | -0.002 |
ovable | -0.002 |
Token | never |
Token ID | 1239 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
mess | +0.120 |
aj | +0.106 |
wra | +0.102 |
pic | +0.099 |
onna | +0.099 |
Neg logit contributions | |
aroo | -0.122 |
ter | -0.108 |
crow | -0.097 |
apped | -0.095 |
itte | -0.094 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
mess | +0.141 |
aj | +0.114 |
onna | +0.110 |
wra | +0.108 |
slippery | +0.104 |
Neg logit contributions | |
aroo | -0.211 |
ter | -0.179 |
crow | -0.172 |
itte | -0.170 |
apped | -0.165 |
Token | a |
Token ID | 257 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
mess | +0.038 |
aj | +0.031 |
wra | +0.031 |
pic | +0.030 |
onna | +0.030 |
Neg logit contributions | |
aroo | -0.055 |
ter | -0.051 |
crow | -0.045 |
apped | -0.045 |
itte | -0.045 |
Token | big |
Token ID | 1263 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
mess | +0.078 |
aj | +0.073 |
fault | +0.065 |
liv | +0.065 |
wra | +0.064 |
Neg logit contributions | |
aroo | -0.122 |
ter | -0.105 |
crow | -0.097 |
member | -0.096 |
itte | -0.094 |
Token | bite |
Token ID | 13197 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
mess | +0.201 |
aj | +0.173 |
wra | +0.156 |
onna | +0.152 |
pic | +0.147 |
Neg logit contributions | |
aroo | -0.411 |
ter | -0.376 |
crow | -0.345 |
apped | -0.341 |
itte | -0.336 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
mess | +0.514 |
wra | +0.444 |
onna | +0.436 |
aj | +0.434 |
slippery | +0.421 |
Neg logit contributions | |
aroo | -0.497 |
ter | -0.432 |
itte | -0.390 |
pilot | -0.386 |
apped | -0.381 |
Token | It |
Token ID | 632 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
mess | +0.034 |
aj | +0.030 |
onna | +0.028 |
wra | +0.028 |
pic | +0.028 |
Neg logit contributions | |
aroo | -0.038 |
ter | -0.035 |
crow | -0.031 |
apped | -0.030 |
itte | -0.030 |
Token | tasted |
Token ID | 29187 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
aroo | +0.030 |
ter | +0.027 |
crow | +0.024 |
apped | +0.024 |
itte | +0.024 |
Neg logit contributions | |
mess | -0.022 |
aj | -0.020 |
fault | -0.018 |
wra | -0.018 |
onna | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
aj | +0.657 |
mess | +0.558 |
liv | +0.545 |
icol | +0.533 |
fault | +0.531 |
Neg logit contributions | |
ter | -0.579 |
aroo | -0.561 |
of | -0.472 |
crow | -0.462 |
apped | -0.434 |
Token | delicious |
Token ID | 12625 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
mess | +0.216 |
aj | +0.207 |
wra | +0.180 |
aman | +0.179 |
icol | +0.178 |
Neg logit contributions | |
aroo | -0.315 |
ter | -0.287 |
apped | -0.257 |
crow | -0.256 |
itte | -0.254 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
mess | +0.486 |
aj | +0.477 |
fault | +0.409 |
onna | +0.404 |
liv | +0.401 |
Neg logit contributions | |
aroo | -0.572 |
ter | -0.538 |
crow | -0.453 |
apped | -0.432 |
ive | -0.428 |
Token | She |
Token ID | 1375 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
mess | +0.019 |
aj | +0.017 |
wra | +0.016 |
onna | +0.016 |
pic | +0.015 |
Neg logit contributions | |
aroo | -0.024 |
ter | -0.021 |
crow | -0.019 |
apped | -0.019 |
itte | -0.019 |
Token | ate |
Token ID | 15063 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
mess | +0.062 |
aj | +0.055 |
wra | +0.051 |
onna | +0.051 |
pic | +0.049 |
Neg logit contributions | |
aroo | -0.072 |
ter | -0.065 |
crow | -0.058 |
apped | -0.057 |
itte | -0.056 |
Token | make |
Token ID | 787 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
mess | +0.109 |
aj | +0.097 |
wra | +0.092 |
onna | +0.091 |
pic | +0.089 |
Neg logit contributions | |
aroo | -0.109 |
ter | -0.097 |
crow | -0.086 |
apped | -0.084 |
itte | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
aroo | +0.140 |
ter | +0.131 |
apped | +0.121 |
pilot | +0.114 |
sailors | +0.113 |
Neg logit contributions | |
aj | -0.134 |
mess | -0.127 |
liv | -0.124 |
onna | -0.123 |
aman | -0.120 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
aroo | +0.184 |
ter | +0.169 |
crow | +0.154 |
apped | +0.153 |
itte | +0.150 |
Neg logit contributions | |
mess | -0.102 |
aj | -0.089 |
wra | -0.081 |
onna | -0.080 |
pic | -0.077 |
Token | on |
Token ID | 319 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
aj | +0.281 |
mess | +0.266 |
liv | +0.259 |
aman | +0.257 |
icol | +0.252 |
Neg logit contributions | |
aroo | -0.272 |
ter | -0.247 |
member | -0.223 |
apped | -0.223 |
crow | -0.215 |
Token | the |
Token ID | 262 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
aroo | +0.206 |
ter | +0.192 |
person | +0.167 |
member | +0.157 |
pilot | +0.152 |
Neg logit contributions | |
aj | -0.379 |
liv | -0.329 |
mess | -0.322 |
icol | -0.317 |
onna | -0.306 |
Token | floor |
Token ID | 4314 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
aroo | +0.189 |
ter | +0.176 |
member | +0.160 |
crow | +0.158 |
apped | +0.157 |
Neg logit contributions | |
mess | -0.088 |
aj | -0.085 |
onna | -0.074 |
liv | -0.071 |
aman | -0.070 |
Token | of |
Token ID | 286 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
mess | +0.579 |
aj | +0.510 |
wra | +0.481 |
onna | +0.476 |
fault | +0.461 |
Neg logit contributions | |
aroo | -0.661 |
ter | -0.590 |
crow | -0.529 |
apped | -0.518 |
itte | -0.512 |
Token | their |
Token ID | 511 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
aroo | +0.696 |
ter | +0.636 |
apped | +0.542 |
crow | +0.541 |
member | +0.537 |
Neg logit contributions | |
mess | -0.697 |
aj | -0.695 |
onna | -0.616 |
icol | -0.614 |
liv | -0.606 |
Token | room |
Token ID | 2119 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
mess | +0.154 |
aj | +0.135 |
wra | +0.128 |
onna | +0.125 |
pic | +0.123 |
Neg logit contributions | |
aroo | -0.172 |
ter | -0.155 |
crow | -0.138 |
apped | -0.134 |
itte | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
mess | +0.217 |
aj | +0.193 |
wra | +0.183 |
onna | +0.180 |
pic | +0.175 |
Neg logit contributions | |
aroo | -0.225 |
ter | -0.201 |
crow | -0.178 |
apped | -0.175 |
itte | -0.172 |
Token |
|
Token ID | 198 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
aroo | +0.086 |
apped | +0.074 |
Everyone | +0.074 |
crow | +0.070 |
ter | +0.068 |
Neg logit contributions | |
mess | -0.136 |
aj | -0.120 |
wra | -0.120 |
icol | -0.116 |
onna | -0.115 |
Token | come |
Token ID | 1282 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
mess | +0.257 |
onna | +0.208 |
aj | +0.202 |
wra | +0.202 |
slippery | +0.201 |
Neg logit contributions | |
aroo | -0.289 |
ter | -0.262 |
apped | -0.240 |
crow | -0.231 |
itte | -0.226 |
Token | home |
Token ID | 1363 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
mess | +0.192 |
aj | +0.166 |
onna | +0.151 |
wra | +0.148 |
slippery | +0.145 |
Neg logit contributions | |
aroo | -0.286 |
ter | -0.252 |
crow | -0.239 |
itte | -0.228 |
apped | -0.226 |
Token | late |
Token ID | 2739 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
aroo | +0.194 |
ter | +0.176 |
crow | +0.155 |
apped | +0.155 |
member | +0.151 |
Neg logit contributions | |
mess | -0.167 |
aj | -0.149 |
wra | -0.141 |
onna | -0.138 |
pic | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
mess | +0.419 |
aj | +0.374 |
wra | +0.352 |
onna | +0.348 |
pic | +0.339 |
Neg logit contributions | |
aroo | -0.450 |
ter | -0.403 |
crow | -0.358 |
apped | -0.353 |
itte | -0.345 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
mess | +0.064 |
wra | +0.052 |
aj | +0.051 |
pic | +0.050 |
slippery | +0.049 |
Neg logit contributions | |
aroo | -0.085 |
ter | -0.075 |
crow | -0.070 |
apped | -0.070 |
itte | -0.068 |
Token | not |
Token ID | 407 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
mess | +0.215 |
wra | +0.169 |
aj | +0.167 |
onna | +0.165 |
slippery | +0.163 |
Neg logit contributions | |
aroo | -0.292 |
ter | -0.260 |
crow | -0.239 |
apped | -0.237 |
itte | -0.232 |
Token | pay |
Token ID | 1414 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
mess | +0.581 |
onna | +0.460 |
slippery | +0.441 |
fuss | +0.441 |
wra | +0.438 |
Neg logit contributions | |
aroo | -0.699 |
ter | -0.592 |
crow | -0.576 |
apped | -0.572 |
itte | -0.565 |
Token | any |
Token ID | 597 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
mess | +0.075 |
aj | +0.068 |
onna | +0.064 |
liv | +0.064 |
wra | +0.063 |
Neg logit contributions | |
aroo | -0.075 |
ter | -0.068 |
crow | -0.059 |
apped | -0.058 |
member | -0.057 |
Token | attention |
Token ID | 3241 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
mess | +0.084 |
aj | +0.067 |
wra | +0.066 |
fault | +0.063 |
slippery | +0.062 |
Neg logit contributions | |
aroo | -0.124 |
ter | -0.112 |
apped | -0.104 |
itte | -0.100 |
crow | -0.099 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
mess | +0.212 |
aj | +0.177 |
wra | +0.173 |
onna | +0.171 |
fault | +0.168 |
Neg logit contributions | |
aroo | -0.297 |
ter | -0.266 |
crow | -0.244 |
apped | -0.241 |
itte | -0.240 |
Token | his |
Token ID | 465 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
mess | +0.216 |
aj | +0.175 |
wra | +0.175 |
onna | +0.171 |
pic | +0.168 |
Neg logit contributions | |
aroo | -0.249 |
ter | -0.222 |
apped | -0.209 |
crow | -0.201 |
itte | -0.201 |