Token | little |
Token ID | 1310 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
barrel | +0.087 |
Bun | +0.081 |
hut | +0.074 |
shield | +0.073 |
he | +0.071 |
Neg logit contributions | |
ases | -0.338 |
olds | -0.319 |
cks | -0.317 |
els | -0.314 |
oke | -0.307 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
Bun | +0.068 |
he | +0.065 |
barrel | +0.065 |
accidentally | +0.063 |
shield | +0.061 |
Neg logit contributions | |
ases | -0.280 |
els | -0.263 |
olds | -0.256 |
ips | -0.251 |
cks | -0.244 |
Token | named |
Token ID | 3706 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
barrel | +0.029 |
dark | +0.028 |
puppy | +0.028 |
bunny | +0.028 |
Bun | +0.027 |
Neg logit contributions | |
ases | -0.152 |
olds | -0.145 |
els | -0.143 |
cks | -0.140 |
ips | -0.138 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
barrel | +0.037 |
shield | +0.036 |
puppy | +0.036 |
he | +0.035 |
cabin | +0.035 |
Neg logit contributions | |
ases | -0.068 |
olds | -0.064 |
els | -0.063 |
cks | -0.061 |
ips | -0.059 |
Token | found |
Token ID | 1043 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
ases | +0.012 |
olds | +0.011 |
els | +0.011 |
cks | +0.011 |
ips | +0.011 |
Neg logit contributions | |
barrel | -0.002 |
Bun | -0.002 |
bunny | -0.002 |
puppy | -0.002 |
hut | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
barrel | +0.025 |
hut | +0.023 |
bicycle | +0.022 |
cabin | +0.022 |
puppy | +0.022 |
Neg logit contributions | |
ases | -0.140 |
els | -0.132 |
olds | -0.132 |
cks | -0.128 |
ips | -0.126 |
Token | big |
Token ID | 1263 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
Bun | +0.148 |
decided | +0.145 |
While | +0.144 |
he | +0.138 |
Lots | +0.129 |
Neg logit contributions | |
els | -0.251 |
olds | -0.246 |
ric | -0.238 |
its | -0.237 |
ocol | -0.231 |
Token | box |
Token ID | 3091 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
Bun | +0.091 |
he | +0.083 |
Under | +0.079 |
decided | +0.077 |
Curious | +0.074 |
Neg logit contributions | |
els | -0.200 |
ases | -0.195 |
olds | -0.182 |
ocol | -0.179 |
cks | -0.175 |
Token | in |
Token ID | 287 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Bun | +0.096 |
barrel | +0.093 |
wolf | +0.092 |
puppy | +0.092 |
hunter | +0.090 |
Neg logit contributions | |
ases | -0.177 |
els | -0.170 |
olds | -0.167 |
cks | -0.164 |
ips | -0.159 |
Token | her |
Token ID | 607 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
dark | +0.051 |
he | +0.049 |
there | +0.049 |
hut | +0.049 |
puppy | +0.049 |
Neg logit contributions | |
ases | -0.101 |
olds | -0.093 |
els | -0.091 |
ips | -0.090 |
cks | -0.088 |
Token | room |
Token ID | 2119 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
Bun | +0.047 |
barrel | +0.047 |
he | +0.046 |
bunny | +0.045 |
wolf | +0.044 |
Neg logit contributions | |
ases | -0.148 |
els | -0.141 |
olds | -0.141 |
cks | -0.136 |
ips | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
superhero | +0.044 |
shield | +0.044 |
cabin | +0.043 |
vest | +0.042 |
wolf | +0.042 |
Neg logit contributions | |
ases | -0.122 |
cks | -0.114 |
olds | -0.111 |
els | -0.109 |
its | -0.105 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Bun | +0.101 |
barrel | +0.099 |
hut | +0.092 |
cabin | +0.090 |
shield | +0.087 |
Neg logit contributions | |
ases | -0.284 |
olds | -0.272 |
oke | -0.270 |
ila | -0.252 |
els | -0.252 |
Token | named |
Token ID | 3706 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
barrel | +0.047 |
Bun | +0.044 |
hut | +0.044 |
bunny | +0.044 |
puppy | +0.044 |
Neg logit contributions | |
ases | -0.169 |
olds | -0.159 |
els | -0.158 |
cks | -0.153 |
ips | -0.150 |
Token | Sue |
Token ID | 26089 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
barrel | +0.056 |
shield | +0.054 |
cabin | +0.054 |
hut | +0.054 |
puppy | +0.053 |
Neg logit contributions | |
ases | -0.099 |
olds | -0.094 |
els | -0.090 |
cks | -0.088 |
ips | -0.085 |
Token | found |
Token ID | 1043 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
barrel | +0.004 |
Bun | +0.004 |
puppy | +0.004 |
bunny | +0.004 |
hut | +0.004 |
Neg logit contributions | |
ases | -0.017 |
olds | -0.016 |
els | -0.016 |
cks | -0.015 |
ips | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
barrel | +0.025 |
cabin | +0.023 |
hut | +0.023 |
bicycle | +0.022 |
Bun | +0.021 |
Neg logit contributions | |
ases | -0.137 |
olds | -0.130 |
els | -0.128 |
cks | -0.125 |
ips | -0.123 |
Token | broken |
Token ID | 5445 |
Feature activation | +7.44e+00 |
Pos logit contributions | |
Bun | +0.155 |
decided | +0.146 |
he | +0.143 |
While | +0.143 |
He | +0.132 |
Neg logit contributions | |
olds | -0.241 |
els | -0.235 |
its | -0.231 |
ases | -0.224 |
mistake | -0.223 |
Token | scarf |
Token ID | 36953 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
Curious | +0.095 |
Under | +0.095 |
he | +0.091 |
While | +0.090 |
Bun | +0.090 |
Neg logit contributions | |
els | -0.193 |
ases | -0.182 |
olds | -0.171 |
ings | -0.169 |
its | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
barrel | +0.088 |
cabin | +0.086 |
hut | +0.084 |
cozy | +0.083 |
hunter | +0.083 |
Neg logit contributions | |
ases | -0.141 |
els | -0.132 |
cks | -0.129 |
olds | -0.128 |
ips | -0.128 |
Token | She |
Token ID | 1375 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
barrel | +0.057 |
dark | +0.056 |
hut | +0.055 |
bunny | +0.055 |
he | +0.054 |
Neg logit contributions | |
ases | -0.158 |
els | -0.149 |
olds | -0.148 |
cks | -0.145 |
irs | -0.143 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
barrel | +0.061 |
hut | +0.059 |
cabin | +0.056 |
puppy | +0.054 |
wolf | +0.053 |
Neg logit contributions | |
ases | -0.156 |
els | -0.156 |
olds | -0.152 |
cks | -0.146 |
its | -0.145 |
Token | little |
Token ID | 1310 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
barrel | +0.100 |
Bun | +0.095 |
hut | +0.090 |
cabin | +0.087 |
decided | +0.085 |
Neg logit contributions | |
ases | -0.285 |
oke | -0.279 |
olds | -0.275 |
els | -0.261 |
avi | -0.259 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
Bun | +0.070 |
accidentally | +0.070 |
barrel | +0.069 |
deserted | +0.069 |
shield | +0.068 |
Neg logit contributions | |
ases | -0.264 |
els | -0.241 |
olds | -0.240 |
ips | -0.235 |
oke | -0.228 |
Token | named |
Token ID | 3706 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
barrel | +0.030 |
hut | +0.029 |
Bun | +0.029 |
bunny | +0.028 |
dark | +0.028 |
Neg logit contributions | |
ases | -0.101 |
olds | -0.094 |
els | -0.094 |
cks | -0.090 |
ips | -0.088 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
hut | +0.037 |
shield | +0.037 |
puppy | +0.037 |
bunny | +0.037 |
cabin | +0.037 |
Neg logit contributions | |
ases | -0.080 |
olds | -0.074 |
cks | -0.071 |
els | -0.069 |
irs | -0.067 |
Token | found |
Token ID | 1043 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
ases | +0.070 |
els | +0.065 |
olds | +0.064 |
cks | +0.063 |
its | +0.060 |
Neg logit contributions | |
barrel | -0.018 |
bunny | -0.017 |
puppy | -0.017 |
Bun | -0.017 |
hut | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
barrel | +0.030 |
hut | +0.030 |
cabin | +0.030 |
bicycle | +0.030 |
puppy | +0.027 |
Neg logit contributions | |
ases | -0.126 |
olds | -0.119 |
els | -0.117 |
cks | -0.115 |
ips | -0.111 |
Token | big |
Token ID | 1263 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
decided | +0.150 |
Bun | +0.150 |
While | +0.140 |
he | +0.132 |
Curious | +0.129 |
Neg logit contributions | |
olds | -0.235 |
els | -0.235 |
ric | -0.225 |
its | -0.221 |
ases | -0.221 |
Token | , |
Token ID | 11 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
Bun | +0.091 |
he | +0.081 |
decided | +0.078 |
Under | +0.077 |
wanted | +0.074 |
Neg logit contributions | |
els | -0.198 |
ases | -0.197 |
olds | -0.183 |
ocol | -0.177 |
cks | -0.174 |
Token | heavy |
Token ID | 4334 |
Feature activation | +7.18e+00 |
Pos logit contributions | |
Bun | +0.077 |
barrel | +0.076 |
While | +0.075 |
cabin | +0.074 |
hut | +0.073 |
Neg logit contributions | |
els | -0.141 |
ases | -0.135 |
olds | -0.135 |
ocol | -0.133 |
cks | -0.131 |
Token | rock |
Token ID | 3881 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
Bun | +0.094 |
decided | +0.090 |
Curious | +0.085 |
he | +0.085 |
There | +0.083 |
Neg logit contributions | |
els | -0.193 |
ases | -0.188 |
ocol | -0.174 |
olds | -0.171 |
ips | -0.163 |
Token | in |
Token ID | 287 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
Bun | +0.080 |
superhero | +0.077 |
cozy | +0.076 |
puppy | +0.074 |
bunny | +0.073 |
Neg logit contributions | |
ases | -0.163 |
els | -0.157 |
cks | -0.153 |
olds | -0.152 |
ips | -0.142 |
Token | a |
Token ID | 257 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
superhero | +0.042 |
shield | +0.040 |
cabin | +0.039 |
barrel | +0.039 |
wolf | +0.039 |
Neg logit contributions | |
ases | -0.108 |
cks | -0.102 |
olds | -0.100 |
els | -0.096 |
its | -0.094 |
Token | boy |
Token ID | 2933 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Bun | +0.101 |
barrel | +0.097 |
hut | +0.092 |
cabin | +0.090 |
shield | +0.087 |
Neg logit contributions | |
ases | -0.274 |
oke | -0.268 |
olds | -0.265 |
ila | -0.248 |
its | -0.247 |
Token | named |
Token ID | 3706 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
barrel | +0.032 |
Bun | +0.031 |
hut | +0.031 |
puppy | +0.030 |
bunny | +0.030 |
Neg logit contributions | |
ases | -0.109 |
olds | -0.101 |
els | -0.101 |
cks | -0.098 |
ips | -0.095 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hut | +0.045 |
cabin | +0.045 |
puppy | +0.045 |
bunny | +0.044 |
shield | +0.044 |
Neg logit contributions | |
ases | -0.094 |
olds | -0.088 |
cks | -0.083 |
els | -0.081 |
icks | -0.078 |
Token | found |
Token ID | 1043 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
ases | +0.039 |
els | +0.035 |
olds | +0.035 |
cks | +0.035 |
its | +0.033 |
Neg logit contributions | |
barrel | -0.011 |
Bun | -0.010 |
bunny | -0.010 |
puppy | -0.010 |
hut | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
hut | +0.030 |
barrel | +0.030 |
cabin | +0.030 |
bicycle | +0.029 |
puppy | +0.028 |
Neg logit contributions | |
ases | -0.126 |
olds | -0.118 |
els | -0.115 |
cks | -0.114 |
ips | -0.111 |
Token | toy |
Token ID | 13373 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
Bun | +0.156 |
decided | +0.151 |
While | +0.138 |
he | +0.131 |
Curious | +0.129 |
Neg logit contributions | |
olds | -0.232 |
els | -0.227 |
its | -0.223 |
ases | -0.221 |
ric | -0.219 |
Token | motorcycle |
Token ID | 18757 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
cozy | +0.121 |
ju | +0.110 |
Bun | +0.110 |
cos | +0.108 |
peaceful | +0.105 |
Neg logit contributions | |
ases | -0.240 |
els | -0.235 |
olds | -0.215 |
cks | -0.206 |
ips | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
cozy | +0.118 |
hut | +0.116 |
cabin | +0.113 |
Bun | +0.112 |
shield | +0.110 |
Neg logit contributions | |
ases | -0.190 |
els | -0.181 |
olds | -0.174 |
cks | -0.173 |
ips | -0.161 |
Token | It |
Token ID | 632 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
puppy | +0.058 |
bunny | +0.058 |
hut | +0.057 |
barrel | +0.057 |
Bun | +0.057 |
Neg logit contributions | |
ases | -0.156 |
olds | -0.146 |
els | -0.144 |
cks | -0.140 |
ips | -0.137 |
Token | was |
Token ID | 373 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
hut | +0.078 |
barrel | +0.069 |
thief | +0.069 |
puppy | +0.068 |
cabin | +0.067 |
Neg logit contributions | |
ases | -0.142 |
els | -0.140 |
cks | -0.138 |
olds | -0.133 |
its | -0.128 |
Token | little |
Token ID | 1310 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
barrel | +0.097 |
Bun | +0.097 |
hut | +0.091 |
decided | +0.089 |
cabin | +0.087 |
Neg logit contributions | |
ases | -0.274 |
oke | -0.264 |
olds | -0.263 |
avi | -0.247 |
els | -0.246 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
accidentally | +0.072 |
deserted | +0.070 |
Bun | +0.070 |
he | +0.068 |
barrel | +0.067 |
Neg logit contributions | |
ases | -0.258 |
els | -0.233 |
olds | -0.231 |
ips | -0.226 |
ocol | -0.221 |
Token | named |
Token ID | 3706 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
barrel | +0.047 |
Bun | +0.044 |
hut | +0.043 |
bunny | +0.043 |
dark | +0.043 |
Neg logit contributions | |
ases | -0.154 |
olds | -0.145 |
els | -0.145 |
cks | -0.139 |
ips | -0.135 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
barrel | +0.035 |
shield | +0.034 |
cabin | +0.033 |
hunter | +0.033 |
hut | +0.033 |
Neg logit contributions | |
ases | -0.072 |
olds | -0.068 |
els | -0.066 |
cks | -0.064 |
irs | -0.063 |
Token | found |
Token ID | 1043 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ases | +0.000 |
els | +0.000 |
olds | +0.000 |
cks | +0.000 |
its | +0.000 |
Neg logit contributions | |
barrel | -0.000 |
shield | -0.000 |
Bun | -0.000 |
bicycle | -0.000 |
hut | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
barrel | +0.030 |
bicycle | +0.028 |
cabin | +0.028 |
hut | +0.027 |
hunter | +0.025 |
Neg logit contributions | |
ases | -0.122 |
olds | -0.116 |
els | -0.115 |
cks | -0.112 |
ips | -0.110 |
Token | big |
Token ID | 1263 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
decided | +0.143 |
Bun | +0.139 |
he | +0.136 |
While | +0.135 |
Curious | +0.126 |
Neg logit contributions | |
olds | -0.230 |
els | -0.226 |
mistake | -0.222 |
its | -0.221 |
ric | -0.220 |
Token | book |
Token ID | 1492 |
Feature activation | +7.07e+00 |
Pos logit contributions | |
Bun | +0.090 |
he | +0.083 |
Under | +0.079 |
decided | +0.079 |
Curious | +0.076 |
Neg logit contributions | |
els | -0.195 |
ases | -0.194 |
olds | -0.180 |
ocol | -0.176 |
ips | -0.171 |
Token | called |
Token ID | 1444 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
wolf | +0.119 |
bunny | +0.119 |
Bun | +0.118 |
puppy | +0.117 |
barrel | +0.116 |
Neg logit contributions | |
ases | -0.187 |
olds | -0.182 |
els | -0.175 |
cks | -0.173 |
ips | -0.171 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
barrel | +0.043 |
hut | +0.041 |
dark | +0.041 |
bunny | +0.041 |
Bun | +0.040 |
Neg logit contributions | |
ases | -0.104 |
olds | -0.098 |
els | -0.097 |
cks | -0.094 |
ips | -0.092 |
Token | dictionary |
Token ID | 22155 |
Feature activation | +8.34e+00 |
Pos logit contributions | |
Bun | +0.159 |
decided | +0.148 |
Benny | +0.145 |
Bug | +0.140 |
there | +0.138 |
Neg logit contributions | |
olds | -0.222 |
oke | -0.208 |
ases | -0.195 |
els | -0.195 |
its | -0.194 |
Token | a |
Token ID | 257 |
Feature activation | +9.90e+00 |
Pos logit contributions | |
shield | +0.036 |
barrel | +0.036 |
superhero | +0.035 |
vest | +0.035 |
puppy | +0.035 |
Neg logit contributions | |
ases | -0.115 |
cks | -0.109 |
els | -0.105 |
olds | -0.105 |
its | -0.100 |
Token | boy |
Token ID | 2933 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Bun | +0.098 |
barrel | +0.092 |
hut | +0.085 |
cabin | +0.083 |
shield | +0.083 |
Neg logit contributions | |
ases | -0.288 |
oke | -0.273 |
olds | -0.273 |
els | -0.260 |
its | -0.258 |
Token | named |
Token ID | 3706 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
barrel | +0.031 |
Bun | +0.030 |
puppy | +0.030 |
hut | +0.030 |
bunny | +0.030 |
Neg logit contributions | |
ases | -0.112 |
olds | -0.105 |
els | -0.105 |
cks | -0.102 |
ips | -0.099 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
puppy | +0.041 |
bunny | +0.039 |
hut | +0.039 |
cabin | +0.039 |
shield | +0.038 |
Neg logit contributions | |
ases | -0.087 |
olds | -0.080 |
cks | -0.077 |
els | -0.076 |
irs | -0.071 |
Token | found |
Token ID | 1043 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ases | +0.062 |
els | +0.058 |
olds | +0.057 |
cks | +0.057 |
ips | +0.054 |
Neg logit contributions | |
barrel | -0.014 |
puppy | -0.014 |
Bun | -0.014 |
bunny | -0.014 |
hut | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
barrel | +0.028 |
hut | +0.028 |
cabin | +0.027 |
puppy | +0.027 |
Bun | +0.027 |
Neg logit contributions | |
ases | -0.131 |
olds | -0.123 |
els | -0.121 |
cks | -0.120 |
ips | -0.116 |
Token | toy |
Token ID | 13373 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
Bun | +0.160 |
decided | +0.153 |
While | +0.142 |
he | +0.137 |
Benny | +0.133 |
Neg logit contributions | |
els | -0.233 |
olds | -0.232 |
ases | -0.225 |
its | -0.223 |
ric | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
cozy | +0.118 |
Bun | +0.110 |
ju | +0.105 |
cos | +0.103 |
peaceful | +0.103 |
Neg logit contributions | |
ases | -0.249 |
els | -0.240 |
olds | -0.224 |
cks | -0.214 |
ips | -0.207 |
Token | The |
Token ID | 383 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
barrel | +0.063 |
puppy | +0.062 |
bunny | +0.062 |
Bun | +0.062 |
hut | +0.061 |
Neg logit contributions | |
ases | -0.177 |
olds | -0.166 |
els | -0.164 |
cks | -0.159 |
ips | -0.156 |
Token | toy |
Token ID | 13373 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
Bun | +0.027 |
hut | +0.025 |
accidentally | +0.024 |
barrel | +0.024 |
cabin | +0.023 |
Neg logit contributions | |
ases | -0.102 |
els | -0.098 |
olds | -0.096 |
cks | -0.092 |
its | -0.092 |
Token | was |
Token ID | 373 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
hut | +0.068 |
cozy | +0.066 |
dark | +0.065 |
Bun | +0.063 |
wolf | +0.063 |
Neg logit contributions | |
els | -0.163 |
ases | -0.163 |
olds | -0.153 |
cks | -0.145 |
ips | -0.142 |
Token | a |
Token ID | 257 |
Feature activation | +9.92e+00 |
Pos logit contributions | |
shield | +0.040 |
cabin | +0.040 |
vest | +0.039 |
superhero | +0.038 |
bicycle | +0.038 |
Neg logit contributions | |
ases | -0.116 |
cks | -0.107 |
olds | -0.104 |
els | -0.103 |
ips | -0.101 |
Token | boy |
Token ID | 2933 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
Bun | +0.093 |
barrel | +0.091 |
hut | +0.087 |
cabin | +0.085 |
shield | +0.081 |
Neg logit contributions | |
ases | -0.286 |
oke | -0.276 |
olds | -0.275 |
ila | -0.256 |
els | -0.256 |
Token | named |
Token ID | 3706 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
barrel | +0.034 |
Bun | +0.033 |
hut | +0.033 |
puppy | +0.032 |
bunny | +0.032 |
Neg logit contributions | |
ases | -0.112 |
olds | -0.104 |
els | -0.104 |
cks | -0.100 |
ips | -0.097 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
bunny | +0.041 |
puppy | +0.041 |
hut | +0.041 |
cabin | +0.041 |
shield | +0.040 |
Neg logit contributions | |
ases | -0.091 |
olds | -0.084 |
cks | -0.081 |
els | -0.080 |
irs | -0.076 |
Token | found |
Token ID | 1043 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ases | +0.040 |
els | +0.037 |
olds | +0.036 |
cks | +0.036 |
its | +0.035 |
Neg logit contributions | |
barrel | -0.011 |
Bun | -0.010 |
bunny | -0.010 |
puppy | -0.010 |
hut | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
hut | +0.031 |
cabin | +0.031 |
barrel | +0.031 |
bicycle | +0.029 |
puppy | +0.028 |
Neg logit contributions | |
ases | -0.129 |
olds | -0.122 |
els | -0.119 |
cks | -0.118 |
ips | -0.114 |
Token | cr |
Token ID | 1067 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Bun | +0.150 |
decided | +0.147 |
While | +0.135 |
he | +0.130 |
Curious | +0.125 |
Neg logit contributions | |
olds | -0.233 |
els | -0.225 |
its | -0.220 |
ric | -0.219 |
mistake | -0.219 |
Token | ay |
Token ID | 323 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
barrel | +0.043 |
puppy | +0.042 |
bunny | +0.042 |
dark | +0.042 |
Bun | +0.042 |
Neg logit contributions | |
ases | -0.036 |
olds | -0.033 |
els | -0.032 |
cks | -0.031 |
ips | -0.030 |
Token | on |
Token ID | 261 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
barrel | +0.034 |
hut | +0.034 |
cabin | +0.033 |
dark | +0.033 |
Bun | +0.033 |
Neg logit contributions | |
ases | -0.033 |
els | -0.031 |
olds | -0.030 |
cks | -0.028 |
ips | -0.027 |
Token | box |
Token ID | 3091 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
Bun | +0.087 |
cozy | +0.081 |
cabin | +0.080 |
wolf | +0.079 |
hunter | +0.078 |
Neg logit contributions | |
ases | -0.148 |
els | -0.139 |
olds | -0.134 |
cks | -0.130 |
ips | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
Bun | +0.092 |
wolf | +0.089 |
puppy | +0.089 |
bunny | +0.087 |
hunter | +0.087 |
Neg logit contributions | |
ases | -0.172 |
els | -0.165 |
olds | -0.160 |
cks | -0.160 |
ips | -0.154 |
Token | little |
Token ID | 1310 |
Feature activation | +8.32e+00 |
Pos logit contributions | |
barrel | +0.099 |
Bun | +0.095 |
hut | +0.090 |
cabin | +0.087 |
shield | +0.085 |
Neg logit contributions | |
ases | -0.285 |
olds | -0.274 |
oke | -0.273 |
cks | -0.256 |
its | -0.255 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
accidentally | +0.071 |
Bun | +0.069 |
barrel | +0.067 |
deserted | +0.067 |
he | +0.067 |
Neg logit contributions | |
ases | -0.271 |
els | -0.246 |
olds | -0.246 |
ips | -0.240 |
ocol | -0.231 |
Token | named |
Token ID | 3706 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
barrel | +0.074 |
dark | +0.073 |
cabin | +0.072 |
bicycle | +0.072 |
puppy | +0.072 |
Neg logit contributions | |
ases | -0.164 |
olds | -0.150 |
els | -0.149 |
cks | -0.146 |
its | -0.134 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
cabin | +0.043 |
hut | +0.042 |
bicycle | +0.041 |
superhero | +0.041 |
barrel | +0.041 |
Neg logit contributions | |
ases | -0.099 |
cks | -0.091 |
olds | -0.089 |
els | -0.089 |
irs | -0.088 |
Token | found |
Token ID | 1043 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
ases | +0.044 |
els | +0.041 |
cks | +0.041 |
olds | +0.041 |
its | +0.039 |
Neg logit contributions | |
barrel | -0.011 |
puppy | -0.011 |
bunny | -0.011 |
hut | -0.010 |
Bun | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
bicycle | +0.026 |
barrel | +0.026 |
cabin | +0.026 |
hut | +0.025 |
puppy | +0.024 |
Neg logit contributions | |
ases | -0.124 |
olds | -0.116 |
els | -0.115 |
cks | -0.114 |
ips | -0.109 |
Token | shiny |
Token ID | 22441 |
Feature activation | +6.89e+00 |
Pos logit contributions | |
decided | +0.143 |
chair | +0.141 |
Lots | +0.137 |
While | +0.133 |
he | +0.133 |
Neg logit contributions | |
ric | -0.209 |
mistake | -0.204 |
its | -0.200 |
upid | -0.194 |
ings | -0.192 |
Token | trophy |
Token ID | 16383 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
Bun | +0.090 |
Curious | +0.088 |
Under | +0.087 |
There | +0.087 |
late | +0.086 |
Neg logit contributions | |
els | -0.186 |
ases | -0.174 |
ocol | -0.165 |
ir | -0.159 |
its | -0.157 |
Token | in |
Token ID | 287 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Bun | +0.124 |
cozy | +0.119 |
dark | +0.113 |
While | +0.112 |
cabin | +0.112 |
Neg logit contributions | |
ases | -0.191 |
els | -0.180 |
cks | -0.171 |
olds | -0.167 |
ips | -0.164 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
barrel | +0.029 |
puppy | +0.028 |
bunny | +0.028 |
hut | +0.028 |
Bun | +0.028 |
Neg logit contributions | |
ases | -0.074 |
olds | -0.070 |
els | -0.070 |
cks | -0.068 |
ips | -0.066 |
Token | forest |
Token ID | 8222 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
while | +0.047 |
he | +0.046 |
Bun | +0.045 |
there | +0.042 |
superhero | +0.042 |
Neg logit contributions | |
ases | -0.101 |
els | -0.093 |
olds | -0.093 |
cks | -0.091 |
ips | -0.088 |
Token | a |
Token ID | 257 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
puppy | +0.032 |
barrel | +0.031 |
shield | +0.030 |
vest | +0.030 |
superhero | +0.030 |
Neg logit contributions | |
ases | -0.114 |
cks | -0.109 |
els | -0.108 |
olds | -0.103 |
ips | -0.102 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
Bun | +0.070 |
barrel | +0.069 |
hut | +0.062 |
he | +0.062 |
shield | +0.061 |
Neg logit contributions | |
ases | -0.315 |
olds | -0.298 |
els | -0.293 |
oke | -0.291 |
cks | -0.289 |
Token | named |
Token ID | 3706 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
barrel | +0.030 |
dark | +0.029 |
puppy | +0.029 |
bunny | +0.029 |
Bun | +0.028 |
Neg logit contributions | |
ases | -0.151 |
olds | -0.143 |
els | -0.142 |
cks | -0.139 |
ips | -0.137 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
barrel | +0.035 |
puppy | +0.033 |
hut | +0.033 |
bunny | +0.033 |
Bun | +0.033 |
Neg logit contributions | |
ases | -0.077 |
olds | -0.073 |
els | -0.072 |
cks | -0.070 |
ips | -0.068 |
Token | found |
Token ID | 1043 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ases | +0.020 |
olds | +0.019 |
els | +0.019 |
cks | +0.019 |
ips | +0.018 |
Neg logit contributions | |
barrel | -0.004 |
bunny | -0.003 |
Bun | -0.003 |
puppy | -0.003 |
hut | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
barrel | +0.022 |
hut | +0.020 |
puppy | +0.019 |
cabin | +0.019 |
Bun | +0.019 |
Neg logit contributions | |
ases | -0.123 |
olds | -0.117 |
els | -0.117 |
cks | -0.113 |
ips | -0.111 |
Token | box |
Token ID | 3091 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Bun | +0.141 |
he | +0.133 |
decided | +0.131 |
While | +0.131 |
Benny | +0.119 |
Neg logit contributions | |
els | -0.251 |
olds | -0.251 |
its | -0.240 |
ases | -0.236 |
ric | -0.230 |
Token | of |
Token ID | 286 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Bun | +0.096 |
barrel | +0.094 |
wolf | +0.093 |
puppy | +0.092 |
bunny | +0.091 |
Neg logit contributions | |
ases | -0.158 |
els | -0.149 |
olds | -0.148 |
cks | -0.144 |
ips | -0.140 |
Token | shiny |
Token ID | 22441 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
Bun | +0.021 |
storm | +0.020 |
barrel | +0.020 |
he | +0.020 |
accidentally | +0.020 |
Neg logit contributions | |
ases | -0.041 |
els | -0.040 |
olds | -0.039 |
irs | -0.036 |
cks | -0.035 |
Token | jewelry |
Token ID | 22634 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
Bun | +0.091 |
storm | +0.083 |
restless | +0.082 |
Benny | +0.082 |
accidentally | +0.082 |
Neg logit contributions | |
els | -0.140 |
ases | -0.126 |
olds | -0.116 |
ocol | -0.111 |
its | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
Bun | +0.113 |
Benny | +0.108 |
While | +0.107 |
accidentally | +0.106 |
dark | +0.106 |
Neg logit contributions | |
els | -0.171 |
ases | -0.156 |
ips | -0.148 |
olds | -0.148 |
cks | -0.143 |
Token | little |
Token ID | 1310 |
Feature activation | +7.93e+00 |
Pos logit contributions | |
barrel | +0.092 |
Bun | +0.091 |
hut | +0.086 |
cabin | +0.083 |
shield | +0.081 |
Neg logit contributions | |
ases | -0.295 |
olds | -0.284 |
oke | -0.279 |
els | -0.267 |
cks | -0.265 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Bun | +0.067 |
accidentally | +0.066 |
deserted | +0.065 |
barrel | +0.063 |
cozy | +0.062 |
Neg logit contributions | |
ases | -0.259 |
els | -0.236 |
olds | -0.236 |
ips | -0.227 |
ocol | -0.223 |
Token | named |
Token ID | 3706 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
barrel | +0.029 |
hut | +0.028 |
Bun | +0.027 |
bunny | +0.027 |
puppy | +0.027 |
Neg logit contributions | |
ases | -0.096 |
olds | -0.090 |
els | -0.090 |
cks | -0.087 |
ips | -0.084 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
bunny | +0.043 |
puppy | +0.043 |
hut | +0.042 |
cabin | +0.042 |
wolf | +0.042 |
Neg logit contributions | |
ases | -0.088 |
olds | -0.082 |
cks | -0.079 |
els | -0.076 |
irs | -0.073 |
Token | found |
Token ID | 1043 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ases | +0.038 |
els | +0.035 |
olds | +0.035 |
cks | +0.034 |
its | +0.033 |
Neg logit contributions | |
barrel | -0.011 |
bunny | -0.011 |
Bun | -0.011 |
puppy | -0.011 |
hut | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
barrel | +0.028 |
hut | +0.028 |
cabin | +0.028 |
bicycle | +0.027 |
bunny | +0.026 |
Neg logit contributions | |
ases | -0.125 |
olds | -0.117 |
els | -0.115 |
cks | -0.114 |
ips | -0.110 |
Token | magic |
Token ID | 5536 |
Feature activation | +7.59e+00 |
Pos logit contributions | |
decided | +0.143 |
Bun | +0.142 |
While | +0.130 |
he | +0.123 |
Curious | +0.120 |
Neg logit contributions | |
olds | -0.234 |
ric | -0.229 |
els | -0.227 |
its | -0.224 |
mistake | -0.219 |
Token | f |
Token ID | 277 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
While | +0.129 |
Bun | +0.129 |
restless | +0.121 |
Curious | +0.120 |
Betsy | +0.119 |
Neg logit contributions | |
els | -0.174 |
ases | -0.171 |
olds | -0.158 |
its | -0.157 |
ocol | -0.153 |
Token | auc |
Token ID | 14272 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
barrel | +0.043 |
puppy | +0.043 |
Bun | +0.043 |
bunny | +0.043 |
hut | +0.042 |
Neg logit contributions | |
ases | -0.031 |
olds | -0.028 |
els | -0.027 |
ips | -0.025 |
cks | -0.025 |
Token | et |
Token ID | 316 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ases | +0.029 |
olds | +0.026 |
els | +0.026 |
cks | +0.024 |
ips | +0.023 |
Neg logit contributions | |
barrel | -0.048 |
bunny | -0.047 |
hut | -0.047 |
puppy | -0.047 |
Bun | -0.047 |
Token | in |
Token ID | 287 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
cozy | +0.032 |
hut | +0.031 |
Bun | +0.031 |
barrel | +0.029 |
cabin | +0.029 |
Neg logit contributions | |
els | -0.063 |
ases | -0.062 |
olds | -0.056 |
cks | -0.055 |
ips | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | +9.76e+00 |
Pos logit contributions | |
shield | +0.041 |
superhero | +0.041 |
vest | +0.041 |
cabin | +0.040 |
bicycle | +0.039 |
Neg logit contributions | |
ases | -0.112 |
cks | -0.107 |
olds | -0.102 |
els | -0.101 |
its | -0.098 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
barrel | +0.094 |
hut | +0.087 |
Bun | +0.085 |
cabin | +0.085 |
shield | +0.082 |
Neg logit contributions | |
ases | -0.263 |
oke | -0.261 |
olds | -0.255 |
avi | -0.243 |
ila | -0.239 |
Token | named |
Token ID | 3706 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
barrel | +0.030 |
hut | +0.028 |
Bun | +0.028 |
bunny | +0.028 |
dark | +0.028 |
Neg logit contributions | |
ases | -0.095 |
olds | -0.089 |
els | -0.088 |
cks | -0.085 |
ips | -0.082 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
hut | +0.036 |
bunny | +0.036 |
cabin | +0.035 |
puppy | +0.034 |
wolf | +0.034 |
Neg logit contributions | |
ases | -0.075 |
olds | -0.070 |
cks | -0.067 |
els | -0.066 |
irs | -0.064 |
Token | found |
Token ID | 1043 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
ases | +0.071 |
els | +0.065 |
olds | +0.064 |
cks | +0.063 |
its | +0.061 |
Neg logit contributions | |
barrel | -0.021 |
bunny | -0.021 |
hut | -0.020 |
Bun | -0.020 |
puppy | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
cabin | +0.030 |
hut | +0.030 |
barrel | +0.029 |
bicycle | +0.028 |
bunny | +0.027 |
Neg logit contributions | |
ases | -0.114 |
olds | -0.107 |
els | -0.105 |
cks | -0.104 |
ips | -0.100 |
Token | heavy |
Token ID | 4334 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
Bun | +0.139 |
decided | +0.139 |
While | +0.129 |
he | +0.123 |
there | +0.120 |
Neg logit contributions | |
olds | -0.229 |
ric | -0.221 |
mistake | -0.220 |
els | -0.218 |
its | -0.212 |
Token | box |
Token ID | 3091 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
Bun | +0.097 |
decided | +0.094 |
There | +0.090 |
Curious | +0.089 |
he | +0.088 |
Neg logit contributions | |
els | -0.194 |
ases | -0.191 |
ocol | -0.178 |
olds | -0.176 |
its | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
Bun | +0.089 |
wolf | +0.088 |
bunny | +0.087 |
barrel | +0.086 |
puppy | +0.086 |
Neg logit contributions | |
ases | -0.160 |
els | -0.153 |
olds | -0.149 |
cks | -0.147 |
ips | -0.143 |
Token | He |
Token ID | 679 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
bunny | +0.047 |
puppy | +0.047 |
Bun | +0.047 |
barrel | +0.046 |
hut | +0.045 |
Neg logit contributions | |
ases | -0.166 |
olds | -0.157 |
els | -0.154 |
cks | -0.150 |
ips | -0.148 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
barrel | +0.059 |
hut | +0.058 |
wolf | +0.057 |
cabin | +0.056 |
puppy | +0.055 |
Neg logit contributions | |
ases | -0.141 |
els | -0.140 |
olds | -0.137 |
cks | -0.131 |
its | -0.128 |
Token | an |
Token ID | 281 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
bicycle | +0.064 |
barrel | +0.064 |
thief | +0.062 |
hunter | +0.061 |
cabin | +0.061 |
Neg logit contributions | |
ases | -0.168 |
els | -0.151 |
cks | -0.151 |
ips | -0.149 |
irs | -0.148 |
Token | attractive |
Token ID | 10966 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
Bun | +0.068 |
he | +0.066 |
barrel | +0.065 |
hut | +0.063 |
bunny | +0.062 |
Neg logit contributions | |
ases | -0.165 |
els | -0.159 |
olds | -0.152 |
cks | -0.148 |
its | -0.140 |
Token | crib |
Token ID | 48083 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
he | +0.098 |
Bun | +0.096 |
There | +0.095 |
decided | +0.091 |
deserted | +0.091 |
Neg logit contributions | |
els | -0.185 |
ases | -0.182 |
ums | -0.170 |
olds | -0.169 |
ocol | -0.167 |
Token | in |
Token ID | 287 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Bun | +0.131 |
cozy | +0.127 |
dark | +0.123 |
ju | +0.122 |
shield | +0.121 |
Neg logit contributions | |
ases | -0.160 |
olds | -0.142 |
els | -0.141 |
ips | -0.130 |
cks | -0.130 |
Token | a |
Token ID | 257 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
barrel | +0.029 |
puppy | +0.028 |
Bun | +0.028 |
bunny | +0.028 |
hut | +0.027 |
Neg logit contributions | |
ases | -0.102 |
els | -0.096 |
olds | -0.095 |
cks | -0.094 |
ips | -0.091 |
Token | nursery |
Token ID | 41326 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
Bun | +0.132 |
he | +0.128 |
Benny | +0.116 |
barrel | +0.114 |
miner | +0.112 |
Neg logit contributions | |
ases | -0.234 |
cks | -0.222 |
els | -0.222 |
olds | -0.218 |
ips | -0.208 |
Token | . |
Token ID | 13 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
Bun | +0.193 |
barrel | +0.185 |
Benny | +0.182 |
wolf | +0.179 |
shield | +0.177 |
Neg logit contributions | |
ases | -0.286 |
olds | -0.274 |
els | -0.264 |
ips | -0.254 |
ums | -0.242 |
Token | Everyday |
Token ID | 48154 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
barrel | +0.097 |
hut | +0.096 |
shield | +0.095 |
puppy | +0.093 |
bunny | +0.093 |
Neg logit contributions | |
ases | -0.161 |
olds | -0.150 |
els | -0.144 |
ips | -0.140 |
cks | -0.139 |
Token | a |
Token ID | 257 |
Feature activation | +7.85e+00 |
Pos logit contributions | |
Bun | +0.088 |
deserted | +0.085 |
barrel | +0.082 |
hut | +0.082 |
puppy | +0.080 |
Neg logit contributions | |
ases | -0.110 |
els | -0.100 |
olds | -0.097 |
ips | -0.097 |
rs | -0.086 |
Token | little |
Token ID | 1310 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
buried | +0.092 |
barrel | +0.089 |
Bun | +0.085 |
hut | +0.084 |
abandoned | +0.078 |
Neg logit contributions | |
oke | -0.178 |
olds | -0.177 |
humor | -0.172 |
apology | -0.169 |
ases | -0.164 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
deserted | +0.083 |
barrel | +0.074 |
hut | +0.072 |
accidentally | +0.071 |
Bun | +0.070 |
Neg logit contributions | |
ases | -0.142 |
olds | -0.132 |
oke | -0.131 |
humor | -0.122 |
supervision | -0.121 |
Token | little |
Token ID | 1310 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
Bun | +0.087 |
barrel | +0.086 |
hut | +0.082 |
cabin | +0.078 |
shield | +0.075 |
Neg logit contributions | |
ases | -0.293 |
olds | -0.282 |
oke | -0.280 |
els | -0.267 |
cks | -0.263 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
Bun | +0.066 |
accidentally | +0.065 |
barrel | +0.062 |
shield | +0.060 |
deserted | +0.059 |
Neg logit contributions | |
ases | -0.267 |
els | -0.244 |
olds | -0.243 |
ips | -0.238 |
ocol | -0.229 |
Token | named |
Token ID | 3706 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
barrel | +0.041 |
Bun | +0.038 |
hut | +0.038 |
puppy | +0.038 |
bunny | +0.038 |
Neg logit contributions | |
ases | -0.148 |
olds | -0.139 |
els | -0.139 |
cks | -0.134 |
ips | -0.131 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
barrel | +0.039 |
shield | +0.038 |
hut | +0.037 |
cabin | +0.037 |
puppy | +0.037 |
Neg logit contributions | |
ases | -0.087 |
olds | -0.082 |
els | -0.079 |
cks | -0.077 |
ips | -0.076 |
Token | found |
Token ID | 1043 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
ases | +0.008 |
els | +0.008 |
olds | +0.008 |
cks | +0.007 |
ips | +0.007 |
Neg logit contributions | |
barrel | -0.002 |
Bun | -0.002 |
shield | -0.002 |
hut | -0.002 |
bunny | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
barrel | +0.025 |
bicycle | +0.023 |
hut | +0.023 |
cabin | +0.023 |
puppy | +0.021 |
Neg logit contributions | |
ases | -0.124 |
olds | -0.118 |
els | -0.117 |
cks | -0.114 |
ips | -0.112 |
Token | big |
Token ID | 1263 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
Bun | +0.140 |
decided | +0.140 |
he | +0.134 |
While | +0.132 |
He | +0.122 |
Neg logit contributions | |
olds | -0.235 |
els | -0.233 |
ric | -0.225 |
its | -0.219 |
mistake | -0.218 |
Token | scale |
Token ID | 5046 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
Bun | +0.088 |
he | +0.081 |
Under | +0.076 |
decided | +0.076 |
Curious | +0.073 |
Neg logit contributions | |
els | -0.193 |
ases | -0.191 |
olds | -0.178 |
ocol | -0.173 |
cks | -0.168 |
Token | in |
Token ID | 287 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Bun | +0.097 |
superhero | +0.089 |
Benny | +0.086 |
bunny | +0.085 |
wolf | +0.084 |
Neg logit contributions | |
ases | -0.182 |
els | -0.179 |
olds | -0.176 |
cks | -0.170 |
ips | -0.161 |
Token | her |
Token ID | 607 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
dark | +0.030 |
there | +0.030 |
he | +0.029 |
puppy | +0.029 |
hut | +0.029 |
Neg logit contributions | |
ases | -0.063 |
olds | -0.058 |
els | -0.057 |
ips | -0.055 |
cks | -0.055 |
Token | house |
Token ID | 2156 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
Bun | +0.041 |
bunny | +0.038 |
puppy | +0.037 |
dark | +0.036 |
barrel | +0.036 |
Neg logit contributions | |
ases | -0.124 |
olds | -0.119 |
els | -0.119 |
cks | -0.115 |
ips | -0.112 |
Token | a |
Token ID | 257 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
shield | +0.043 |
superhero | +0.043 |
barrel | +0.042 |
cabin | +0.041 |
hunter | +0.040 |
Neg logit contributions | |
ases | -0.111 |
olds | -0.104 |
cks | -0.103 |
els | -0.101 |
ips | -0.098 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
barrel | +0.095 |
Bun | +0.095 |
hut | +0.088 |
cabin | +0.087 |
decided | +0.084 |
Neg logit contributions | |
ases | -0.275 |
oke | -0.271 |
olds | -0.268 |
ila | -0.248 |
its | -0.246 |
Token | named |
Token ID | 3706 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
barrel | +0.029 |
Bun | +0.028 |
hut | +0.028 |
puppy | +0.028 |
bunny | +0.028 |
Neg logit contributions | |
ases | -0.105 |
olds | -0.099 |
els | -0.098 |
cks | -0.095 |
ips | -0.093 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
hut | +0.042 |
bunny | +0.041 |
puppy | +0.041 |
cabin | +0.041 |
shield | +0.041 |
Neg logit contributions | |
ases | -0.096 |
olds | -0.090 |
cks | -0.086 |
els | -0.085 |
irs | -0.081 |
Token | found |
Token ID | 1043 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
ases | +0.041 |
els | +0.038 |
olds | +0.038 |
cks | +0.037 |
its | +0.035 |
Neg logit contributions | |
barrel | -0.012 |
bunny | -0.012 |
Bun | -0.012 |
puppy | -0.012 |
hut | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
hut | +0.028 |
barrel | +0.028 |
cabin | +0.028 |
bicycle | +0.027 |
puppy | +0.026 |
Neg logit contributions | |
ases | -0.123 |
olds | -0.116 |
els | -0.113 |
cks | -0.112 |
ips | -0.109 |
Token | big |
Token ID | 1263 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
Bun | +0.148 |
decided | +0.146 |
While | +0.133 |
he | +0.127 |
Curious | +0.125 |
Neg logit contributions | |
olds | -0.230 |
els | -0.219 |
its | -0.216 |
mistake | -0.214 |
ric | -0.214 |
Token | hammer |
Token ID | 15554 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
Bun | +0.090 |
decided | +0.079 |
he | +0.079 |
Under | +0.079 |
Curious | +0.076 |
Neg logit contributions | |
els | -0.189 |
ases | -0.189 |
olds | -0.174 |
ocol | -0.170 |
ips | -0.166 |
Token | in |
Token ID | 287 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
cozy | +0.068 |
hut | +0.068 |
Bun | +0.068 |
cabin | +0.066 |
barrel | +0.066 |
Neg logit contributions | |
ases | -0.148 |
els | -0.145 |
olds | -0.136 |
cks | -0.135 |
ips | -0.132 |
Token | his |
Token ID | 465 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
barrel | +0.029 |
dark | +0.029 |
puppy | +0.028 |
bunny | +0.028 |
Bun | +0.028 |
Neg logit contributions | |
ases | -0.080 |
olds | -0.076 |
els | -0.075 |
cks | -0.073 |
ips | -0.072 |
Token | toy |
Token ID | 13373 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
Bun | +0.044 |
bunny | +0.042 |
he | +0.040 |
barrel | +0.040 |
while | +0.039 |
Neg logit contributions | |
ases | -0.127 |
olds | -0.121 |
els | -0.120 |
cks | -0.117 |
ips | -0.114 |
Token | , |
Token ID | 11 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
barrel | +0.051 |
Bun | +0.050 |
dark | +0.050 |
he | +0.050 |
bunny | +0.049 |
Neg logit contributions | |
ases | -0.178 |
olds | -0.168 |
els | -0.167 |
cks | -0.163 |
ips | -0.159 |
Token | a |
Token ID | 257 |
Feature activation | +9.97e+00 |
Pos logit contributions | |
barrel | +0.039 |
shield | +0.038 |
superhero | +0.038 |
hunter | +0.038 |
puppy | +0.038 |
Neg logit contributions | |
ases | -0.125 |
cks | -0.122 |
els | -0.120 |
ips | -0.113 |
olds | -0.112 |
Token | little |
Token ID | 1310 |
Feature activation | +8.04e+00 |
Pos logit contributions | |
barrel | +0.082 |
Bun | +0.074 |
hut | +0.071 |
he | +0.071 |
shield | +0.071 |
Neg logit contributions | |
ases | -0.318 |
olds | -0.301 |
oke | -0.299 |
els | -0.298 |
cks | -0.297 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
barrel | +0.067 |
he | +0.067 |
Bun | +0.066 |
accidentally | +0.065 |
shield | +0.063 |
Neg logit contributions | |
ases | -0.267 |
els | -0.250 |
olds | -0.241 |
ips | -0.238 |
ocol | -0.234 |
Token | found |
Token ID | 1043 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
barrel | +0.033 |
bunny | +0.032 |
puppy | +0.032 |
Bun | +0.031 |
dark | +0.031 |
Neg logit contributions | |
ases | -0.140 |
olds | -0.133 |
els | -0.132 |
cks | -0.129 |
ips | -0.126 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
barrel | +0.022 |
hut | +0.020 |
puppy | +0.019 |
Bun | +0.019 |
dark | +0.019 |
Neg logit contributions | |
ases | -0.128 |
olds | -0.122 |
els | -0.121 |
cks | -0.118 |
ips | -0.116 |
Token | special |
Token ID | 2041 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
Bun | +0.133 |
While | +0.128 |
he | +0.128 |
decided | +0.126 |
He | +0.115 |
Neg logit contributions | |
olds | -0.248 |
els | -0.240 |
its | -0.234 |
ocol | -0.229 |
ric | -0.229 |
Token | sp |
Token ID | 599 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
Bun | +0.110 |
he | +0.103 |
There | +0.103 |
While | +0.102 |
Under | +0.098 |
Neg logit contributions | |
els | -0.175 |
olds | -0.172 |
ases | -0.171 |
ocol | -0.162 |
its | -0.155 |
Token | ade |
Token ID | 671 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
Bun | +0.113 |
puppy | +0.110 |
bunny | +0.107 |
hunter | +0.104 |
Benny | +0.102 |
Neg logit contributions | |
ases | -0.097 |
els | -0.094 |
olds | -0.092 |
its | -0.090 |
ips | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
Bun | +0.079 |
dark | +0.078 |
cozy | +0.077 |
puppy | +0.073 |
bicycle | +0.073 |
Neg logit contributions | |
ases | -0.152 |
els | -0.145 |
olds | -0.138 |
ips | -0.135 |
cks | -0.132 |
Token | It |
Token ID | 632 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
barrel | +0.066 |
puppy | +0.063 |
Bun | +0.063 |
hut | +0.062 |
dark | +0.062 |
Neg logit contributions | |
ases | -0.160 |
olds | -0.151 |
els | -0.149 |
cks | -0.143 |
ips | -0.142 |
Token | little |
Token ID | 1310 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
barrel | +0.096 |
Bun | +0.089 |
hut | +0.085 |
shield | +0.083 |
cabin | +0.081 |
Neg logit contributions | |
ases | -0.274 |
olds | -0.269 |
oke | -0.267 |
avi | -0.251 |
els | -0.248 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
Bun | +0.065 |
barrel | +0.065 |
accidentally | +0.064 |
shield | +0.062 |
he | +0.062 |
Neg logit contributions | |
ases | -0.260 |
els | -0.239 |
olds | -0.238 |
ips | -0.230 |
ocol | -0.226 |
Token | named |
Token ID | 3706 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
barrel | +0.041 |
Bun | +0.039 |
bunny | +0.038 |
hut | +0.038 |
puppy | +0.038 |
Neg logit contributions | |
ases | -0.146 |
olds | -0.138 |
els | -0.138 |
cks | -0.133 |
ips | -0.129 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
barrel | +0.032 |
shield | +0.030 |
cabin | +0.030 |
hut | +0.030 |
puppy | +0.030 |
Neg logit contributions | |
ases | -0.073 |
olds | -0.069 |
els | -0.067 |
cks | -0.065 |
irs | -0.064 |
Token | found |
Token ID | 1043 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ases | +0.005 |
els | +0.005 |
olds | +0.005 |
cks | +0.005 |
its | +0.005 |
Neg logit contributions | |
barrel | -0.001 |
shield | -0.001 |
Bun | -0.001 |
bicycle | -0.001 |
cabin | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
barrel | +0.026 |
cabin | +0.024 |
hut | +0.023 |
bicycle | +0.023 |
puppy | +0.021 |
Neg logit contributions | |
ases | -0.122 |
olds | -0.115 |
els | -0.115 |
cks | -0.111 |
ips | -0.109 |
Token | colorful |
Token ID | 20239 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
decided | +0.136 |
Bun | +0.134 |
he | +0.132 |
While | +0.130 |
Curious | +0.120 |
Neg logit contributions | |
olds | -0.232 |
els | -0.222 |
its | -0.222 |
mistake | -0.222 |
ric | -0.220 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Bun | +0.111 |
he | +0.107 |
Curious | +0.106 |
late | +0.105 |
could | +0.104 |
Neg logit contributions | |
els | -0.213 |
ases | -0.199 |
ocol | -0.195 |
olds | -0.187 |
ir | -0.180 |
Token | c |
Token ID | 66 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
barrel | +0.040 |
cabin | +0.037 |
superhero | +0.037 |
Bun | +0.036 |
wolf | +0.035 |
Neg logit contributions | |
els | -0.089 |
ases | -0.089 |
cks | -0.087 |
olds | -0.081 |
ips | -0.079 |
Token | age |
Token ID | 496 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
barrel | +0.038 |
puppy | +0.037 |
dark | +0.037 |
bunny | +0.037 |
Bun | +0.037 |
Neg logit contributions | |
ases | -0.073 |
olds | -0.068 |
els | -0.067 |
cks | -0.065 |
ips | -0.064 |
Token | in |
Token ID | 287 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
barrel | +0.066 |
hut | +0.063 |
cabin | +0.063 |
superhero | +0.062 |
vest | +0.061 |
Neg logit contributions | |
ases | -0.128 |
els | -0.124 |
cks | -0.121 |
ips | -0.118 |
olds | -0.116 |
Token | a |
Token ID | 257 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
shield | +0.051 |
vest | +0.050 |
superhero | +0.048 |
cabin | +0.048 |
barrel | +0.047 |
Neg logit contributions | |
ases | -0.095 |
cks | -0.089 |
olds | -0.085 |
els | -0.083 |
its | -0.082 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
Bun | +0.090 |
barrel | +0.090 |
hut | +0.085 |
cabin | +0.081 |
decided | +0.078 |
Neg logit contributions | |
ases | -0.274 |
oke | -0.273 |
olds | -0.268 |
avi | -0.249 |
els | -0.248 |
Token | named |
Token ID | 3706 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
barrel | +0.047 |
Bun | +0.044 |
hut | +0.043 |
dark | +0.043 |
puppy | +0.043 |
Neg logit contributions | |
ases | -0.150 |
olds | -0.142 |
els | -0.141 |
cks | -0.135 |
ips | -0.132 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
barrel | +0.032 |
shield | +0.030 |
cabin | +0.030 |
hut | +0.030 |
bunny | +0.029 |
Neg logit contributions | |
ases | -0.076 |
olds | -0.073 |
els | -0.070 |
cks | -0.068 |
ips | -0.067 |
Token | found |
Token ID | 1043 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
ases | +0.009 |
els | +0.008 |
olds | +0.008 |
cks | +0.008 |
ips | +0.008 |
Neg logit contributions | |
barrel | -0.002 |
Bun | -0.002 |
shield | -0.002 |
bunny | -0.002 |
cabin | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
barrel | +0.027 |
cabin | +0.025 |
bicycle | +0.024 |
hut | +0.024 |
shield | +0.022 |
Neg logit contributions | |
ases | -0.116 |
olds | -0.111 |
els | -0.109 |
cks | -0.105 |
ips | -0.104 |
Token | warm |
Token ID | 5814 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
Bun | +0.143 |
decided | +0.140 |
he | +0.135 |
While | +0.134 |
He | +0.126 |
Neg logit contributions | |
olds | -0.233 |
els | -0.228 |
its | -0.219 |
ric | -0.219 |
mistake | -0.217 |
Token | muff |
Token ID | 27563 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
he | +0.083 |
accidentally | +0.083 |
Under | +0.082 |
decided | +0.082 |
could | +0.078 |
Neg logit contributions | |
els | -0.143 |
ases | -0.139 |
ir | -0.134 |
olds | -0.134 |
rs | -0.133 |
Token | in |
Token ID | 259 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ases | +0.011 |
els | +0.010 |
olds | +0.010 |
cks | +0.010 |
ips | +0.010 |
Neg logit contributions | |
Bun | -0.010 |
barrel | -0.010 |
puppy | -0.010 |
bunny | -0.010 |
dark | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Bun | +0.048 |
cozy | +0.044 |
superhero | +0.044 |
Benny | +0.044 |
shield | +0.043 |
Neg logit contributions | |
ases | -0.082 |
els | -0.077 |
olds | -0.074 |
cks | -0.071 |
ips | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
barrel | +0.031 |
hut | +0.029 |
puppy | +0.029 |
Bun | +0.029 |
bunny | +0.028 |
Neg logit contributions | |
ases | -0.059 |
els | -0.056 |
olds | -0.055 |
cks | -0.054 |
irs | -0.052 |
Token | small |
Token ID | 1402 |
Feature activation | +6.74e+00 |
Pos logit contributions | |
Bun | +0.087 |
barrel | +0.083 |
hut | +0.080 |
cabin | +0.075 |
he | +0.073 |
Neg logit contributions | |
ases | -0.297 |
olds | -0.284 |
oke | -0.282 |
els | -0.271 |
cks | -0.264 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Bun | +0.079 |
deserted | +0.075 |
accidentally | +0.072 |
decided | +0.072 |
he | +0.070 |
Neg logit contributions | |
ases | -0.201 |
els | -0.186 |
olds | -0.184 |
oke | -0.176 |
ips | -0.171 |
Token | named |
Token ID | 3706 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
barrel | +0.031 |
hut | +0.029 |
Bun | +0.029 |
puppy | +0.029 |
dark | +0.029 |
Neg logit contributions | |
ases | -0.103 |
olds | -0.096 |
els | -0.096 |
cks | -0.092 |
ips | -0.090 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
puppy | +0.045 |
shield | +0.045 |
bunny | +0.045 |
superhero | +0.044 |
hut | +0.044 |
Neg logit contributions | |
ases | -0.087 |
olds | -0.081 |
cks | -0.078 |
els | -0.075 |
irs | -0.073 |
Token | found |
Token ID | 1043 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
ases | +0.084 |
els | +0.078 |
olds | +0.076 |
cks | +0.075 |
its | +0.072 |
Neg logit contributions | |
barrel | -0.029 |
bunny | -0.029 |
puppy | -0.029 |
Bun | -0.028 |
hut | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
hut | +0.029 |
barrel | +0.028 |
cabin | +0.028 |
bicycle | +0.028 |
puppy | +0.026 |
Neg logit contributions | |
ases | -0.121 |
olds | -0.114 |
els | -0.112 |
cks | -0.110 |
ips | -0.107 |
Token | penny |
Token ID | 26369 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
decided | +0.147 |
Bun | +0.145 |
While | +0.133 |
he | +0.129 |
wanted | +0.126 |
Neg logit contributions | |
els | -0.230 |
olds | -0.229 |
ric | -0.220 |
its | -0.218 |
mistake | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
Bun | +0.073 |
superhero | +0.071 |
cozy | +0.070 |
cabin | +0.069 |
hut | +0.069 |
Neg logit contributions | |
els | -0.131 |
ases | -0.125 |
cks | -0.119 |
ips | -0.116 |
olds | -0.115 |
Token | This |
Token ID | 770 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
bunny | +0.052 |
puppy | +0.052 |
hut | +0.051 |
Bun | +0.051 |
barrel | +0.051 |
Neg logit contributions | |
ases | -0.160 |
olds | -0.151 |
els | -0.149 |
cks | -0.144 |
ips | -0.141 |
Token | penny |
Token ID | 26369 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Bun | +0.054 |
barrel | +0.054 |
hut | +0.053 |
dark | +0.051 |
cabin | +0.050 |
Neg logit contributions | |
ases | -0.156 |
els | -0.149 |
olds | -0.146 |
cks | -0.142 |
ips | -0.140 |
Token | was |
Token ID | 373 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
hut | +0.033 |
cabin | +0.031 |
wolf | +0.030 |
puppy | +0.030 |
barrel | +0.030 |
Neg logit contributions | |
els | -0.078 |
ases | -0.075 |
olds | -0.073 |
cks | -0.071 |
ips | -0.069 |
Token | a |
Token ID | 257 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
shield | +0.039 |
superhero | +0.038 |
vest | +0.037 |
barrel | +0.037 |
cabin | +0.036 |
Neg logit contributions | |
ases | -0.121 |
cks | -0.112 |
olds | -0.111 |
els | -0.108 |
ips | -0.105 |
Token | boy |
Token ID | 2933 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
barrel | +0.093 |
Bun | +0.092 |
hut | +0.084 |
decided | +0.082 |
cabin | +0.081 |
Neg logit contributions | |
ases | -0.281 |
olds | -0.273 |
oke | -0.269 |
els | -0.253 |
its | -0.248 |
Token | named |
Token ID | 3706 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
barrel | +0.032 |
Bun | +0.030 |
hut | +0.030 |
puppy | +0.030 |
bunny | +0.030 |
Neg logit contributions | |
ases | -0.113 |
olds | -0.106 |
els | -0.106 |
cks | -0.102 |
ips | -0.100 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
bunny | +0.040 |
hut | +0.039 |
cabin | +0.039 |
puppy | +0.039 |
shield | +0.038 |
Neg logit contributions | |
ases | -0.101 |
olds | -0.095 |
cks | -0.091 |
els | -0.090 |
irs | -0.086 |
Token | found |
Token ID | 1043 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
ases | +0.037 |
els | +0.034 |
olds | +0.034 |
cks | +0.034 |
its | +0.032 |
Neg logit contributions | |
barrel | -0.011 |
bunny | -0.011 |
Bun | -0.011 |
puppy | -0.010 |
hut | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
barrel | +0.027 |
hut | +0.027 |
cabin | +0.027 |
bicycle | +0.026 |
bunny | +0.025 |
Neg logit contributions | |
ases | -0.124 |
olds | -0.117 |
els | -0.115 |
cks | -0.113 |
ips | -0.110 |
Token | microphone |
Token ID | 21822 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
Bun | +0.146 |
decided | +0.144 |
While | +0.133 |
Curious | +0.127 |
he | +0.125 |
Neg logit contributions | |
olds | -0.237 |
els | -0.225 |
ases | -0.223 |
its | -0.222 |
ric | -0.221 |
Token | in |
Token ID | 287 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Bun | +0.109 |
cabin | +0.103 |
cozy | +0.103 |
hunter | +0.102 |
superhero | +0.101 |
Neg logit contributions | |
ases | -0.156 |
els | -0.148 |
olds | -0.139 |
cks | -0.138 |
ips | -0.136 |
Token | his |
Token ID | 465 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
barrel | +0.026 |
dark | +0.026 |
puppy | +0.025 |
bunny | +0.025 |
Bun | +0.025 |
Neg logit contributions | |
ases | -0.073 |
olds | -0.069 |
els | -0.068 |
cks | -0.066 |
ips | -0.065 |
Token | toy |
Token ID | 13373 |
Feature activation | +7.83e+00 |
Pos logit contributions | |
barrel | +0.037 |
Bun | +0.037 |
he | +0.036 |
bunny | +0.035 |
wolf | +0.034 |
Neg logit contributions | |
ases | -0.124 |
olds | -0.117 |
els | -0.116 |
cks | -0.114 |
ips | -0.112 |
Token | box |
Token ID | 3091 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
Bun | +0.084 |
restless | +0.082 |
dark | +0.082 |
cozy | +0.080 |
thief | +0.079 |
Neg logit contributions | |
ases | -0.250 |
els | -0.241 |
olds | -0.234 |
ips | -0.230 |
cks | -0.221 |
Token | little |
Token ID | 1310 |
Feature activation | +7.85e+00 |
Pos logit contributions | |
barrel | +0.094 |
Bun | +0.091 |
hut | +0.089 |
shield | +0.084 |
decided | +0.083 |
Neg logit contributions | |
ases | -0.267 |
oke | -0.263 |
olds | -0.260 |
avi | -0.247 |
ila | -0.243 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
accidentally | +0.068 |
deserted | +0.067 |
barrel | +0.065 |
shield | +0.065 |
Bun | +0.065 |
Neg logit contributions | |
ases | -0.248 |
els | -0.226 |
olds | -0.224 |
ips | -0.218 |
ocol | -0.215 |
Token | named |
Token ID | 3706 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
barrel | +0.044 |
Bun | +0.042 |
hut | +0.041 |
bunny | +0.041 |
dark | +0.041 |
Neg logit contributions | |
ases | -0.149 |
olds | -0.140 |
els | -0.139 |
cks | -0.134 |
ips | -0.130 |
Token | Amy |
Token ID | 14235 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
barrel | +0.033 |
shield | +0.032 |
cabin | +0.031 |
hunter | +0.031 |
hut | +0.031 |
Neg logit contributions | |
ases | -0.074 |
olds | -0.071 |
els | -0.068 |
cks | -0.066 |
irs | -0.065 |
Token | found |
Token ID | 1043 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
barrel | +0.010 |
Bun | +0.009 |
shield | +0.009 |
bunny | +0.009 |
bicycle | +0.009 |
Neg logit contributions | |
ases | -0.035 |
els | -0.033 |
olds | -0.033 |
cks | -0.032 |
its | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
barrel | +0.026 |
hut | +0.024 |
cabin | +0.023 |
bicycle | +0.023 |
puppy | +0.021 |
Neg logit contributions | |
ases | -0.116 |
olds | -0.110 |
els | -0.109 |
cks | -0.106 |
ips | -0.104 |
Token | big |
Token ID | 1263 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
decided | +0.137 |
While | +0.132 |
he | +0.132 |
Bun | +0.132 |
Curious | +0.123 |
Neg logit contributions | |
olds | -0.227 |
els | -0.224 |
mistake | -0.220 |
ric | -0.219 |
its | -0.218 |
Token | box |
Token ID | 3091 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
Bun | +0.089 |
he | +0.082 |
Under | +0.080 |
decided | +0.078 |
Curious | +0.076 |
Neg logit contributions | |
els | -0.191 |
ases | -0.187 |
olds | -0.174 |
ocol | -0.172 |
ips | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
Bun | +0.092 |
barrel | +0.089 |
wolf | +0.088 |
puppy | +0.088 |
hunter | +0.087 |
Neg logit contributions | |
ases | -0.178 |
els | -0.172 |
olds | -0.167 |
cks | -0.166 |
ips | -0.161 |
Token | Inside |
Token ID | 14384 |
Feature activation | +5.41e+00 |
Pos logit contributions | |
barrel | +0.060 |
Bun | +0.058 |
puppy | +0.058 |
bunny | +0.057 |
dark | +0.057 |
Neg logit contributions | |
ases | -0.147 |
olds | -0.139 |
els | -0.136 |
cks | -0.132 |
ips | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
he | +0.060 |
barrel | +0.060 |
dark | +0.059 |
bunny | +0.057 |
hut | +0.057 |
Neg logit contributions | |
ases | -0.189 |
olds | -0.178 |
els | -0.174 |
cks | -0.172 |
ips | -0.166 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ases | +0.028 |
olds | +0.026 |
els | +0.026 |
cks | +0.025 |
ips | +0.025 |
Neg logit contributions | |
bunny | -0.013 |
Bun | -0.013 |
puppy | -0.013 |
barrel | -0.013 |
dark | -0.013 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
barrel | +0.018 |
puppy | +0.018 |
Bun | +0.017 |
hut | +0.017 |
bunny | +0.017 |
Neg logit contributions | |
ases | -0.034 |
olds | -0.032 |
els | -0.031 |
cks | -0.031 |
ips | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ases | +0.045 |
els | +0.041 |
olds | +0.041 |
rs | +0.040 |
cks | +0.039 |
Neg logit contributions | |
barrel | -0.031 |
thief | -0.028 |
bicycle | -0.027 |
stole | -0.026 |
abandoned | -0.026 |
Token | ate |
Token ID | 15063 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
barrel | +0.004 |
hut | +0.004 |
Bun | +0.004 |
puppy | +0.004 |
cabin | +0.004 |
Neg logit contributions | |
ases | -0.006 |
olds | -0.006 |
els | -0.006 |
cks | -0.005 |
ips | -0.005 |
Token | ch |
Token ID | 442 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
ases | +0.033 |
olds | +0.031 |
els | +0.031 |
cks | +0.030 |
ips | +0.029 |
Neg logit contributions | |
barrel | -0.014 |
puppy | -0.014 |
Bun | -0.014 |
bunny | -0.013 |
hut | -0.013 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.70e+01 |
Pos logit contributions | |
supervision | +0.083 |
olds | +0.072 |
ric | +0.062 |
reating | +0.061 |
angles | +0.059 |
Neg logit contributions | |
little | -0.170 |
bunny | -0.169 |
dark | -0.168 |
restless | -0.167 |
hungry | -0.165 |
Token | ates |
Token ID | 689 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
olds | +0.345 |
supervision | +0.318 |
ases | +0.312 |
its | +0.304 |
humor | +0.303 |
Neg logit contributions | |
barrel | -0.342 |
hut | -0.331 |
there | -0.331 |
Bun | -0.330 |
outside | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
ases | +0.101 |
olds | +0.096 |
els | +0.094 |
cks | +0.092 |
ips | +0.091 |
Neg logit contributions | |
barrel | -0.025 |
bunny | -0.025 |
dark | -0.024 |
he | -0.024 |
puppy | -0.024 |
Token | They |
Token ID | 1119 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
barrel | +0.029 |
puppy | +0.028 |
bunny | +0.028 |
Bun | +0.027 |
hut | +0.027 |
Neg logit contributions | |
ases | -0.063 |
olds | -0.059 |
els | -0.059 |
cks | -0.057 |
ips | -0.056 |
Token | had |
Token ID | 550 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
barrel | +0.020 |
hut | +0.019 |
Bun | +0.019 |
puppy | +0.018 |
cabin | +0.018 |
Neg logit contributions | |
ases | -0.045 |
els | -0.042 |
olds | -0.041 |
cks | -0.040 |
ips | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
barrel | +0.005 |
hut | +0.004 |
bicycle | +0.004 |
Bun | +0.004 |
bunny | +0.004 |
Neg logit contributions | |
ases | -0.020 |
olds | -0.019 |
cks | -0.019 |
els | -0.019 |
ips | -0.018 |
Token | bled |
Token ID | 9342 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
ases | +0.129 |
olds | +0.120 |
els | +0.117 |
cks | +0.116 |
irs | +0.111 |
Neg logit contributions | |
bunny | -0.113 |
he | -0.112 |
barrel | -0.111 |
Bun | -0.110 |
hut | -0.110 |
Token | up |
Token ID | 510 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
ases | +0.154 |
olds | +0.148 |
cks | +0.140 |
els | +0.138 |
irs | +0.137 |
Neg logit contributions | |
bunny | -0.051 |
he | -0.050 |
there | -0.049 |
dark | -0.049 |
puppy | -0.047 |
Token | all |
Token ID | 477 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
ases | +0.099 |
olds | +0.094 |
els | +0.093 |
cks | +0.090 |
ips | +0.088 |
Neg logit contributions | |
barrel | -0.043 |
puppy | -0.041 |
Bun | -0.041 |
hut | -0.041 |
bunny | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
ases | +0.134 |
olds | +0.126 |
cks | +0.124 |
els | +0.124 |
irs | +0.119 |
Neg logit contributions | |
dark | -0.048 |
he | -0.048 |
barrel | -0.047 |
bunny | -0.047 |
there | -0.047 |
Token | ch |
Token ID | 442 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
ases | +0.128 |
olds | +0.119 |
els | +0.117 |
cks | +0.114 |
ips | +0.113 |
Neg logit contributions | |
barrel | -0.049 |
dark | -0.049 |
bunny | -0.048 |
puppy | -0.048 |
hut | -0.047 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.70e+01 |
Pos logit contributions | |
ases | +0.056 |
cks | +0.055 |
olds | +0.055 |
ric | +0.054 |
supervision | +0.054 |
Neg logit contributions | |
hut | -0.145 |
seed | -0.145 |
little | -0.142 |
barrel | -0.140 |
shield | -0.140 |
Token | ates |
Token ID | 689 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
olds | +0.355 |
ases | +0.327 |
supervision | +0.321 |
its | +0.312 |
humor | +0.312 |
Neg logit contributions | |
barrel | -0.329 |
seed | -0.321 |
hut | -0.319 |
there | -0.312 |
in | -0.306 |
Token | , |
Token ID | 11 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ases | +0.087 |
olds | +0.082 |
els | +0.082 |
cks | +0.080 |
ips | +0.078 |
Neg logit contributions | |
barrel | -0.031 |
puppy | -0.030 |
Bun | -0.030 |
dark | -0.030 |
bunny | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
barrel | +0.004 |
Bun | +0.004 |
puppy | +0.004 |
hut | +0.004 |
bunny | +0.004 |
Neg logit contributions | |
ases | -0.010 |
olds | -0.010 |
els | -0.010 |
cks | -0.009 |
ips | -0.009 |
Token | she |
Token ID | 673 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
barrel | +0.024 |
hut | +0.023 |
puppy | +0.022 |
dark | +0.022 |
Bun | +0.022 |
Neg logit contributions | |
ases | -0.059 |
olds | -0.056 |
els | -0.056 |
cks | -0.054 |
ips | -0.053 |
Token | was |
Token ID | 373 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
barrel | +0.013 |
puppy | +0.013 |
dark | +0.013 |
hut | +0.012 |
Bun | +0.012 |
Neg logit contributions | |
ases | -0.040 |
olds | -0.038 |
els | -0.038 |
cks | -0.037 |
ips | -0.036 |
Token | 't |
Token ID | 470 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ases | +0.064 |
els | +0.060 |
cks | +0.059 |
olds | +0.059 |
ips | +0.057 |
Neg logit contributions | |
puppy | -0.029 |
Bun | -0.029 |
bunny | -0.029 |
he | -0.029 |
dark | -0.028 |
Token | have |
Token ID | 423 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
ases | +0.089 |
olds | +0.083 |
els | +0.082 |
cks | +0.080 |
ips | +0.077 |
Neg logit contributions | |
barrel | -0.056 |
dark | -0.054 |
Bun | -0.054 |
bunny | -0.054 |
hut | -0.054 |
Token | all |
Token ID | 477 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ases | +0.027 |
olds | +0.025 |
els | +0.025 |
cks | +0.024 |
ips | +0.024 |
Neg logit contributions | |
barrel | -0.012 |
hut | -0.011 |
bunny | -0.011 |
Bun | -0.011 |
puppy | -0.011 |
Token | these |
Token ID | 777 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ases | +0.089 |
els | +0.084 |
cks | +0.081 |
olds | +0.081 |
ips | +0.080 |
Neg logit contributions | |
he | -0.040 |
dark | -0.039 |
there | -0.039 |
puppy | -0.038 |
barrel | -0.038 |
Token | ch |
Token ID | 442 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
ases | +0.081 |
olds | +0.075 |
els | +0.075 |
cks | +0.074 |
ips | +0.072 |
Neg logit contributions | |
barrel | -0.031 |
dark | -0.031 |
puppy | -0.030 |
bunny | -0.030 |
he | -0.030 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.70e+01 |
Pos logit contributions | |
cks | +0.058 |
ases | +0.054 |
irs | +0.053 |
olds | +0.050 |
angles | +0.048 |
Neg logit contributions | |
little | -0.140 |
restless | -0.132 |
barrel | -0.132 |
hungry | -0.131 |
long | -0.131 |
Token | ates |
Token ID | 689 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
olds | +0.355 |
horror | +0.350 |
ases | +0.330 |
its | +0.329 |
oke | +0.314 |
Neg logit contributions | |
there | -0.290 |
in | -0.287 |
outside | -0.284 |
barrel | -0.283 |
seed | -0.278 |
Token | ! |
Token ID | 0 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ases | +0.064 |
olds | +0.060 |
els | +0.060 |
cks | +0.058 |
ips | +0.057 |
Neg logit contributions | |
barrel | -0.024 |
Bun | -0.023 |
puppy | -0.023 |
hut | -0.023 |
bunny | -0.023 |
Token | Now |
Token ID | 2735 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Bun | +0.024 |
puppy | +0.024 |
bunny | +0.024 |
he | +0.023 |
barrel | +0.023 |
Neg logit contributions | |
ases | -0.051 |
els | -0.048 |
cks | -0.047 |
olds | -0.046 |
ips | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
barrel | +0.005 |
dark | +0.005 |
bunny | +0.005 |
puppy | +0.005 |
Bun | +0.005 |
Neg logit contributions | |
ases | -0.012 |
olds | -0.012 |
els | -0.011 |
cks | -0.011 |
ips | -0.011 |
Token | go |
Token ID | 467 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ases | +0.027 |
olds | +0.026 |
els | +0.025 |
cks | +0.024 |
ips | +0.024 |
Neg logit contributions | |
barrel | -0.015 |
hut | -0.014 |
dark | -0.014 |
Bun | -0.014 |
puppy | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
barrel | +0.013 |
hut | +0.012 |
Bun | +0.012 |
puppy | +0.011 |
bunny | +0.011 |
Neg logit contributions | |
olds | -0.065 |
ases | -0.065 |
els | -0.062 |
cks | -0.060 |
supervision | -0.060 |
Token | ate |
Token ID | 15063 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
hut | +0.030 |
barrel | +0.028 |
cabin | +0.028 |
dark | +0.026 |
wolf | +0.025 |
Neg logit contributions | |
ases | -0.046 |
olds | -0.044 |
els | -0.043 |
cks | -0.042 |
its | -0.041 |
Token | all |
Token ID | 477 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
barrel | +0.002 |
dark | +0.002 |
bunny | +0.002 |
puppy | +0.002 |
Bun | +0.002 |
Neg logit contributions | |
ases | -0.006 |
olds | -0.006 |
els | -0.006 |
cks | -0.006 |
ips | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ases | +0.107 |
els | +0.100 |
olds | +0.100 |
cks | +0.098 |
ips | +0.095 |
Neg logit contributions | |
he | -0.044 |
barrel | -0.044 |
dark | -0.043 |
bunny | -0.042 |
Bun | -0.042 |
Token | ch |
Token ID | 442 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
ases | +0.082 |
els | +0.079 |
olds | +0.079 |
cks | +0.076 |
its | +0.074 |
Neg logit contributions | |
barrel | -0.029 |
hut | -0.029 |
Bun | -0.028 |
puppy | -0.028 |
dark | -0.027 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.62e+01 |
Pos logit contributions | |
ases | +0.050 |
olds | +0.050 |
cks | +0.047 |
supervision | +0.047 |
irs | +0.044 |
Neg logit contributions | |
bunny | -0.141 |
he | -0.140 |
little | -0.139 |
shield | -0.135 |
seed | -0.135 |
Token | ates |
Token ID | 689 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
olds | +0.331 |
ases | +0.314 |
its | +0.292 |
supervision | +0.282 |
humor | +0.278 |
Neg logit contributions | |
barrel | -0.318 |
there | -0.311 |
outside | -0.310 |
hut | -0.308 |
in | -0.307 |
Token | and |
Token ID | 290 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ases | +0.049 |
els | +0.047 |
olds | +0.047 |
cks | +0.045 |
ips | +0.044 |
Neg logit contributions | |
barrel | -0.018 |
Bun | -0.018 |
puppy | -0.017 |
dark | -0.017 |
hut | -0.017 |
Token | sweets |
Token ID | 42402 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
barrel | +0.025 |
hut | +0.025 |
cabin | +0.024 |
dark | +0.023 |
puppy | +0.023 |
Neg logit contributions | |
ases | -0.056 |
olds | -0.054 |
els | -0.053 |
cks | -0.052 |
ips | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
barrel | +0.005 |
Bun | +0.004 |
dark | +0.004 |
puppy | +0.004 |
hut | +0.004 |
Neg logit contributions | |
ases | -0.010 |
els | -0.010 |
olds | -0.010 |
cks | -0.009 |
ips | -0.009 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
hut | +0.025 |
dark | +0.025 |
barrel | +0.025 |
bunny | +0.024 |
shield | +0.024 |
Neg logit contributions | |
ases | -0.070 |
olds | -0.069 |
els | -0.064 |
ips | -0.063 |
irs | -0.061 |
Token | giving |
Token ID | 3501 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
ases | +0.148 |
olds | +0.141 |
els | +0.136 |
ips | +0.135 |
irs | +0.132 |
Neg logit contributions | |
little | -0.083 |
bunny | -0.081 |
there | -0.080 |
puppy | -0.079 |
Bun | -0.079 |
Token | him |
Token ID | 683 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ases | +0.109 |
olds | +0.102 |
els | +0.101 |
cks | +0.099 |
ips | +0.097 |
Neg logit contributions | |
barrel | -0.053 |
puppy | -0.053 |
bunny | -0.053 |
Bun | -0.053 |
dark | -0.053 |
Token | too |
Token ID | 1165 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ases | +0.116 |
olds | +0.110 |
els | +0.108 |
cks | +0.105 |
ips | +0.102 |
Neg logit contributions | |
barrel | -0.038 |
Bun | -0.037 |
hut | -0.036 |
puppy | -0.036 |
bunny | -0.036 |
Token | many |
Token ID | 867 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ases | +0.064 |
olds | +0.062 |
els | +0.060 |
cks | +0.059 |
its | +0.057 |
Neg logit contributions | |
barrel | -0.022 |
puppy | -0.021 |
bunny | -0.021 |
Bun | -0.021 |
hut | -0.021 |
Token | ch |
Token ID | 442 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
ases | +0.085 |
olds | +0.081 |
els | +0.080 |
cks | +0.077 |
ips | +0.075 |
Neg logit contributions | |
barrel | -0.035 |
Bun | -0.034 |
hut | -0.034 |
puppy | -0.034 |
bunny | -0.034 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.62e+01 |
Pos logit contributions | |
olds | +0.066 |
ases | +0.065 |
cks | +0.063 |
irs | +0.062 |
els | +0.059 |
Neg logit contributions | |
dark | -0.134 |
there | -0.134 |
hut | -0.132 |
barrel | -0.132 |
little | -0.132 |
Token | ates |
Token ID | 689 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
olds | +0.312 |
ases | +0.286 |
its | +0.284 |
irs | +0.279 |
oke | +0.261 |
Neg logit contributions | |
there | -0.337 |
barrel | -0.334 |
hut | -0.327 |
in | -0.323 |
seed | -0.323 |
Token | ." |
Token ID | 526 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ases | +0.050 |
olds | +0.047 |
els | +0.047 |
cks | +0.045 |
ips | +0.044 |
Neg logit contributions | |
barrel | -0.020 |
Bun | -0.020 |
puppy | -0.019 |
hut | -0.019 |
dark | -0.019 |
Token | The |
Token ID | 383 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ases | +0.035 |
olds | +0.033 |
els | +0.033 |
cks | +0.032 |
ips | +0.031 |
Neg logit contributions | |
barrel | -0.016 |
dark | -0.016 |
hut | -0.016 |
bunny | -0.015 |
puppy | -0.015 |
Token | king |
Token ID | 5822 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ases | +0.078 |
olds | +0.075 |
els | +0.073 |
cks | +0.070 |
its | +0.068 |
Neg logit contributions | |
Bun | -0.027 |
barrel | -0.027 |
dark | -0.026 |
hut | -0.026 |
puppy | -0.025 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ases | +0.088 |
olds | +0.083 |
els | +0.082 |
cks | +0.080 |
ips | +0.078 |
Neg logit contributions | |
barrel | -0.037 |
dark | -0.036 |
puppy | -0.035 |
Bun | -0.035 |
hut | -0.035 |
Token | as |
Token ID | 355 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
barrel | +0.014 |
Bun | +0.014 |
dark | +0.014 |
hut | +0.014 |
bunny | +0.013 |
Neg logit contributions | |
ases | -0.040 |
olds | -0.038 |
els | -0.038 |
cks | -0.037 |
ips | -0.036 |
Token | he |
Token ID | 339 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ases | +0.030 |
olds | +0.029 |
els | +0.028 |
cks | +0.027 |
irs | +0.027 |
Neg logit contributions | |
barrel | -0.009 |
hut | -0.008 |
puppy | -0.008 |
bunny | -0.008 |
cabin | -0.008 |
Token | opened |
Token ID | 4721 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
barrel | +0.003 |
hut | +0.003 |
dark | +0.003 |
Bun | +0.003 |
puppy | +0.003 |
Neg logit contributions | |
ases | -0.009 |
olds | -0.009 |
els | -0.009 |
cks | -0.008 |
ips | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
barrel | +0.003 |
puppy | +0.003 |
bunny | +0.003 |
dark | +0.003 |
Bun | +0.003 |
Neg logit contributions | |
ases | -0.006 |
olds | -0.006 |
els | -0.006 |
cks | -0.006 |
ips | -0.006 |
Token | ch |
Token ID | 442 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
Bun | +0.003 |
he | +0.002 |
accidentally | +0.002 |
Benny | +0.002 |
bunny | +0.002 |
Neg logit contributions | |
ases | -0.005 |
olds | -0.005 |
els | -0.005 |
cks | -0.004 |
its | -0.004 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.61e+01 |
Pos logit contributions | |
ases | +0.040 |
olds | +0.039 |
cks | +0.036 |
els | +0.035 |
irs | +0.034 |
Neg logit contributions | |
barrel | -0.097 |
shield | -0.097 |
bunny | -0.096 |
little | -0.096 |
dark | -0.096 |
Token | ates |
Token ID | 689 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
olds | +0.331 |
ases | +0.300 |
its | +0.290 |
oke | +0.276 |
irs | +0.276 |
Neg logit contributions | |
barrel | -0.324 |
hut | -0.309 |
there | -0.307 |
shield | -0.304 |
in | -0.303 |
Token | and |
Token ID | 290 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
ases | +0.014 |
els | +0.013 |
olds | +0.013 |
cks | +0.013 |
ips | +0.012 |
Neg logit contributions | |
barrel | -0.005 |
Bun | -0.005 |
puppy | -0.005 |
dark | -0.005 |
bunny | -0.005 |
Token | started |
Token ID | 2067 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
barrel | +0.035 |
Bun | +0.034 |
hut | +0.034 |
dark | +0.034 |
puppy | +0.034 |
Neg logit contributions | |
ases | -0.078 |
olds | -0.074 |
els | -0.073 |
cks | -0.071 |
ips | -0.068 |
Token | eating |
Token ID | 6600 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
barrel | +0.034 |
he | +0.034 |
dark | +0.034 |
bunny | +0.034 |
puppy | +0.034 |
Neg logit contributions | |
ases | -0.102 |
olds | -0.095 |
els | -0.095 |
cks | -0.092 |
ips | -0.090 |
Token | them |
Token ID | 606 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
barrel | +0.006 |
dark | +0.006 |
bunny | +0.006 |
puppy | +0.006 |
hut | +0.006 |
Neg logit contributions | |
ases | -0.013 |
olds | -0.012 |
els | -0.012 |
cks | -0.012 |
ips | -0.011 |
Token | not |
Token ID | 407 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ases | +0.052 |
els | +0.049 |
olds | +0.049 |
cks | +0.048 |
ips | +0.047 |
Neg logit contributions | |
he | -0.021 |
barrel | -0.020 |
bunny | -0.020 |
Bun | -0.020 |
puppy | -0.020 |
Token | eat |
Token ID | 4483 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
ases | +0.072 |
olds | +0.067 |
els | +0.067 |
cks | +0.065 |
ips | +0.063 |
Neg logit contributions | |
barrel | -0.042 |
puppy | -0.041 |
bunny | -0.041 |
dark | -0.041 |
Bun | -0.041 |
Token | too |
Token ID | 1165 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ases | +0.066 |
olds | +0.062 |
els | +0.060 |
cks | +0.059 |
ips | +0.059 |
Neg logit contributions | |
dark | -0.027 |
he | -0.027 |
barrel | -0.027 |
bunny | -0.027 |
puppy | -0.026 |
Token | many |
Token ID | 867 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ases | +0.053 |
olds | +0.050 |
els | +0.049 |
cks | +0.048 |
ips | +0.047 |
Neg logit contributions | |
barrel | -0.017 |
puppy | -0.016 |
Bun | -0.016 |
bunny | -0.016 |
hut | -0.016 |
Token | ch |
Token ID | 442 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
ases | +0.073 |
olds | +0.068 |
ips | +0.067 |
cks | +0.066 |
els | +0.066 |
Neg logit contributions | |
he | -0.027 |
dark | -0.026 |
bunny | -0.025 |
barrel | -0.025 |
puppy | -0.025 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.61e+01 |
Pos logit contributions | |
olds | +0.047 |
ases | +0.046 |
supervision | +0.045 |
irs | +0.044 |
cks | +0.043 |
Neg logit contributions | |
there | -0.141 |
little | -0.140 |
seed | -0.140 |
he | -0.140 |
dark | -0.139 |
Token | ates |
Token ID | 689 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
olds | +0.318 |
its | +0.291 |
ases | +0.288 |
irs | +0.283 |
oke | +0.270 |
Neg logit contributions | |
barrel | -0.328 |
there | -0.324 |
hut | -0.317 |
in | -0.315 |
seed | -0.314 |
Token | and |
Token ID | 290 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ases | +0.059 |
olds | +0.056 |
els | +0.055 |
cks | +0.054 |
ips | +0.053 |
Neg logit contributions | |
barrel | -0.018 |
bunny | -0.018 |
puppy | -0.018 |
dark | -0.018 |
Bun | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
barrel | +0.023 |
Bun | +0.022 |
hut | +0.022 |
puppy | +0.022 |
bunny | +0.022 |
Neg logit contributions | |
ases | -0.061 |
olds | -0.058 |
els | -0.057 |
cks | -0.055 |
ips | -0.053 |
Token | friend |
Token ID | 1545 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
ases | +0.023 |
olds | +0.022 |
els | +0.022 |
cks | +0.021 |
ips | +0.021 |
Neg logit contributions | |
barrel | -0.011 |
Bun | -0.011 |
puppy | -0.011 |
dark | -0.011 |
bunny | -0.011 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ases | +0.030 |
olds | +0.028 |
els | +0.028 |
cks | +0.027 |
ips | +0.026 |
Neg logit contributions | |
barrel | -0.008 |
hut | -0.007 |
dark | -0.007 |
Bun | -0.007 |
puppy | -0.007 |
Token | we |
Token ID | 356 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ases | +0.105 |
olds | +0.099 |
els | +0.098 |
cks | +0.095 |
ips | +0.093 |
Neg logit contributions | |
barrel | -0.047 |
puppy | -0.046 |
bunny | -0.046 |
dark | -0.045 |
Bun | -0.045 |
Token | can |
Token ID | 460 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
ases | +0.043 |
olds | +0.040 |
els | +0.040 |
irs | +0.038 |
its | +0.038 |
Neg logit contributions | |
barrel | -0.022 |
Bun | -0.022 |
dark | -0.022 |
puppy | -0.021 |
hut | -0.021 |
Token | get |
Token ID | 651 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
ases | +0.019 |
olds | +0.018 |
els | +0.018 |
cks | +0.017 |
ips | +0.016 |
Neg logit contributions | |
barrel | -0.013 |
dark | -0.012 |
puppy | -0.012 |
Bun | -0.012 |
hut | -0.012 |
Token | more |
Token ID | 517 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ases | +0.089 |
olds | +0.084 |
els | +0.083 |
cks | +0.081 |
ips | +0.079 |
Neg logit contributions | |
barrel | -0.035 |
hut | -0.034 |
Bun | -0.033 |
puppy | -0.033 |
bunny | -0.032 |
Token | ch |
Token ID | 442 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
ases | +0.015 |
olds | +0.014 |
els | +0.014 |
cks | +0.014 |
ips | +0.013 |
Neg logit contributions | |
barrel | -0.006 |
dark | -0.005 |
bunny | -0.005 |
puppy | -0.005 |
Bun | -0.005 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
olds | +0.057 |
ases | +0.056 |
irs | +0.052 |
cks | +0.049 |
supervision | +0.048 |
Neg logit contributions | |
strong | -0.148 |
little | -0.148 |
bunny | -0.146 |
dark | -0.145 |
seed | -0.145 |
Token | ates |
Token ID | 689 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
olds | +0.311 |
its | +0.295 |
ases | +0.288 |
irs | +0.276 |
humor | +0.275 |
Neg logit contributions | |
barrel | -0.328 |
outside | -0.322 |
there | -0.322 |
hut | -0.316 |
in | -0.315 |
Token | later |
Token ID | 1568 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ases | +0.057 |
olds | +0.054 |
els | +0.054 |
cks | +0.052 |
ips | +0.051 |
Neg logit contributions | |
barrel | -0.022 |
Bun | -0.022 |
puppy | -0.021 |
dark | -0.021 |
hut | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
barrel | +0.019 |
bunny | +0.018 |
hut | +0.018 |
Bun | +0.018 |
shield | +0.017 |
Neg logit contributions | |
ases | -0.038 |
olds | -0.036 |
els | -0.035 |
ips | -0.034 |
cks | -0.034 |
Token | For |
Token ID | 1114 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
barrel | +0.039 |
Bun | +0.039 |
puppy | +0.039 |
bunny | +0.038 |
dark | +0.038 |
Neg logit contributions | |
ases | -0.093 |
els | -0.087 |
olds | -0.087 |
cks | -0.085 |
ips | -0.082 |
Token | now |
Token ID | 783 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ases | +0.109 |
olds | +0.105 |
els | +0.104 |
cks | +0.100 |
its | +0.099 |
Neg logit contributions | |
Bun | -0.034 |
dark | -0.034 |
there | -0.033 |
bunny | -0.032 |
puppy | -0.032 |
Token | L |
Token ID | 43 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
ases | +0.083 |
olds | +0.079 |
els | +0.078 |
cks | +0.077 |
irs | +0.074 |
Neg logit contributions | |
bunny | -0.040 |
puppy | -0.039 |
dark | -0.039 |
he | -0.038 |
barrel | -0.037 |
Token | ily |
Token ID | 813 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
ases | +0.262 |
els | +0.254 |
cks | +0.251 |
olds | +0.247 |
irs | +0.233 |
Neg logit contributions | |
he | -0.175 |
barrel | -0.171 |
there | -0.168 |
bunny | -0.168 |
Bun | -0.167 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ases | +0.117 |
olds | +0.110 |
els | +0.109 |
cks | +0.106 |
ips | +0.104 |
Neg logit contributions | |
barrel | -0.046 |
hut | -0.044 |
dark | -0.044 |
Bun | -0.044 |
puppy | -0.043 |
Token | these |
Token ID | 777 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ases | +0.068 |
olds | +0.064 |
els | +0.063 |
cks | +0.061 |
ips | +0.060 |
Neg logit contributions | |
barrel | -0.041 |
bunny | -0.040 |
puppy | -0.040 |
he | -0.040 |
dark | -0.040 |
Token | ch |
Token ID | 442 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
ases | +0.042 |
olds | +0.038 |
els | +0.038 |
cks | +0.036 |
ips | +0.035 |
Neg logit contributions | |
barrel | -0.044 |
Bun | -0.043 |
dark | -0.043 |
hut | -0.043 |
puppy | -0.043 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
olds | +0.079 |
supervision | +0.078 |
cks | +0.071 |
irs | +0.070 |
ases | +0.069 |
Neg logit contributions | |
bunny | -0.138 |
wolf | -0.129 |
bear | -0.128 |
little | -0.127 |
hunter | -0.126 |
Token | ates |
Token ID | 689 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
olds | +0.336 |
supervision | +0.304 |
irs | +0.297 |
ases | +0.295 |
apology | +0.289 |
Neg logit contributions | |
barrel | -0.289 |
there | -0.284 |
bunny | -0.281 |
carrot | -0.280 |
in | -0.280 |
Token | are |
Token ID | 389 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
ases | +0.057 |
olds | +0.054 |
els | +0.053 |
cks | +0.052 |
ips | +0.050 |
Neg logit contributions | |
barrel | -0.030 |
bunny | -0.030 |
dark | -0.030 |
puppy | -0.030 |
Bun | -0.029 |
Token | bitter |
Token ID | 12922 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ases | +0.100 |
olds | +0.095 |
els | +0.094 |
cks | +0.091 |
ips | +0.090 |
Neg logit contributions | |
barrel | -0.027 |
dark | -0.027 |
bunny | -0.026 |
puppy | -0.026 |
Bun | -0.026 |
Token | ," |
Token ID | 553 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
ases | +0.047 |
olds | +0.044 |
els | +0.044 |
cks | +0.041 |
its | +0.041 |
Neg logit contributions | |
barrel | -0.021 |
Bun | -0.021 |
hut | -0.020 |
puppy | -0.020 |
cabin | -0.019 |
Token | he |
Token ID | 339 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
ases | +0.140 |
olds | +0.135 |
els | +0.131 |
cks | +0.128 |
ips | +0.124 |
Neg logit contributions | |
barrel | -0.045 |
hut | -0.043 |
Bun | -0.043 |
puppy | -0.042 |
bunny | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
barrel | +0.001 |
puppy | +0.001 |
hut | +0.001 |
bunny | +0.001 |
dark | +0.001 |
Neg logit contributions | |
ases | -0.002 |
olds | -0.002 |
els | -0.002 |
cks | -0.002 |
ips | -0.002 |
Token | filled |
Token ID | 5901 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
ases | +0.042 |
els | +0.040 |
olds | +0.040 |
cks | +0.039 |
irs | +0.037 |
Neg logit contributions | |
barrel | -0.016 |
bunny | -0.015 |
puppy | -0.015 |
Bun | -0.015 |
hut | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ases | +0.022 |
els | +0.021 |
olds | +0.021 |
cks | +0.021 |
ips | +0.020 |
Neg logit contributions | |
barrel | -0.009 |
bunny | -0.008 |
puppy | -0.008 |
hut | -0.008 |
dark | -0.008 |
Token | delicious |
Token ID | 12625 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
ases | +0.071 |
olds | +0.067 |
els | +0.066 |
cks | +0.064 |
ips | +0.062 |
Neg logit contributions | |
barrel | -0.035 |
Bun | -0.033 |
bunny | -0.033 |
puppy | -0.033 |
hut | -0.033 |
Token | ch |
Token ID | 442 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
ases | +0.022 |
els | +0.022 |
olds | +0.021 |
cks | +0.020 |
irs | +0.020 |
Neg logit contributions | |
Bun | -0.011 |
barrel | -0.010 |
he | -0.010 |
dark | -0.010 |
hut | -0.010 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
olds | +0.049 |
ases | +0.049 |
cks | +0.043 |
supervision | +0.041 |
els | +0.038 |
Neg logit contributions | |
little | -0.135 |
bunny | -0.135 |
hut | -0.134 |
dark | -0.134 |
barrel | -0.133 |
Token | ates |
Token ID | 689 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
olds | +0.305 |
ases | +0.289 |
its | +0.267 |
oke | +0.250 |
supervision | +0.249 |
Neg logit contributions | |
barrel | -0.350 |
hut | -0.342 |
there | -0.340 |
seed | -0.335 |
outside | -0.334 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ases | +0.056 |
olds | +0.053 |
els | +0.053 |
cks | +0.052 |
ips | +0.050 |
Neg logit contributions | |
barrel | -0.021 |
Bun | -0.021 |
dark | -0.020 |
hut | -0.020 |
puppy | -0.020 |
Token | He |
Token ID | 679 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
barrel | +0.026 |
dark | +0.026 |
hut | +0.026 |
puppy | +0.025 |
bunny | +0.025 |
Neg logit contributions | |
ases | -0.065 |
olds | -0.062 |
els | -0.060 |
cks | -0.059 |
ips | -0.058 |
Token | was |
Token ID | 373 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
barrel | +0.027 |
dark | +0.026 |
hut | +0.026 |
puppy | +0.025 |
Bun | +0.025 |
Neg logit contributions | |
ases | -0.071 |
olds | -0.067 |
els | -0.066 |
cks | -0.064 |
ips | -0.062 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
barrel | +0.001 |
dark | +0.001 |
puppy | +0.001 |
bunny | +0.001 |
Bun | +0.001 |
Neg logit contributions | |
ases | -0.008 |
olds | -0.007 |
els | -0.007 |
cks | -0.007 |
ips | -0.007 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
puppy | +0.015 |
barrel | +0.015 |
Bun | +0.014 |
hut | +0.014 |
bunny | +0.014 |
Neg logit contributions | |
ases | -0.052 |
els | -0.050 |
olds | -0.049 |
cks | -0.048 |
ips | -0.047 |
Token | all |
Token ID | 477 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ases | +0.021 |
olds | +0.020 |
els | +0.019 |
cks | +0.019 |
ips | +0.019 |
Neg logit contributions | |
dark | -0.007 |
barrel | -0.007 |
bunny | -0.007 |
hut | -0.007 |
he | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ases | +0.048 |
olds | +0.045 |
els | +0.044 |
cks | +0.043 |
ips | +0.042 |
Neg logit contributions | |
dark | -0.022 |
barrel | -0.022 |
he | -0.022 |
hut | -0.021 |
bunny | -0.021 |
Token | tasty |
Token ID | 25103 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ases | +0.069 |
olds | +0.066 |
els | +0.065 |
cks | +0.063 |
ips | +0.061 |
Neg logit contributions | |
barrel | -0.029 |
Bun | -0.028 |
bunny | -0.028 |
puppy | -0.028 |
hut | -0.028 |
Token | ch |
Token ID | 442 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
ases | +0.018 |
olds | +0.017 |
els | +0.017 |
cks | +0.017 |
ips | +0.016 |
Neg logit contributions | |
barrel | -0.008 |
puppy | -0.008 |
bunny | -0.008 |
dark | -0.008 |
hut | -0.008 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
ases | +0.036 |
olds | +0.035 |
cks | +0.030 |
irs | +0.026 |
rs | +0.025 |
Neg logit contributions | |
hut | -0.134 |
barrel | -0.131 |
there | -0.129 |
shield | -0.129 |
thief | -0.129 |
Token | ates |
Token ID | 689 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
olds | +0.327 |
ases | +0.300 |
its | +0.280 |
humor | +0.279 |
supervision | +0.278 |
Neg logit contributions | |
barrel | -0.326 |
hut | -0.317 |
seed | -0.312 |
there | -0.312 |
outside | -0.304 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ases | +0.031 |
els | +0.030 |
olds | +0.029 |
cks | +0.029 |
ips | +0.028 |
Neg logit contributions | |
Bun | -0.011 |
barrel | -0.011 |
puppy | -0.011 |
bunny | -0.010 |
dark | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
barrel | +0.016 |
dark | +0.016 |
bunny | +0.015 |
hut | +0.015 |
he | +0.015 |
Neg logit contributions | |
ases | -0.060 |
olds | -0.057 |
els | -0.056 |
cks | -0.055 |
ips | -0.054 |
Token | She |
Token ID | 1375 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
barrel | +0.027 |
dark | +0.026 |
puppy | +0.026 |
bunny | +0.026 |
hut | +0.026 |
Neg logit contributions | |
ases | -0.060 |
olds | -0.058 |
els | -0.056 |
cks | -0.054 |
ips | -0.054 |
Token | couldn |
Token ID | 3521 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
barrel | +0.033 |
hut | +0.032 |
dark | +0.032 |
puppy | +0.032 |
Bun | +0.031 |
Neg logit contributions | |
ases | -0.085 |
els | -0.081 |
olds | -0.081 |
cks | -0.078 |
its | -0.075 |
Token | box |
Token ID | 3091 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ases | +0.027 |
els | +0.025 |
olds | +0.025 |
cks | +0.024 |
ips | +0.024 |
Neg logit contributions | |
Bun | -0.006 |
barrel | -0.006 |
puppy | -0.006 |
bunny | -0.006 |
dark | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
barrel | +0.011 |
dark | +0.011 |
hut | +0.011 |
he | +0.011 |
bunny | +0.010 |
Neg logit contributions | |
ases | -0.037 |
olds | -0.035 |
els | -0.035 |
cks | -0.034 |
irs | -0.034 |
Token | share |
Token ID | 2648 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
barrel | +0.029 |
dark | +0.028 |
bunny | +0.028 |
puppy | +0.028 |
hut | +0.028 |
Neg logit contributions | |
ases | -0.057 |
olds | -0.053 |
els | -0.053 |
cks | -0.051 |
ips | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
ases | +0.072 |
olds | +0.067 |
els | +0.064 |
ips | +0.064 |
irs | +0.064 |
Neg logit contributions | |
there | -0.024 |
dark | -0.022 |
he | -0.022 |
a | -0.022 |
bunny | -0.022 |
Token | ch |
Token ID | 442 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
ases | +0.107 |
els | +0.103 |
olds | +0.102 |
cks | +0.100 |
its | +0.094 |
Neg logit contributions | |
Bun | -0.042 |
accidentally | -0.041 |
he | -0.038 |
puppy | -0.037 |
bunny | -0.036 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
ases | +0.052 |
olds | +0.051 |
supervision | +0.045 |
cks | +0.044 |
irs | +0.043 |
Neg logit contributions | |
barrel | -0.143 |
shield | -0.142 |
hut | -0.141 |
little | -0.140 |
hunter | -0.137 |
Token | ates |
Token ID | 689 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
olds | +0.325 |
supervision | +0.300 |
ases | +0.294 |
horror | +0.289 |
humor | +0.289 |
Neg logit contributions | |
barrel | -0.311 |
hut | -0.299 |
seed | -0.299 |
whole | -0.284 |
cave | -0.279 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ases | +0.066 |
olds | +0.062 |
els | +0.061 |
cks | +0.060 |
ips | +0.060 |
Neg logit contributions | |
he | -0.015 |
barrel | -0.014 |
bunny | -0.014 |
hut | -0.013 |
puppy | -0.013 |
Token | They |
Token ID | 1119 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
barrel | +0.022 |
bunny | +0.021 |
puppy | +0.021 |
Bun | +0.021 |
dark | +0.021 |
Neg logit contributions | |
ases | -0.048 |
olds | -0.045 |
els | -0.045 |
cks | -0.043 |
ips | -0.042 |
Token | are |
Token ID | 389 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
barrel | +0.024 |
bunny | +0.024 |
dark | +0.024 |
he | +0.024 |
hut | +0.024 |
Neg logit contributions | |
ases | -0.038 |
olds | -0.036 |
els | -0.036 |
cks | -0.034 |
ips | -0.034 |
Token | happy |
Token ID | 3772 |
Feature activation | +7.91e-03 |
Pos logit contributions | |
ases | +0.051 |
olds | +0.048 |
els | +0.048 |
cks | +0.047 |
ips | +0.045 |
Neg logit contributions | |
barrel | -0.019 |
Bun | -0.019 |
puppy | -0.018 |
bunny | -0.018 |
hut | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
barrel | +0.017 |
bunny | +0.016 |
puppy | +0.016 |
dark | +0.016 |
hut | +0.016 |
Neg logit contributions | |
ases | -0.046 |
olds | -0.044 |
els | -0.043 |
cks | -0.042 |
ips | -0.041 |
Token | they |
Token ID | 484 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
barrel | +0.013 |
hut | +0.012 |
dark | +0.012 |
puppy | +0.012 |
cabin | +0.012 |
Neg logit contributions | |
ases | -0.033 |
olds | -0.031 |
els | -0.030 |
cks | -0.029 |
ips | -0.029 |
Token | shared |
Token ID | 4888 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
dark | +0.002 |
hut | +0.002 |
barrel | +0.002 |
wolf | +0.002 |
puppy | +0.002 |
Neg logit contributions | |
ases | -0.004 |
els | -0.004 |
olds | -0.003 |
cks | -0.003 |
ips | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
ases | +0.045 |
olds | +0.042 |
els | +0.041 |
cks | +0.040 |
ips | +0.040 |
Neg logit contributions | |
dark | -0.016 |
barrel | -0.016 |
he | -0.015 |
there | -0.015 |
puppy | -0.015 |
Token | ch |
Token ID | 442 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
ases | +0.111 |
olds | +0.105 |
els | +0.104 |
cks | +0.100 |
ips | +0.098 |
Neg logit contributions | |
Bun | -0.048 |
barrel | -0.048 |
hut | -0.047 |
bunny | -0.046 |
puppy | -0.046 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
cks | +0.057 |
ases | +0.055 |
irs | +0.053 |
els | +0.047 |
supervision | +0.046 |
Neg logit contributions | |
little | -0.132 |
barrel | -0.124 |
bunny | -0.120 |
toy | -0.120 |
boy | -0.119 |
Token | ates |
Token ID | 689 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
horror | +0.315 |
supervision | +0.315 |
olds | +0.313 |
irs | +0.300 |
ases | +0.295 |
Neg logit contributions | |
barrel | -0.276 |
seed | -0.265 |
in | -0.263 |
outside | -0.257 |
there | -0.255 |
Token | with |
Token ID | 351 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
ases | +0.075 |
olds | +0.069 |
els | +0.069 |
cks | +0.068 |
irs | +0.067 |
Neg logit contributions | |
he | -0.021 |
barrel | -0.020 |
bunny | -0.019 |
while | -0.018 |
puppy | -0.018 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ases | +0.112 |
olds | +0.104 |
els | +0.104 |
cks | +0.102 |
ips | +0.101 |
Neg logit contributions | |
he | -0.066 |
puppy | -0.064 |
dark | -0.063 |
a | -0.063 |
little | -0.063 |
Token | in |
Token ID | 287 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
ases | +0.050 |
olds | +0.047 |
els | +0.046 |
cks | +0.045 |
ips | +0.044 |
Neg logit contributions | |
barrel | -0.017 |
Bun | -0.017 |
dark | -0.017 |
puppy | -0.017 |
bunny | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ases | +0.143 |
olds | +0.141 |
els | +0.137 |
its | +0.135 |
cks | +0.134 |
Neg logit contributions | |
there | -0.047 |
dark | -0.044 |
little | -0.043 |
a | -0.042 |
he | -0.042 |
Token | reward |
Token ID | 6721 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
Bun | +0.029 |
barrel | +0.026 |
dark | +0.026 |
he | +0.025 |
cozy | +0.025 |
Neg logit contributions | |
ases | -0.081 |
els | -0.077 |
olds | -0.075 |
cks | -0.071 |
ips | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
barrel | +0.005 |
puppy | +0.005 |
bunny | +0.005 |
Bun | +0.005 |
dark | +0.005 |
Neg logit contributions | |
ases | -0.015 |
olds | -0.014 |
els | -0.014 |
cks | -0.014 |
ips | -0.013 |
Token | It |
Token ID | 632 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
barrel | +0.066 |
dark | +0.065 |
hut | +0.063 |
shield | +0.061 |
bunny | +0.061 |
Neg logit contributions | |
ases | -0.133 |
olds | -0.127 |
els | -0.122 |
cks | -0.117 |
irs | -0.117 |
Token | was |
Token ID | 373 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
barrel | +0.041 |
puppy | +0.039 |
dark | +0.039 |
hut | +0.038 |
Bun | +0.038 |
Neg logit contributions | |
ases | -0.120 |
olds | -0.113 |
els | -0.112 |
cks | -0.109 |
its | -0.106 |
Token | ch |
Token ID | 442 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
barrel | +0.015 |
bunny | +0.014 |
puppy | +0.014 |
hut | +0.013 |
Bun | +0.013 |
Neg logit contributions | |
ases | -0.062 |
olds | -0.059 |
els | -0.059 |
cks | -0.057 |
ips | -0.056 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
ases | +0.059 |
olds | +0.057 |
els | +0.054 |
cks | +0.053 |
irs | +0.049 |
Neg logit contributions | |
dark | -0.098 |
bunny | -0.097 |
barrel | -0.096 |
Bun | -0.096 |
hut | -0.095 |
Token | ates |
Token ID | 689 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
olds | +0.305 |
ases | +0.276 |
its | +0.266 |
irs | +0.252 |
oke | +0.244 |
Neg logit contributions | |
there | -0.340 |
barrel | -0.332 |
in | -0.323 |
a | -0.323 |
outside | -0.320 |
Token | and |
Token ID | 290 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
barrel | +0.005 |
puppy | +0.005 |
Bun | +0.005 |
hut | +0.005 |
dark | +0.005 |
Neg logit contributions | |
ases | -0.013 |
els | -0.012 |
olds | -0.012 |
cks | -0.012 |
ips | -0.012 |
Token | sweets |
Token ID | 42402 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
barrel | +0.036 |
hut | +0.035 |
puppy | +0.035 |
Bun | +0.034 |
dark | +0.034 |
Neg logit contributions | |
ases | -0.093 |
els | -0.088 |
olds | -0.087 |
cks | -0.086 |
ips | -0.082 |
Token | ! |
Token ID | 0 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
barrel | +0.017 |
hut | +0.017 |
Bun | +0.017 |
dark | +0.016 |
puppy | +0.016 |
Neg logit contributions | |
ases | -0.038 |
els | -0.037 |
olds | -0.036 |
cks | -0.035 |
ips | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
barrel | +0.038 |
dark | +0.037 |
hut | +0.036 |
bunny | +0.036 |
puppy | +0.036 |
Neg logit contributions | |
ases | -0.081 |
olds | -0.076 |
els | -0.075 |
cks | -0.073 |
ips | -0.071 |
Token | temper |
Token ID | 4124 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Bun | +0.027 |
barrel | +0.026 |
dark | +0.026 |
hut | +0.026 |
bunny | +0.026 |
Neg logit contributions | |
ases | -0.051 |
olds | -0.048 |
els | -0.047 |
cks | -0.044 |
its | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
barrel | +0.038 |
hut | +0.037 |
Bun | +0.037 |
bunny | +0.037 |
puppy | +0.036 |
Neg logit contributions | |
ases | -0.095 |
olds | -0.091 |
els | -0.089 |
cks | -0.086 |
ips | -0.084 |
Token | often |
Token ID | 1690 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
hut | +0.040 |
barrel | +0.038 |
bunny | +0.036 |
cabin | +0.035 |
puppy | +0.034 |
Neg logit contributions | |
olds | -0.124 |
ases | -0.124 |
els | -0.118 |
cks | -0.112 |
its | -0.110 |
Token | threw |
Token ID | 9617 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
barrel | +0.027 |
hut | +0.025 |
bunny | +0.025 |
Bun | +0.025 |
puppy | +0.024 |
Neg logit contributions | |
ases | -0.081 |
olds | -0.076 |
els | -0.075 |
cks | -0.073 |
ips | -0.071 |
Token | temper |
Token ID | 4124 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
barrel | +0.007 |
dark | +0.007 |
puppy | +0.007 |
bunny | +0.007 |
Bun | +0.007 |
Neg logit contributions | |
ases | -0.019 |
olds | -0.018 |
els | -0.018 |
cks | -0.017 |
ips | -0.017 |
Token | tant |
Token ID | 24246 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
barrel | +0.003 |
dark | +0.003 |
puppy | +0.003 |
bunny | +0.003 |
he | +0.003 |
Neg logit contributions | |
ases | -0.005 |
olds | -0.005 |
els | -0.004 |
cks | -0.004 |
ips | -0.004 |
Token | rums |
Token ID | 45241 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
ases | +0.263 |
ips | +0.258 |
olds | +0.228 |
irs | +0.219 |
ucks | +0.218 |
Neg logit contributions | |
Bun | -0.360 |
he | -0.346 |
wolf | -0.329 |
wanted | -0.327 |
barrel | -0.321 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
ases | +0.101 |
els | +0.095 |
olds | +0.095 |
cks | +0.092 |
ips | +0.090 |
Neg logit contributions | |
barrel | -0.032 |
hut | -0.030 |
dark | -0.030 |
bunny | -0.029 |
puppy | -0.029 |
Token | One |
Token ID | 1881 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
bunny | +0.040 |
barrel | +0.039 |
puppy | +0.039 |
Bun | +0.038 |
hut | +0.038 |
Neg logit contributions | |
ases | -0.095 |
olds | -0.093 |
els | -0.089 |
cks | -0.086 |
ips | -0.084 |
Token | day |
Token ID | 1110 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
Bun | +0.021 |
hut | +0.020 |
barrel | +0.019 |
puppy | +0.018 |
shield | +0.017 |
Neg logit contributions | |
ases | -0.052 |
olds | -0.050 |
els | -0.048 |
its | -0.045 |
ips | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
bunny | +0.075 |
barrel | +0.074 |
Bun | +0.073 |
hut | +0.072 |
puppy | +0.071 |
Neg logit contributions | |
olds | -0.131 |
ases | -0.129 |
els | -0.124 |
irs | -0.115 |
cks | -0.115 |
Token | she |
Token ID | 673 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
barrel | +0.015 |
hut | +0.014 |
shield | +0.014 |
Bun | +0.014 |
hunter | +0.014 |
Neg logit contributions | |
ases | -0.032 |
olds | -0.032 |
els | -0.030 |
ips | -0.029 |
cks | -0.028 |
Token | paid |
Token ID | 3432 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
barrel | +0.025 |
Bun | +0.025 |
dark | +0.025 |
puppy | +0.024 |
hut | +0.024 |
Neg logit contributions | |
ases | -0.059 |
els | -0.056 |
olds | -0.056 |
cks | -0.053 |
its | -0.052 |
Token | for |
Token ID | 329 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
ases | +0.198 |
els | +0.185 |
olds | +0.182 |
cks | +0.182 |
ips | +0.177 |
Neg logit contributions | |
he | -0.083 |
Bun | -0.079 |
puppy | -0.077 |
bunny | -0.077 |
little | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ases | +0.177 |
els | +0.164 |
olds | +0.162 |
cks | +0.160 |
its | +0.157 |
Neg logit contributions | |
he | -0.059 |
dark | -0.056 |
puppy | -0.055 |
bunny | -0.054 |
Bun | -0.054 |
Token | ch |
Token ID | 442 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
ases | +0.057 |
olds | +0.056 |
els | +0.054 |
its | +0.051 |
cks | +0.051 |
Neg logit contributions | |
Bun | -0.029 |
barrel | -0.027 |
hut | -0.027 |
dark | -0.026 |
Benny | -0.026 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
ases | +0.048 |
cks | +0.043 |
irs | +0.041 |
olds | +0.040 |
els | +0.036 |
Neg logit contributions | |
little | -0.135 |
bunny | -0.133 |
barrel | -0.131 |
superhero | -0.130 |
thief | -0.129 |
Token | ates |
Token ID | 689 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
olds | +0.317 |
irs | +0.291 |
ases | +0.290 |
its | +0.290 |
horror | +0.274 |
Neg logit contributions | |
barrel | -0.290 |
seed | -0.276 |
carrot | -0.275 |
hut | -0.271 |
whole | -0.270 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ases | +0.060 |
olds | +0.057 |
els | +0.057 |
cks | +0.055 |
ips | +0.054 |
Neg logit contributions | |
barrel | -0.022 |
Bun | -0.022 |
dark | -0.022 |
puppy | -0.022 |
bunny | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
barrel | +0.018 |
hut | +0.017 |
dark | +0.017 |
Bun | +0.017 |
bunny | +0.017 |
Neg logit contributions | |
ases | -0.040 |
olds | -0.038 |
els | -0.038 |
cks | -0.036 |
ips | -0.035 |
Token | two |
Token ID | 734 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ases | +0.043 |
olds | +0.043 |
els | +0.041 |
cks | +0.038 |
its | +0.038 |
Neg logit contributions | |
Bun | -0.023 |
barrel | -0.021 |
hut | -0.021 |
Benny | -0.020 |
dark | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
ases | +0.045 |
olds | +0.041 |
els | +0.041 |
cks | +0.041 |
ips | +0.039 |
Neg logit contributions | |
he | -0.026 |
barrel | -0.026 |
bunny | -0.026 |
dark | -0.026 |
puppy | -0.026 |
Token | son |
Token ID | 3367 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
ases | +0.062 |
olds | +0.059 |
els | +0.058 |
cks | +0.055 |
ips | +0.054 |
Neg logit contributions | |
Bun | -0.034 |
barrel | -0.033 |
hut | -0.033 |
dark | -0.032 |
he | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ases | +0.018 |
olds | +0.017 |
els | +0.017 |
cks | +0.017 |
ips | +0.016 |
Neg logit contributions | |
barrel | -0.008 |
dark | -0.008 |
hut | -0.008 |
Bun | -0.008 |
puppy | -0.008 |
Token | eating |
Token ID | 6600 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ases | +0.017 |
olds | +0.016 |
els | +0.016 |
cks | +0.016 |
ips | +0.015 |
Neg logit contributions | |
barrel | -0.007 |
Bun | -0.007 |
hut | -0.007 |
bunny | -0.006 |
puppy | -0.006 |
Token | our |
Token ID | 674 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
barrel | +0.008 |
Bun | +0.008 |
puppy | +0.008 |
hut | +0.008 |
bunny | +0.008 |
Neg logit contributions | |
ases | -0.019 |
els | -0.018 |
olds | -0.017 |
cks | -0.017 |
ips | -0.016 |
Token | ch |
Token ID | 442 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
ases | +0.094 |
olds | +0.089 |
els | +0.088 |
cks | +0.086 |
ips | +0.084 |
Neg logit contributions | |
barrel | -0.031 |
bunny | -0.030 |
dark | -0.030 |
puppy | -0.030 |
Bun | -0.029 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
olds | +0.044 |
ases | +0.043 |
cks | +0.042 |
irs | +0.038 |
supervision | +0.037 |
Neg logit contributions | |
little | -0.121 |
superhero | -0.119 |
bunny | -0.118 |
barrel | -0.117 |
shield | -0.116 |
Token | ates |
Token ID | 689 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
olds | +0.316 |
ases | +0.295 |
irs | +0.292 |
its | +0.289 |
horror | +0.288 |
Neg logit contributions | |
barrel | -0.277 |
seed | -0.264 |
whole | -0.260 |
outside | -0.260 |
hut | -0.259 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ases | +0.026 |
els | +0.024 |
olds | +0.024 |
cks | +0.023 |
ips | +0.023 |
Neg logit contributions | |
Bun | -0.012 |
barrel | -0.011 |
puppy | -0.011 |
hut | -0.011 |
dark | -0.011 |
Token | |
Token ID | 220 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
ases | +0.056 |
olds | +0.054 |
els | +0.052 |
cks | +0.051 |
ips | +0.050 |
Neg logit contributions | |
barrel | -0.029 |
hut | -0.028 |
dark | -0.028 |
bunny | -0.027 |
puppy | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
ases | +0.201 |
els | +0.194 |
cks | +0.183 |
olds | +0.180 |
ocol | +0.178 |
Neg logit contributions | |
he | -0.045 |
Bun | -0.040 |
there | -0.038 |
little | -0.036 |
Benny | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
ases | +0.173 |
els | +0.164 |
olds | +0.157 |
cks | +0.156 |
ips | +0.150 |
Neg logit contributions | |
Bun | -0.066 |
he | -0.066 |
puppy | -0.063 |
bunny | -0.063 |
little | -0.062 |
Token | started |
Token ID | 2067 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
barrel | +0.041 |
Bun | +0.040 |
dark | +0.040 |
puppy | +0.039 |
hut | +0.039 |
Neg logit contributions | |
ases | -0.116 |
els | -0.113 |
olds | -0.110 |
cks | -0.106 |
irs | -0.106 |
Token | eating |
Token ID | 6600 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
barrel | +0.036 |
dark | +0.035 |
bunny | +0.035 |
hut | +0.035 |
puppy | +0.035 |
Neg logit contributions | |
ases | -0.124 |
olds | -0.117 |
els | -0.116 |
cks | -0.113 |
ips | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
barrel | +0.018 |
dark | +0.017 |
bunny | +0.017 |
hut | +0.017 |
puppy | +0.017 |
Neg logit contributions | |
ases | -0.050 |
olds | -0.047 |
els | -0.046 |
cks | -0.045 |
ips | -0.044 |
Token | delicious |
Token ID | 12625 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
ases | +0.051 |
els | +0.048 |
olds | +0.048 |
cks | +0.047 |
ips | +0.045 |
Neg logit contributions | |
barrel | -0.015 |
Bun | -0.015 |
hut | -0.015 |
puppy | -0.015 |
bunny | -0.015 |
Token | ch |
Token ID | 442 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
ases | +0.001 |
olds | +0.001 |
els | +0.001 |
cks | +0.001 |
ips | +0.001 |
Neg logit contributions | |
barrel | -0.000 |
dark | -0.000 |
bunny | -0.000 |
puppy | -0.000 |
hut | -0.000 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
ases | +0.039 |
cks | +0.034 |
olds | +0.033 |
irs | +0.029 |
rs | +0.029 |
Neg logit contributions | |
barrel | -0.109 |
little | -0.108 |
seed | -0.106 |
thief | -0.105 |
hut | -0.104 |
Token | ates |
Token ID | 689 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
olds | +0.294 |
ases | +0.284 |
humor | +0.267 |
its | +0.264 |
supervision | +0.258 |
Neg logit contributions | |
barrel | -0.321 |
hut | -0.302 |
outside | -0.300 |
seed | -0.299 |
whole | -0.288 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
ases | +0.015 |
els | +0.014 |
olds | +0.014 |
cks | +0.013 |
ips | +0.013 |
Neg logit contributions | |
barrel | -0.005 |
Bun | -0.005 |
puppy | -0.005 |
dark | -0.005 |
bunny | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
puppy | +0.027 |
dark | +0.026 |
he | +0.026 |
there | +0.026 |
Bun | +0.025 |
Neg logit contributions | |
ases | -0.083 |
els | -0.077 |
olds | -0.074 |
cks | -0.073 |
ips | -0.071 |
Token | was |
Token ID | 373 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
barrel | +0.033 |
hut | +0.031 |
puppy | +0.031 |
dark | +0.031 |
Bun | +0.031 |
Neg logit contributions | |
ases | -0.110 |
olds | -0.105 |
els | -0.105 |
cks | -0.101 |
ips | -0.099 |
Token | so |
Token ID | 523 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
barrel | +0.005 |
puppy | +0.005 |
Bun | +0.005 |
bunny | +0.005 |
hut | +0.005 |
Neg logit contributions | |
ases | -0.032 |
olds | -0.031 |
els | -0.031 |
cks | -0.030 |
ips | -0.029 |
Token | ates |
Token ID | 689 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
olds | +0.295 |
ases | +0.265 |
its | +0.263 |
oke | +0.248 |
humor | +0.242 |
Neg logit contributions | |
barrel | -0.315 |
hut | -0.307 |
there | -0.301 |
outside | -0.297 |
seed | -0.293 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Bun | +0.016 |
barrel | +0.016 |
puppy | +0.016 |
dark | +0.015 |
hut | +0.015 |
Neg logit contributions | |
ases | -0.040 |
els | -0.039 |
olds | -0.038 |
cks | -0.037 |
ips | -0.036 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
barrel | +0.032 |
puppy | +0.032 |
dark | +0.031 |
hut | +0.031 |
Bun | +0.031 |
Neg logit contributions | |
ases | -0.089 |
olds | -0.085 |
els | -0.082 |
cks | -0.081 |
ips | -0.079 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ases | +0.076 |
els | +0.073 |
olds | +0.073 |
cks | +0.070 |
ips | +0.068 |
Neg logit contributions | |
barrel | -0.026 |
dark | -0.026 |
puppy | -0.026 |
Bun | -0.025 |
hut | -0.025 |
Token | ch |
Token ID | 442 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
he | +0.027 |
bunny | +0.027 |
barrel | +0.027 |
puppy | +0.027 |
dark | +0.027 |
Neg logit contributions | |
ases | -0.060 |
olds | -0.057 |
els | -0.055 |
cks | -0.054 |
ips | -0.054 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
supervision | +0.052 |
olds | +0.051 |
ases | +0.043 |
angles | +0.037 |
irs | +0.036 |
Neg logit contributions | |
bunny | -0.122 |
little | -0.120 |
he | -0.119 |
there | -0.117 |
shield | -0.115 |
Token | ates |
Token ID | 689 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
olds | +0.321 |
its | +0.286 |
ases | +0.284 |
apology | +0.277 |
supervision | +0.274 |
Neg logit contributions | |
barrel | -0.292 |
there | -0.280 |
outside | -0.278 |
hut | -0.278 |
in | -0.276 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ases | +0.034 |
els | +0.033 |
olds | +0.033 |
cks | +0.032 |
ips | +0.031 |
Neg logit contributions | |
barrel | -0.013 |
Bun | -0.012 |
puppy | -0.012 |
hut | -0.012 |
dark | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
barrel | +0.025 |
bunny | +0.024 |
Bun | +0.024 |
puppy | +0.024 |
hut | +0.023 |
Neg logit contributions | |
ases | -0.072 |
olds | -0.068 |
els | -0.068 |
cks | -0.066 |
ips | -0.064 |
Token | thanked |
Token ID | 26280 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
barrel | +0.032 |
puppy | +0.030 |
dark | +0.030 |
hut | +0.030 |
Bun | +0.030 |
Neg logit contributions | |
ases | -0.085 |
els | -0.081 |
olds | -0.080 |
cks | -0.077 |
its | -0.074 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
ases | +0.132 |
olds | +0.126 |
cks | +0.121 |
its | +0.120 |
els | +0.119 |
Neg logit contributions | |
bunny | -0.071 |
he | -0.071 |
puppy | -0.066 |
Benny | -0.066 |
Bun | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
Bun | +0.041 |
bunny | +0.040 |
puppy | +0.040 |
barrel | +0.040 |
hut | +0.039 |
Neg logit contributions | |
ases | -0.090 |
olds | -0.085 |
els | -0.085 |
cks | -0.081 |
ips | -0.081 |
Token | started |
Token ID | 2067 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
barrel | +0.051 |
Bun | +0.051 |
wolf | +0.051 |
hut | +0.050 |
hunter | +0.050 |
Neg logit contributions | |
ases | -0.109 |
olds | -0.108 |
els | -0.108 |
cks | -0.100 |
irs | -0.099 |
Token | eating |
Token ID | 6600 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
barrel | +0.040 |
puppy | +0.039 |
bunny | +0.039 |
Bun | +0.039 |
dark | +0.038 |
Neg logit contributions | |
ases | -0.132 |
olds | -0.125 |
els | -0.124 |
cks | -0.120 |
ips | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
Bun | +0.020 |
barrel | +0.020 |
puppy | +0.020 |
bunny | +0.019 |
hut | +0.019 |
Neg logit contributions | |
ases | -0.050 |
els | -0.048 |
olds | -0.048 |
cks | -0.046 |
ips | -0.045 |
Token | ch |
Token ID | 442 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
els | +0.024 |
olds | +0.024 |
ases | +0.023 |
its | +0.022 |
ocol | +0.021 |
Neg logit contributions | |
Bun | -0.013 |
accidentally | -0.013 |
hunter | -0.013 |
shield | -0.012 |
wolf | -0.012 |
Token | ocol |
Token ID | 4668 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
ases | +0.029 |
olds | +0.026 |
cks | +0.025 |
els | +0.021 |
irs | +0.021 |
Neg logit contributions | |
barrel | -0.100 |
little | -0.098 |
bunny | -0.098 |
hut | -0.097 |
dark | -0.097 |
Token | ates |
Token ID | 689 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
olds | +0.312 |
ases | +0.294 |
its | +0.282 |
supervision | +0.278 |
humor | +0.277 |
Neg logit contributions | |
barrel | -0.297 |
seed | -0.280 |
hut | -0.278 |
whole | -0.272 |
outside | -0.270 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Bun | +0.005 |
barrel | +0.005 |
puppy | +0.004 |
dark | +0.004 |
hut | +0.004 |
Neg logit contributions | |
ases | -0.013 |
els | -0.012 |
olds | -0.012 |
cks | -0.012 |
ips | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
barrel | +0.030 |
hut | +0.029 |
dark | +0.029 |
shield | +0.028 |
bunny | +0.028 |
Neg logit contributions | |
ases | -0.078 |
olds | -0.077 |
els | -0.072 |
ips | -0.071 |
cks | -0.070 |
Token | shop |
Token ID | 6128 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ases | +0.006 |
olds | +0.006 |
els | +0.006 |
ips | +0.005 |
cks | +0.005 |
Neg logit contributions | |
Bun | -0.004 |
barrel | -0.004 |
hut | -0.003 |
dark | -0.003 |
shield | -0.003 |
Token | keeper |
Token ID | 13884 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
barrel | +0.018 |
Bun | +0.018 |
dark | +0.018 |
hut | +0.018 |
bunny | +0.018 |
Neg logit contributions | |
ases | -0.038 |
olds | -0.037 |
els | -0.036 |
cks | -0.034 |
ips | -0.034 |
Token | wear |
Token ID | 5806 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
barrel | +0.000 |
puppy | +0.000 |
bunny | +0.000 |
dark | +0.000 |
Bun | +0.000 |
Neg logit contributions | |
ases | -0.001 |
olds | -0.001 |
els | -0.001 |
cks | -0.001 |
ips | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
barrel | +0.045 |
hut | +0.043 |
hunter | +0.041 |
thief | +0.041 |
cabin | +0.040 |
Neg logit contributions | |
ases | -0.067 |
els | -0.065 |
olds | -0.062 |
cks | -0.061 |
irs | -0.060 |
Token | new |
Token ID | 649 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
barrel | +0.021 |
Bun | +0.021 |
hunter | +0.020 |
hut | +0.020 |
thief | +0.019 |
Neg logit contributions | |
els | -0.051 |
ases | -0.051 |
olds | -0.048 |
ips | -0.047 |
cks | -0.046 |
Token | jacket |
Token ID | 15224 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
barrel | +0.042 |
Bun | +0.042 |
he | +0.042 |
hunter | +0.040 |
hut | +0.040 |
Neg logit contributions | |
ases | -0.075 |
els | -0.073 |
olds | -0.069 |
ips | -0.066 |
cks | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
barrel | +0.044 |
hut | +0.043 |
hunter | +0.040 |
wolf | +0.040 |
dark | +0.040 |
Neg logit contributions | |
ases | -0.085 |
els | -0.082 |
olds | -0.081 |
ips | -0.079 |
ums | -0.073 |
Token | school |
Token ID | 1524 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
ases | +0.021 |
olds | +0.020 |
els | +0.020 |
cks | +0.020 |
ips | +0.019 |
Neg logit contributions | |
dark | -0.010 |
he | -0.010 |
puppy | -0.010 |
Bun | -0.010 |
bunny | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
barrel | +0.095 |
hut | +0.088 |
wolf | +0.087 |
bunny | +0.085 |
Bun | +0.084 |
Neg logit contributions | |
ases | -0.191 |
olds | -0.182 |
els | -0.180 |
ips | -0.174 |
cks | -0.165 |
Token | It |
Token ID | 632 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
barrel | +0.055 |
bunny | +0.053 |
puppy | +0.053 |
Bun | +0.053 |
hut | +0.053 |
Neg logit contributions | |
ases | -0.126 |
olds | -0.118 |
els | -0.117 |
cks | -0.113 |
ips | -0.111 |
Token | was |
Token ID | 373 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
barrel | +0.056 |
hut | +0.053 |
thief | +0.049 |
puppy | +0.048 |
hunter | +0.047 |
Neg logit contributions | |
ases | -0.125 |
olds | -0.119 |
els | -0.118 |
ips | -0.113 |
its | -0.112 |
Token | pink |
Token ID | 11398 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
barrel | +0.025 |
hut | +0.023 |
bunny | +0.022 |
puppy | +0.021 |
Bun | +0.021 |
Neg logit contributions | |
ases | -0.092 |
olds | -0.088 |
els | -0.088 |
cks | -0.084 |
ips | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
barrel | +0.033 |
hunter | +0.033 |
Bun | +0.032 |
wolf | +0.032 |
hut | +0.031 |
Neg logit contributions | |
ases | -0.044 |
els | -0.042 |
ips | -0.040 |
olds | -0.040 |
rs | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
puppy | +0.013 |
dark | +0.013 |
barrel | +0.013 |
cabin | +0.013 |
wolf | +0.013 |
Neg logit contributions | |
ases | -0.030 |
olds | -0.028 |
els | -0.027 |
cks | -0.027 |
ips | -0.026 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
barrel | +0.033 |
dark | +0.033 |
hut | +0.033 |
shield | +0.032 |
puppy | +0.032 |
Neg logit contributions | |
ases | -0.064 |
olds | -0.061 |
els | -0.058 |
cks | -0.058 |
ips | -0.056 |
Token | One |
Token ID | 3198 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
barrel | +0.025 |
Bun | +0.025 |
dark | +0.025 |
bunny | +0.024 |
puppy | +0.024 |
Neg logit contributions | |
ases | -0.065 |
olds | -0.061 |
els | -0.061 |
cks | -0.059 |
ips | -0.057 |
Token | day |
Token ID | 1110 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
Bun | +0.023 |
barrel | +0.023 |
puppy | +0.022 |
hut | +0.021 |
bunny | +0.021 |
Neg logit contributions | |
ases | -0.072 |
olds | -0.069 |
els | -0.066 |
cks | -0.066 |
ips | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
barrel | +0.074 |
puppy | +0.072 |
hut | +0.071 |
bunny | +0.071 |
Bun | +0.070 |
Neg logit contributions | |
ases | -0.178 |
olds | -0.167 |
els | -0.166 |
cks | -0.161 |
ips | -0.159 |
Token | a |
Token ID | 257 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
vest | +0.038 |
shield | +0.038 |
superhero | +0.038 |
barrel | +0.036 |
cabin | +0.036 |
Neg logit contributions | |
ases | -0.126 |
cks | -0.119 |
els | -0.116 |
olds | -0.115 |
ips | -0.110 |
Token | sm |
Token ID | 895 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
barrel | +0.096 |
Bun | +0.094 |
hut | +0.090 |
cabin | +0.086 |
decided | +0.084 |
Neg logit contributions | |
ases | -0.297 |
olds | -0.284 |
oke | -0.283 |
els | -0.265 |
cks | -0.263 |
Token | elly |
Token ID | 6148 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
barrel | +0.056 |
Bun | +0.055 |
bunny | +0.055 |
puppy | +0.055 |
hut | +0.055 |
Neg logit contributions | |
ases | -0.058 |
olds | -0.053 |
els | -0.051 |
cks | -0.049 |
ips | -0.048 |
Token | cat |
Token ID | 3797 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Bun | +0.090 |
There | +0.089 |
While | +0.088 |
deserted | +0.087 |
Under | +0.086 |
Neg logit contributions | |
ases | -0.197 |
els | -0.187 |
olds | -0.185 |
ocol | -0.176 |
oke | -0.173 |
Token | named |
Token ID | 3706 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
ju | +0.066 |
perfect | +0.066 |
cozy | +0.066 |
brightly | +0.064 |
bicycle | +0.064 |
Neg logit contributions | |
ases | -0.105 |
olds | -0.094 |
els | -0.093 |
cks | -0.090 |
rs | -0.082 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
hut | +0.053 |
cabin | +0.052 |
barrel | +0.052 |
shield | +0.052 |
bicycle | +0.051 |
Neg logit contributions | |
ases | -0.081 |
olds | -0.074 |
cks | -0.073 |
els | -0.072 |
irs | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
Bun | +0.082 |
cozy | +0.080 |
thief | +0.079 |
dark | +0.079 |
puppy | +0.078 |
Neg logit contributions | |
ases | -0.122 |
els | -0.115 |
olds | -0.111 |
cks | -0.110 |
ums | -0.100 |
Token | He |
Token ID | 679 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
barrel | +0.074 |
puppy | +0.072 |
hut | +0.072 |
bunny | +0.071 |
Bun | +0.070 |
Neg logit contributions | |
ases | -0.180 |
olds | -0.168 |
els | -0.166 |
cks | -0.162 |
ips | -0.157 |
Token | was |
Token ID | 373 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
hut | +0.063 |
puppy | +0.060 |
cabin | +0.059 |
barrel | +0.059 |
thief | +0.057 |
Neg logit contributions | |
ases | -0.140 |
cks | -0.133 |
els | -0.130 |
its | -0.124 |
olds | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | +8.21e+00 |
Pos logit contributions | |
barrel | +0.038 |
hut | +0.036 |
puppy | +0.033 |
cabin | +0.033 |
Bun | +0.033 |
Neg logit contributions | |
ases | -0.129 |
cks | -0.123 |
olds | -0.122 |
els | -0.121 |
ips | -0.114 |
Token | very |
Token ID | 845 |
Feature activation | +6.99e+00 |
Pos logit contributions | |
Bun | +0.111 |
barrel | +0.099 |
hut | +0.097 |
cabin | +0.094 |
decided | +0.090 |
Neg logit contributions | |
ases | -0.196 |
olds | -0.180 |
humor | -0.179 |
oke | -0.178 |
ums | -0.176 |
Token | charming |
Token ID | 23332 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
Bun | +0.088 |
puppy | +0.085 |
hut | +0.079 |
cabin | +0.079 |
barrel | +0.077 |
Neg logit contributions | |
ases | -0.228 |
olds | -0.218 |
cks | -0.207 |
els | -0.204 |
its | -0.202 |
Token | triangle |
Token ID | 22950 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
Bun | +0.123 |
Bug | +0.116 |
hut | +0.116 |
cabin | +0.116 |
barrel | +0.113 |
Neg logit contributions | |
ases | -0.148 |
els | -0.130 |
olds | -0.125 |
ums | -0.121 |
angles | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Bun | +0.081 |
puppy | +0.077 |
dark | +0.077 |
thief | +0.077 |
hut | +0.076 |
Neg logit contributions | |
ases | -0.110 |
els | -0.101 |
olds | -0.096 |
cks | -0.095 |
ips | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
hut | +0.047 |
barrel | +0.045 |
puppy | +0.044 |
cabin | +0.044 |
thief | +0.044 |
Neg logit contributions | |
ases | -0.080 |
cks | -0.080 |
olds | -0.074 |
els | -0.074 |
its | -0.069 |
Token | he |
Token ID | 339 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
hut | +0.073 |
cabin | +0.065 |
barrel | +0.062 |
puppy | +0.061 |
thief | +0.057 |
Neg logit contributions | |
ases | -0.173 |
olds | -0.168 |
els | -0.166 |
cks | -0.163 |
ks | -0.150 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
hut | +0.041 |
barrel | +0.039 |
puppy | +0.038 |
cabin | +0.037 |
thief | +0.036 |
Neg logit contributions | |
ases | -0.090 |
els | -0.083 |
cks | -0.083 |
olds | -0.083 |
its | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Bun | +0.005 |
there | +0.005 |
dark | +0.005 |
he | +0.005 |
bunny | +0.005 |
Neg logit contributions | |
ases | -0.016 |
olds | -0.015 |
cks | -0.014 |
els | -0.014 |
irs | -0.014 |
Token | key |
Token ID | 1994 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
els | +0.037 |
ases | +0.037 |
olds | +0.036 |
cks | +0.034 |
its | +0.034 |
Neg logit contributions | |
Bun | -0.019 |
Benny | -0.018 |
he | -0.017 |
barrel | -0.017 |
bunny | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
barrel | +0.011 |
puppy | +0.011 |
bunny | +0.011 |
Bun | +0.011 |
hut | +0.011 |
Neg logit contributions | |
ases | -0.032 |
olds | -0.030 |
els | -0.030 |
cks | -0.029 |
ips | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
barrel | +0.029 |
puppy | +0.028 |
hut | +0.028 |
bunny | +0.027 |
cabin | +0.027 |
Neg logit contributions | |
ases | -0.070 |
olds | -0.065 |
els | -0.065 |
cks | -0.063 |
ips | -0.061 |
Token | made |
Token ID | 925 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
barrel | +0.024 |
puppy | +0.024 |
hut | +0.023 |
bunny | +0.023 |
dark | +0.022 |
Neg logit contributions | |
ases | -0.077 |
els | -0.073 |
olds | -0.072 |
cks | -0.070 |
ips | -0.069 |
Token | a |
Token ID | 257 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
ases | +0.036 |
olds | +0.033 |
els | +0.033 |
cks | +0.032 |
ips | +0.031 |
Neg logit contributions | |
barrel | -0.014 |
puppy | -0.014 |
bunny | -0.013 |
hut | -0.013 |
Bun | -0.013 |
Token | ' |
Token ID | 705 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
barrel | +0.052 |
Bun | +0.052 |
he | +0.051 |
there | +0.051 |
Benny | +0.049 |
Neg logit contributions | |
ases | -0.127 |
olds | -0.123 |
its | -0.121 |
cks | -0.120 |
els | -0.119 |
Token | click |
Token ID | 12976 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ases | +0.071 |
olds | +0.066 |
els | +0.066 |
cks | +0.064 |
ips | +0.062 |
Neg logit contributions | |
barrel | -0.044 |
puppy | -0.043 |
bunny | -0.043 |
dark | -0.043 |
Bun | -0.043 |
Token | ' |
Token ID | 6 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ases | +0.039 |
olds | +0.036 |
els | +0.036 |
cks | +0.034 |
ips | +0.034 |
Neg logit contributions | |
barrel | -0.027 |
hut | -0.026 |
dark | -0.026 |
bunny | -0.025 |
puppy | -0.025 |
Token | sound |
Token ID | 2128 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ases | +0.046 |
olds | +0.044 |
els | +0.043 |
its | +0.041 |
cks | +0.041 |
Neg logit contributions | |
barrel | -0.024 |
hut | -0.023 |
bunny | -0.023 |
puppy | -0.023 |
cabin | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
barrel | +0.026 |
hut | +0.024 |
Bun | +0.024 |
puppy | +0.024 |
bunny | +0.024 |
Neg logit contributions | |
ases | -0.052 |
olds | -0.049 |
els | -0.048 |
cks | -0.047 |
its | -0.046 |
Token | playing |
Token ID | 2712 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
puppy | +0.025 |
bunny | +0.024 |
Bun | +0.024 |
barrel | +0.023 |
hut | +0.023 |
Neg logit contributions | |
ases | -0.036 |
olds | -0.034 |
els | -0.034 |
cks | -0.033 |
ips | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
puppy | +0.054 |
Bun | +0.051 |
bunny | +0.050 |
wolf | +0.047 |
hut | +0.046 |
Neg logit contributions | |
ases | -0.103 |
els | -0.094 |
olds | -0.094 |
ips | -0.091 |
cks | -0.089 |
Token | he |
Token ID | 339 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
hut | +0.022 |
bicycle | +0.021 |
barrel | +0.020 |
case | +0.020 |
wagon | +0.019 |
Neg logit contributions | |
ases | -0.052 |
els | -0.050 |
olds | -0.050 |
irs | -0.049 |
ocol | -0.047 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
puppy | +0.046 |
Bun | +0.044 |
bicycle | +0.044 |
hut | +0.042 |
bunny | +0.042 |
Neg logit contributions | |
ases | -0.094 |
els | -0.091 |
olds | -0.086 |
cks | -0.084 |
ks | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
Bun | +0.014 |
hut | +0.014 |
puppy | +0.014 |
bunny | +0.014 |
cabin | +0.014 |
Neg logit contributions | |
ases | -0.048 |
olds | -0.046 |
els | -0.044 |
cks | -0.042 |
its | -0.040 |
Token | silly |
Token ID | 14397 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
Bun | +0.088 |
While | +0.070 |
Bug | +0.070 |
Benny | +0.070 |
he | +0.064 |
Neg logit contributions | |
ases | -0.188 |
olds | -0.188 |
els | -0.187 |
oke | -0.183 |
its | -0.182 |
Token | crab |
Token ID | 32202 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Bun | +0.082 |
hut | +0.071 |
cozy | +0.070 |
While | +0.070 |
cabin | +0.069 |
Neg logit contributions | |
ases | -0.171 |
els | -0.164 |
olds | -0.160 |
its | -0.157 |
cks | -0.152 |
Token | near |
Token ID | 1474 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Bun | +0.030 |
cozy | +0.028 |
dark | +0.028 |
puppy | +0.028 |
barrel | +0.027 |
Neg logit contributions | |
ases | -0.059 |
els | -0.056 |
cks | -0.055 |
olds | -0.054 |
its | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
ases | +0.017 |
olds | +0.016 |
els | +0.016 |
ips | +0.016 |
cks | +0.016 |
Neg logit contributions | |
barrel | -0.006 |
dark | -0.006 |
puppy | -0.006 |
he | -0.006 |
bunny | -0.006 |
Token | sand |
Token ID | 6450 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Bun | +0.007 |
puppy | +0.006 |
Benny | +0.006 |
bunny | +0.006 |
Bug | +0.006 |
Neg logit contributions | |
ases | -0.011 |
els | -0.010 |
olds | -0.010 |
cks | -0.010 |
its | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Bun | +0.034 |
puppy | +0.034 |
barrel | +0.033 |
bunny | +0.033 |
dark | +0.033 |
Neg logit contributions | |
ases | -0.090 |
els | -0.085 |
olds | -0.084 |
cks | -0.082 |
ips | -0.080 |
Token | either |
Token ID | 2035 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
ases | +0.017 |
olds | +0.016 |
cks | +0.015 |
ips | +0.015 |
els | +0.015 |
Neg logit contributions | |
there | -0.005 |
he | -0.005 |
dark | -0.004 |
Bun | -0.004 |
bunny | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ases | +0.029 |
cks | +0.027 |
ips | +0.026 |
olds | +0.026 |
irs | +0.026 |
Neg logit contributions | |
he | -0.004 |
dark | -0.004 |
puppy | -0.004 |
there | -0.004 |
bunny | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
shield | +0.031 |
barrel | +0.030 |
hunter | +0.030 |
hut | +0.029 |
cabin | +0.029 |
Neg logit contributions | |
olds | -0.053 |
ases | -0.052 |
els | -0.049 |
ips | -0.047 |
rs | -0.046 |
Token | decided |
Token ID | 3066 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
ases | +0.072 |
els | +0.070 |
olds | +0.070 |
its | +0.065 |
cks | +0.065 |
Neg logit contributions | |
barrel | -0.032 |
hut | -0.032 |
cabin | -0.031 |
dark | -0.030 |
Bun | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
barrel | +0.069 |
cabin | +0.068 |
hut | +0.067 |
bunny | +0.061 |
shield | +0.061 |
Neg logit contributions | |
olds | -0.121 |
ases | -0.115 |
els | -0.111 |
supervision | -0.103 |
cks | -0.103 |
Token | touch |
Token ID | 3638 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
ases | +0.060 |
olds | +0.056 |
els | +0.055 |
cks | +0.053 |
ips | +0.052 |
Neg logit contributions | |
barrel | -0.039 |
dark | -0.038 |
puppy | -0.038 |
Bun | -0.038 |
bunny | -0.038 |
Token | it |
Token ID | 340 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ases | +0.022 |
olds | +0.021 |
cks | +0.020 |
ips | +0.020 |
its | +0.019 |
Neg logit contributions | |
dark | -0.004 |
there | -0.004 |
he | -0.004 |
bunny | -0.004 |
puppy | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
barrel | +0.015 |
puppy | +0.015 |
hut | +0.015 |
Bun | +0.014 |
cabin | +0.014 |
Neg logit contributions | |
ases | -0.033 |
els | -0.032 |
olds | -0.031 |
cks | -0.030 |
ips | -0.029 |
Token | see |
Token ID | 766 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
ases | +0.090 |
ips | +0.085 |
els | +0.084 |
olds | +0.084 |
cks | +0.080 |
Neg logit contributions | |
dark | -0.042 |
he | -0.042 |
little | -0.040 |
bunny | -0.039 |
a | -0.039 |
Token | what |
Token ID | 644 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
ases | +0.013 |
olds | +0.012 |
ips | +0.012 |
els | +0.012 |
cks | +0.012 |
Neg logit contributions | |
bunny | -0.006 |
puppy | -0.006 |
there | -0.006 |
he | -0.006 |
dark | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
barrel | +0.020 |
hut | +0.019 |
Bun | +0.019 |
puppy | +0.019 |
bunny | +0.019 |
Neg logit contributions | |
ases | -0.070 |
els | -0.067 |
olds | -0.066 |
cks | -0.064 |
ips | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
barrel | +0.023 |
Bun | +0.022 |
hut | +0.022 |
dark | +0.022 |
puppy | +0.021 |
Neg logit contributions | |
ases | -0.043 |
olds | -0.041 |
els | -0.040 |
ips | -0.038 |
cks | -0.038 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Bun | +0.023 |
barrel | +0.023 |
he | +0.023 |
puppy | +0.023 |
bunny | +0.023 |
Neg logit contributions | |
ases | -0.063 |
els | -0.060 |
olds | -0.058 |
cks | -0.058 |
ips | -0.055 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
barrel | +0.010 |
puppy | +0.009 |
hut | +0.009 |
dark | +0.009 |
bunny | +0.009 |
Neg logit contributions | |
ases | -0.019 |
olds | -0.017 |
els | -0.017 |
cks | -0.017 |
ips | -0.017 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
he | +0.002 |
dark | +0.002 |
there | +0.002 |
barrel | +0.002 |
hut | +0.002 |
Neg logit contributions | |
ases | -0.007 |
els | -0.007 |
olds | -0.007 |
cks | -0.006 |
ips | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
barrel | +0.062 |
wagon | +0.053 |
cabin | +0.053 |
miner | +0.053 |
hut | +0.052 |
Neg logit contributions | |
ases | -0.097 |
olds | -0.091 |
cks | -0.091 |
its | -0.087 |
ks | -0.085 |
Token | time |
Token ID | 640 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
barrel | +0.099 |
puppy | +0.096 |
bunny | +0.096 |
Bun | +0.096 |
hut | +0.095 |
Neg logit contributions | |
ases | -0.217 |
olds | -0.204 |
els | -0.202 |
cks | -0.196 |
ips | -0.191 |
Token | there |
Token ID | 612 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
he | +0.039 |
barrel | +0.038 |
there | +0.038 |
Bun | +0.038 |
dark | +0.038 |
Neg logit contributions | |
ases | -0.151 |
els | -0.142 |
olds | -0.142 |
cks | -0.138 |
ips | -0.135 |
Token | was |
Token ID | 373 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
barrel | +0.029 |
bunny | +0.027 |
puppy | +0.027 |
dark | +0.027 |
Bun | +0.027 |
Neg logit contributions | |
ases | -0.163 |
olds | -0.155 |
els | -0.154 |
cks | -0.150 |
ips | -0.147 |
Token | a |
Token ID | 257 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
barrel | +0.064 |
bicycle | +0.059 |
cabin | +0.057 |
thief | +0.055 |
hunter | +0.054 |
Neg logit contributions | |
ases | -0.168 |
els | -0.152 |
cks | -0.151 |
olds | -0.149 |
irs | -0.148 |
Token | hungry |
Token ID | 14720 |
Feature activation | +7.07e+00 |
Pos logit contributions | |
barrel | +0.097 |
Bun | +0.096 |
he | +0.093 |
case | +0.088 |
buried | +0.085 |
Neg logit contributions | |
oke | -0.252 |
ases | -0.245 |
els | -0.236 |
olds | -0.236 |
avi | -0.235 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
Bun | +0.075 |
lost | +0.070 |
accidentally | +0.070 |
there | +0.066 |
dark | +0.065 |
Neg logit contributions | |
ases | -0.207 |
els | -0.199 |
olds | -0.198 |
oke | -0.192 |
ocol | -0.188 |
Token | them |
Token ID | 606 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ases | +0.004 |
olds | +0.004 |
els | +0.004 |
cks | +0.003 |
ips | +0.003 |
Neg logit contributions | |
he | -0.002 |
bunny | -0.002 |
dark | -0.002 |
barrel | -0.002 |
puppy | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ases | +0.046 |
els | +0.044 |
olds | +0.044 |
cks | +0.042 |
ips | +0.041 |
Neg logit contributions | |
barrel | -0.018 |
puppy | -0.017 |
Bun | -0.017 |
hut | -0.017 |
bunny | -0.016 |
Token | It |
Token ID | 632 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
barrel | +0.025 |
hut | +0.024 |
shield | +0.023 |
cabin | +0.023 |
dark | +0.023 |
Neg logit contributions | |
ases | -0.051 |
olds | -0.049 |
els | -0.046 |
ips | -0.046 |
cks | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
barrel | +0.030 |
bicycle | +0.029 |
cabin | +0.028 |
hut | +0.028 |
puppy | +0.027 |
Neg logit contributions | |
ases | -0.067 |
els | -0.064 |
cks | -0.064 |
olds | -0.062 |
its | -0.061 |
Token | so |
Token ID | 523 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
barrel | +0.002 |
puppy | +0.002 |
Bun | +0.002 |
hut | +0.002 |
bunny | +0.002 |
Neg logit contributions | |
ases | -0.009 |
olds | -0.008 |
els | -0.008 |
cks | -0.008 |
ips | -0.008 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
barrel | +0.006 |
puppy | +0.006 |
Bun | +0.006 |
bunny | +0.006 |
hut | +0.006 |
Neg logit contributions | |
ases | -0.026 |
olds | -0.025 |
els | -0.025 |
cks | -0.024 |
ips | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
barrel | +0.033 |
hut | +0.032 |
cabin | +0.031 |
shield | +0.031 |
bicycle | +0.031 |
Neg logit contributions | |
ases | -0.069 |
olds | -0.066 |
els | -0.064 |
cks | -0.062 |
ips | -0.061 |
Token | it |
Token ID | 340 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
barrel | +0.008 |
puppy | +0.008 |
bunny | +0.008 |
dark | +0.008 |
Bun | +0.008 |
Neg logit contributions | |
ases | -0.031 |
olds | -0.030 |
els | -0.029 |
cks | -0.029 |
ips | -0.028 |
Token | started |
Token ID | 2067 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
ases | +0.002 |
els | +0.002 |
cks | +0.002 |
olds | +0.002 |
its | +0.002 |
Neg logit contributions | |
bicycle | -0.001 |
barrel | -0.001 |
hut | -0.001 |
cabin | -0.001 |
dark | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
dark | +0.018 |
barrel | +0.018 |
bunny | +0.018 |
puppy | +0.017 |
Bun | +0.017 |
Neg logit contributions | |
ases | -0.094 |
els | -0.089 |
olds | -0.089 |
cks | -0.087 |
ips | -0.085 |
Token | sing |
Token ID | 1702 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
ases | +0.088 |
olds | +0.082 |
els | +0.082 |
cks | +0.080 |
ips | +0.077 |
Neg logit contributions | |
barrel | -0.041 |
puppy | -0.039 |
bunny | -0.039 |
Bun | -0.039 |
hut | -0.039 |
Token | Yes |
Token ID | 5297 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
ases | +0.078 |
els | +0.073 |
olds | +0.073 |
cks | +0.071 |
ips | +0.069 |
Neg logit contributions | |
barrel | -0.031 |
bunny | -0.031 |
puppy | -0.031 |
dark | -0.031 |
Bun | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
ases | +0.131 |
olds | +0.124 |
els | +0.123 |
cks | +0.119 |
ips | +0.117 |
Neg logit contributions | |
barrel | -0.048 |
puppy | -0.046 |
bunny | -0.046 |
hut | -0.045 |
Bun | -0.045 |
Token | please |
Token ID | 3387 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
ases | +0.102 |
olds | +0.098 |
els | +0.096 |
cks | +0.090 |
its | +0.088 |
Neg logit contributions | |
barrel | -0.054 |
Bun | -0.052 |
hut | -0.052 |
dark | -0.051 |
cabin | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ases | +0.136 |
olds | +0.129 |
els | +0.127 |
cks | +0.124 |
ips | +0.120 |
Neg logit contributions | |
barrel | -0.051 |
Bun | -0.049 |
puppy | -0.049 |
hut | -0.049 |
bunny | -0.049 |
Token | Milk |
Token ID | 24796 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
barrel | +0.019 |
dark | +0.018 |
hut | +0.018 |
puppy | +0.018 |
Bun | +0.018 |
Neg logit contributions | |
ases | -0.041 |
olds | -0.039 |
els | -0.038 |
cks | -0.037 |
ips | -0.037 |
Token | makes |
Token ID | 1838 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ases | +0.036 |
olds | +0.034 |
els | +0.034 |
cks | +0.033 |
ips | +0.032 |
Neg logit contributions | |
barrel | -0.023 |
bunny | -0.023 |
puppy | -0.023 |
dark | -0.023 |
Bun | -0.023 |
Token | cereal |
Token ID | 33158 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
ases | +0.071 |
olds | +0.067 |
els | +0.065 |
cks | +0.064 |
ips | +0.063 |
Neg logit contributions | |
bunny | -0.031 |
dark | -0.031 |
Bun | -0.031 |
puppy | -0.030 |
barrel | -0.030 |
Token | y |
Token ID | 331 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
ases | +0.001 |
olds | +0.001 |
els | +0.001 |
cks | +0.001 |
its | +0.001 |
Neg logit contributions | |
barrel | -0.001 |
puppy | -0.001 |
Bun | -0.001 |
bunny | -0.001 |
dark | -0.001 |
Token | ummy |
Token ID | 13513 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ases | +0.147 |
olds | +0.140 |
cks | +0.135 |
els | +0.134 |
ips | +0.126 |
Neg logit contributions | |
barrel | -0.101 |
dark | -0.100 |
hut | -0.098 |
bunny | -0.097 |
Bun | -0.097 |
Token | ," |
Token ID | 553 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
ases | +0.034 |
els | +0.033 |
olds | +0.033 |
cks | +0.031 |
its | +0.031 |
Neg logit contributions | |
barrel | -0.016 |
Bun | -0.015 |
puppy | -0.015 |
hunter | -0.014 |
thief | -0.014 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
ases | +0.129 |
olds | +0.122 |
els | +0.121 |
cks | +0.119 |
ips | +0.116 |
Neg logit contributions | |
barrel | -0.032 |
bunny | -0.032 |
puppy | -0.032 |
Bun | -0.031 |
dark | -0.031 |
Token | it |
Token ID | 340 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
ases | +0.031 |
olds | +0.029 |
els | +0.029 |
cks | +0.028 |
ips | +0.028 |
Neg logit contributions | |
barrel | -0.015 |
bunny | -0.014 |
dark | -0.014 |
puppy | -0.014 |
Bun | -0.014 |
Token | pop |
Token ID | 1461 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
barrel | +0.011 |
Bun | +0.011 |
puppy | +0.011 |
bunny | +0.010 |
hut | +0.010 |
Neg logit contributions | |
ases | -0.032 |
olds | -0.030 |
cks | -0.030 |
els | -0.030 |
its | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
ases | +0.055 |
els | +0.052 |
olds | +0.051 |
cks | +0.050 |
ips | +0.049 |
Neg logit contributions | |
barrel | -0.018 |
Bun | -0.017 |
puppy | -0.017 |
bunny | -0.017 |
hut | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ases | +0.062 |
olds | +0.059 |
els | +0.057 |
cks | +0.055 |
ips | +0.055 |
Neg logit contributions | |
dark | -0.023 |
barrel | -0.022 |
hut | -0.022 |
puppy | -0.022 |
bunny | -0.022 |
Token | big |
Token ID | 1263 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Bun | +0.026 |
puppy | +0.023 |
he | +0.023 |
bunny | +0.022 |
Benny | +0.022 |
Neg logit contributions | |
ases | -0.051 |
olds | -0.047 |
els | -0.046 |
cks | -0.045 |
ips | -0.045 |
Token | pot |
Token ID | 1787 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Bun | +0.028 |
barrel | +0.027 |
puppy | +0.027 |
bunny | +0.027 |
hut | +0.026 |
Neg logit contributions | |
ases | -0.067 |
els | -0.062 |
olds | -0.062 |
cks | -0.060 |
ips | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
Bun | +0.017 |
barrel | +0.017 |
puppy | +0.017 |
bunny | +0.016 |
dark | +0.016 |
Neg logit contributions | |
ases | -0.049 |
olds | -0.046 |
els | -0.046 |
cks | -0.045 |
ips | -0.044 |
Token | They |
Token ID | 1119 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
dark | +0.038 |
he | +0.036 |
barrel | +0.036 |
there | +0.035 |
little | +0.033 |
Neg logit contributions | |
ases | -0.112 |
els | -0.107 |
olds | -0.104 |
cks | -0.103 |
irs | -0.100 |
Token | also |
Token ID | 635 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
barrel | +0.047 |
Bun | +0.047 |
puppy | +0.047 |
hut | +0.046 |
bunny | +0.045 |
Neg logit contributions | |
ases | -0.075 |
els | -0.070 |
olds | -0.069 |
cks | -0.067 |
its | -0.064 |
Token | like |
Token ID | 588 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
dark | +0.034 |
barrel | +0.033 |
bunny | +0.033 |
he | +0.032 |
puppy | +0.032 |
Neg logit contributions | |
ases | -0.072 |
els | -0.067 |
olds | -0.067 |
cks | -0.064 |
ips | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
barrel | +0.040 |
Bun | +0.039 |
hut | +0.037 |
puppy | +0.037 |
dark | +0.037 |
Neg logit contributions | |
ases | -0.113 |
olds | -0.108 |
els | -0.105 |
cks | -0.103 |
ips | -0.100 |
Token | herself |
Token ID | 5223 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ases | +0.145 |
olds | +0.133 |
els | +0.133 |
cks | +0.129 |
ips | +0.127 |
Neg logit contributions | |
he | -0.081 |
there | -0.076 |
Bun | -0.075 |
dark | -0.075 |
puppy | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
barrel | +0.012 |
dark | +0.011 |
Bun | +0.011 |
hut | +0.011 |
cabin | +0.011 |
Neg logit contributions | |
ases | -0.020 |
olds | -0.019 |
els | -0.019 |
cks | -0.017 |
ips | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
barrel | +0.031 |
dark | +0.030 |
hut | +0.030 |
bunny | +0.030 |
puppy | +0.030 |
Neg logit contributions | |
ases | -0.067 |
olds | -0.064 |
els | -0.062 |
cks | -0.060 |
ips | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
barrel | +0.032 |
hut | +0.030 |
dark | +0.030 |
Bun | +0.029 |
puppy | +0.029 |
Neg logit contributions | |
ases | -0.087 |
olds | -0.082 |
els | -0.081 |
cks | -0.079 |
ips | -0.077 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
barrel | +0.007 |
hut | +0.006 |
puppy | +0.006 |
Bun | +0.006 |
bunny | +0.006 |
Neg logit contributions | |
ases | -0.023 |
olds | -0.022 |
els | -0.022 |
cks | -0.021 |
ips | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
barrel | +0.025 |
hut | +0.023 |
Bun | +0.023 |
bunny | +0.023 |
puppy | +0.022 |
Neg logit contributions | |
ases | -0.065 |
olds | -0.063 |
els | -0.061 |
cks | -0.059 |
ips | -0.058 |
Token | show |
Token ID | 905 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ases | +0.089 |
olds | +0.083 |
els | +0.083 |
cks | +0.081 |
ips | +0.079 |
Neg logit contributions | |
he | -0.048 |
bunny | -0.048 |
puppy | -0.048 |
dark | -0.048 |
barrel | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ases | +0.017 |
cks | +0.016 |
els | +0.016 |
olds | +0.016 |
ips | +0.015 |
Neg logit contributions | |
he | -0.007 |
puppy | -0.007 |
Bun | -0.007 |
little | -0.007 |
bunny | -0.007 |
Token | stranger |
Token ID | 16195 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
ases | +0.062 |
olds | +0.061 |
els | +0.060 |
its | +0.056 |
irs | +0.054 |
Neg logit contributions | |
Bun | -0.027 |
barrel | -0.025 |
hut | -0.025 |
he | -0.024 |
accidentally | -0.023 |
Token | what |
Token ID | 644 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
barrel | +0.001 |
dark | +0.001 |
Bun | +0.001 |
hut | +0.001 |
bunny | +0.001 |
Neg logit contributions | |
ases | -0.002 |
olds | -0.002 |
els | -0.002 |
cks | -0.002 |
ips | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
barrel | +0.015 |
hut | +0.014 |
Bun | +0.014 |
bunny | +0.014 |
dark | +0.014 |
Neg logit contributions | |
ases | -0.054 |
olds | -0.052 |
els | -0.051 |
cks | -0.049 |
ips | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
ases | +0.068 |
els | +0.064 |
olds | +0.063 |
cks | +0.063 |
ips | +0.060 |
Neg logit contributions | |
dark | -0.023 |
Bun | -0.023 |
barrel | -0.023 |
puppy | -0.023 |
bunny | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
ases | +0.224 |
els | +0.214 |
olds | +0.205 |
cks | +0.204 |
ips | +0.204 |
Neg logit contributions | |
Bun | -0.060 |
he | -0.057 |
dark | -0.056 |
little | -0.054 |
bunny | -0.053 |
Token | L |
Token ID | 43 |
Feature activation | -9.77e+00 |
Pos logit contributions | |
ases | +0.147 |
olds | +0.140 |
els | +0.137 |
cks | +0.132 |
ips | +0.128 |
Neg logit contributions | |
barrel | -0.089 |
hut | -0.084 |
bunny | -0.084 |
puppy | -0.084 |
dark | -0.083 |
Token | ily |
Token ID | 813 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
ases | +0.240 |
olds | +0.223 |
els | +0.222 |
cks | +0.217 |
irs | +0.205 |
Neg logit contributions | |
barrel | -0.197 |
bunny | -0.195 |
dark | -0.194 |
Bun | -0.194 |
puppy | -0.194 |
Token | feels |
Token ID | 5300 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ases | +0.096 |
olds | +0.089 |
els | +0.088 |
cks | +0.085 |
ips | +0.083 |
Neg logit contributions | |
barrel | -0.073 |
bunny | -0.071 |
puppy | -0.071 |
dark | -0.071 |
hut | -0.071 |
Token | better |
Token ID | 1365 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
ases | +0.055 |
olds | +0.052 |
els | +0.052 |
cks | +0.050 |
ips | +0.049 |
Neg logit contributions | |
barrel | -0.020 |
dark | -0.019 |
bunny | -0.019 |
puppy | -0.019 |
Bun | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
ases | +0.151 |
els | +0.146 |
irs | +0.144 |
cks | +0.142 |
olds | +0.138 |
Neg logit contributions | |
he | -0.028 |
there | -0.026 |
dark | -0.025 |
while | -0.025 |
little | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
barrel | +0.012 |
hunter | +0.011 |
shield | +0.011 |
cabin | +0.011 |
Bun | +0.011 |
Neg logit contributions | |
ases | -0.017 |
olds | -0.017 |
els | -0.016 |
ips | -0.015 |
rs | -0.014 |
Token | says |
Token ID | 1139 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
barrel | +0.021 |
Bun | +0.021 |
hut | +0.021 |
dark | +0.020 |
puppy | +0.020 |
Neg logit contributions | |
ases | -0.017 |
olds | -0.016 |
els | -0.015 |
cks | -0.015 |
its | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ases | +0.084 |
els | +0.079 |
olds | +0.078 |
cks | +0.077 |
ips | +0.075 |
Neg logit contributions | |
barrel | -0.025 |
bunny | -0.025 |
puppy | -0.025 |
dark | -0.025 |
he | -0.025 |
Token | " |
Token ID | 366 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
ases | +0.070 |
olds | +0.066 |
els | +0.065 |
cks | +0.064 |
ips | +0.063 |
Neg logit contributions | |
barrel | -0.023 |
hut | -0.022 |
dark | -0.022 |
puppy | -0.022 |
Bun | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ases | +0.155 |
els | +0.146 |
olds | +0.146 |
cks | +0.143 |
irs | +0.139 |
Neg logit contributions | |
bunny | -0.037 |
barrel | -0.036 |
he | -0.036 |
puppy | -0.036 |
Bun | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
ases | +0.051 |
els | +0.048 |
olds | +0.047 |
cks | +0.047 |
irs | +0.045 |
Neg logit contributions | |
Bun | -0.017 |
bunny | -0.017 |
puppy | -0.016 |
dark | -0.016 |
barrel | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
ases | +0.267 |
els | +0.262 |
ocol | +0.247 |
cks | +0.247 |
olds | +0.246 |
Neg logit contributions | |
Bun | -0.057 |
he | -0.051 |
Benny | -0.046 |
there | -0.043 |
little | -0.042 |
Token | They |
Token ID | 2990 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ases | +0.181 |
olds | +0.169 |
els | +0.169 |
cks | +0.164 |
ips | +0.159 |
Neg logit contributions | |
barrel | -0.091 |
Bun | -0.091 |
puppy | -0.089 |
dark | -0.089 |
bunny | -0.089 |
Token | took |
Token ID | 1718 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
ases | +0.004 |
olds | +0.004 |
els | +0.004 |
ips | +0.004 |
cks | +0.004 |
Neg logit contributions | |
barrel | -0.002 |
hut | -0.002 |
puppy | -0.002 |
Bun | -0.002 |
bunny | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
ases | +0.157 |
olds | +0.150 |
els | +0.147 |
cks | +0.145 |
ips | +0.139 |
Neg logit contributions | |
barrel | -0.081 |
dark | -0.081 |
puppy | -0.080 |
bunny | -0.080 |
Bun | -0.080 |
Token | equipment |
Token ID | 5112 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ases | +0.092 |
olds | +0.086 |
els | +0.085 |
cks | +0.083 |
ips | +0.081 |
Neg logit contributions | |
barrel | -0.040 |
Bun | -0.040 |
bunny | -0.040 |
puppy | -0.040 |
hut | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
barrel | +0.017 |
dark | +0.016 |
hut | +0.016 |
he | +0.016 |
puppy | +0.016 |
Neg logit contributions | |
ases | -0.054 |
olds | -0.051 |
els | -0.050 |
cks | -0.050 |
irs | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
ases | +0.128 |
olds | +0.124 |
els | +0.122 |
cks | +0.120 |
ips | +0.117 |
Neg logit contributions | |
dark | -0.045 |
Bun | -0.045 |
puppy | -0.045 |
little | -0.044 |
bunny | -0.043 |
Token | nearby |
Token ID | 6716 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
Bun | +0.050 |
bunny | +0.045 |
puppy | +0.044 |
he | +0.044 |
barrel | +0.043 |
Neg logit contributions | |
ases | -0.122 |
olds | -0.119 |
els | -0.112 |
cks | -0.108 |
ips | -0.108 |
Token | fountain |
Token ID | 29420 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Bun | +0.037 |
bunny | +0.034 |
puppy | +0.033 |
he | +0.033 |
barrel | +0.033 |
Neg logit contributions | |
ases | -0.097 |
olds | -0.091 |
els | -0.090 |
cks | -0.085 |
ips | -0.084 |
Token | They |
Token ID | 1119 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
dark | +0.019 |
Bun | +0.018 |
puppy | +0.018 |
barrel | +0.018 |
hut | +0.018 |
Neg logit contributions | |
ases | -0.053 |
els | -0.050 |
olds | -0.049 |
cks | -0.048 |
ips | -0.047 |
Token | will |
Token ID | 481 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
barrel | +0.012 |
bunny | +0.012 |
puppy | +0.012 |
dark | +0.012 |
Bun | +0.012 |
Neg logit contributions | |
ases | -0.014 |
olds | -0.013 |
els | -0.013 |
cks | -0.012 |
ips | -0.012 |
Token | listen |
Token ID | 6004 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
ases | +0.040 |
els | +0.038 |
olds | +0.038 |
cks | +0.036 |
ips | +0.036 |
Neg logit contributions | |
Bun | -0.018 |
puppy | -0.018 |
dark | -0.018 |
bunny | -0.018 |
he | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
ases | +0.024 |
olds | +0.023 |
els | +0.023 |
cks | +0.022 |
ips | +0.022 |
Neg logit contributions | |
barrel | -0.008 |
hut | -0.007 |
Bun | -0.007 |
puppy | -0.007 |
bunny | -0.007 |
Token | each |
Token ID | 1123 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
ases | +0.217 |
olds | +0.209 |
ips | +0.208 |
els | +0.201 |
its | +0.197 |
Neg logit contributions | |
dark | -0.098 |
puppy | -0.097 |
little | -0.094 |
a | -0.092 |
bunny | -0.092 |
Token | other |
Token ID | 584 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
ases | +0.207 |
cks | +0.202 |
ips | +0.199 |
els | +0.196 |
olds | +0.196 |
Neg logit contributions | |
little | -0.066 |
bunny | -0.062 |
puppy | -0.062 |
dark | -0.062 |
boy | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ases | +0.168 |
olds | +0.159 |
els | +0.158 |
cks | +0.154 |
ips | +0.151 |
Neg logit contributions | |
barrel | -0.052 |
puppy | -0.050 |
bunny | -0.050 |
Bun | -0.050 |
dark | -0.050 |
Token | They |
Token ID | 1119 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
dark | +0.014 |
Bun | +0.014 |
puppy | +0.014 |
he | +0.014 |
barrel | +0.014 |
Neg logit contributions | |
ases | -0.046 |
els | -0.044 |
cks | -0.042 |
olds | -0.042 |
ips | -0.041 |
Token | will |
Token ID | 481 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
barrel | +0.007 |
bunny | +0.007 |
puppy | +0.007 |
dark | +0.007 |
hut | +0.007 |
Neg logit contributions | |
ases | -0.008 |
els | -0.008 |
olds | -0.008 |
cks | -0.007 |
ips | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
ases | +0.044 |
els | +0.042 |
olds | +0.041 |
cks | +0.040 |
ips | +0.040 |
Neg logit contributions | |
Bun | -0.020 |
puppy | -0.020 |
bunny | -0.020 |
dark | -0.020 |
he | -0.020 |
Token | safe |
Token ID | 3338 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ases | +0.150 |
olds | +0.139 |
els | +0.138 |
cks | +0.137 |
ips | +0.132 |
Neg logit contributions | |
barrel | -0.060 |
Bun | -0.056 |
bunny | -0.056 |
hut | -0.055 |
puppy | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ases | +0.137 |
els | +0.132 |
olds | +0.128 |
cks | +0.125 |
its | +0.117 |
Neg logit contributions | |
dark | -0.064 |
hut | -0.063 |
barrel | -0.062 |
Bun | -0.062 |
bunny | -0.061 |
Token | but |
Token ID | 475 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ases | +0.040 |
olds | +0.038 |
els | +0.038 |
cks | +0.036 |
irs | +0.035 |
Neg logit contributions | |
barrel | -0.021 |
hut | -0.021 |
dark | -0.020 |
Bun | -0.020 |
puppy | -0.020 |
Token | be |
Token ID | 307 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ases | +0.009 |
els | +0.008 |
olds | +0.008 |
cks | +0.008 |
ips | +0.008 |
Neg logit contributions | |
barrel | -0.005 |
hut | -0.005 |
puppy | -0.005 |
Bun | -0.005 |
bunny | -0.005 |
Token | careful |
Token ID | 8161 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ases | +0.053 |
olds | +0.049 |
cks | +0.048 |
els | +0.047 |
ips | +0.046 |
Neg logit contributions | |
barrel | -0.035 |
puppy | -0.034 |
bunny | -0.034 |
Bun | -0.034 |
hut | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
ases | +0.054 |
olds | +0.051 |
els | +0.050 |
cks | +0.049 |
ips | +0.048 |
Neg logit contributions | |
barrel | -0.021 |
puppy | -0.020 |
bunny | -0.020 |
hut | -0.020 |
Bun | -0.020 |
Token | don |
Token ID | 836 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
barrel | +0.011 |
puppy | +0.011 |
Bun | +0.011 |
bunny | +0.011 |
hut | +0.011 |
Neg logit contributions | |
ases | -0.020 |
olds | -0.019 |
els | -0.018 |
cks | -0.018 |
ips | -0.017 |
Token | 't |
Token ID | 470 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ases | +0.125 |
olds | +0.118 |
els | +0.116 |
cks | +0.112 |
ips | +0.109 |
Neg logit contributions | |
Bun | -0.062 |
dark | -0.061 |
barrel | -0.061 |
bunny | -0.061 |
he | -0.061 |
Token | get |
Token ID | 651 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
ases | +0.090 |
olds | +0.083 |
els | +0.080 |
cks | +0.079 |
its | +0.076 |
Neg logit contributions | |
barrel | -0.065 |
hut | -0.062 |
Bun | -0.061 |
puppy | -0.061 |
bunny | -0.061 |
Token | too |
Token ID | 1165 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
ases | +0.125 |
olds | +0.119 |
els | +0.117 |
cks | +0.117 |
ips | +0.110 |
Neg logit contributions | |
barrel | -0.049 |
hut | -0.046 |
cabin | -0.044 |
bunny | -0.043 |
puppy | -0.042 |
Token | close |
Token ID | 1969 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ases | +0.025 |
olds | +0.024 |
cks | +0.023 |
els | +0.023 |
its | +0.022 |
Neg logit contributions | |
Bun | -0.010 |
puppy | -0.009 |
bunny | -0.009 |
barrel | -0.009 |
Benny | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
ases | +0.072 |
olds | +0.068 |
els | +0.067 |
cks | +0.065 |
ips | +0.064 |
Neg logit contributions | |
barrel | -0.022 |
bunny | -0.021 |
puppy | -0.021 |
Bun | -0.021 |
hut | -0.021 |
Token | perfect |
Token ID | 2818 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
barrel | +0.040 |
Bun | +0.040 |
hut | +0.039 |
cabin | +0.038 |
puppy | +0.038 |
Neg logit contributions | |
ases | -0.107 |
olds | -0.103 |
els | -0.101 |
cks | -0.099 |
ips | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Bun | +0.009 |
barrel | +0.008 |
dark | +0.008 |
puppy | +0.008 |
bunny | +0.008 |
Neg logit contributions | |
ases | -0.020 |
olds | -0.019 |
els | -0.019 |
ips | -0.018 |
cks | -0.018 |
Token | |
Token ID | 220 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
barrel | +0.045 |
dark | +0.043 |
hut | +0.043 |
bunny | +0.042 |
puppy | +0.042 |
Neg logit contributions | |
ases | -0.089 |
olds | -0.085 |
els | -0.082 |
cks | -0.080 |
ips | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
ases | +0.128 |
els | +0.123 |
cks | +0.117 |
olds | +0.117 |
ocol | +0.113 |
Neg logit contributions | |
he | -0.029 |
there | -0.028 |
Bun | -0.028 |
little | -0.025 |
barrel | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
ases | +0.124 |
els | +0.118 |
olds | +0.114 |
cks | +0.112 |
ips | +0.110 |
Neg logit contributions | |
Bun | -0.038 |
he | -0.037 |
bunny | -0.035 |
barrel | -0.034 |
there | -0.034 |
Token | Pe |
Token ID | 6435 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
ases | +0.088 |
olds | +0.083 |
els | +0.082 |
cks | +0.079 |
ips | +0.077 |
Neg logit contributions | |
barrel | -0.048 |
dark | -0.046 |
puppy | -0.046 |
hut | -0.046 |
bunny | -0.046 |
Token | ggy |
Token ID | 19970 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ases | +0.236 |
olds | +0.208 |
els | +0.202 |
irs | +0.197 |
ips | +0.196 |
Neg logit contributions | |
he | -0.229 |
lost | -0.224 |
Bun | -0.223 |
there | -0.222 |
hunter | -0.221 |
Token | was |
Token ID | 373 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
ases | +0.033 |
olds | +0.031 |
els | +0.031 |
cks | +0.030 |
ips | +0.029 |
Neg logit contributions | |
barrel | -0.012 |
hut | -0.011 |
dark | -0.011 |
cabin | -0.011 |
puppy | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
barrel | +0.005 |
Bun | +0.005 |
hut | +0.005 |
puppy | +0.005 |
bunny | +0.005 |
Neg logit contributions | |
ases | -0.023 |
olds | -0.022 |
els | -0.022 |
cks | -0.022 |
ips | -0.021 |
Token | very |
Token ID | 845 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
barrel | +0.017 |
puppy | +0.016 |
bunny | +0.016 |
Bun | +0.016 |
dark | +0.016 |
Neg logit contributions | |
ases | -0.051 |
olds | -0.048 |
els | -0.047 |
cks | -0.046 |
ips | -0.045 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
barrel | +0.023 |
Bun | +0.023 |
puppy | +0.022 |
bunny | +0.022 |
hut | +0.022 |
Neg logit contributions | |
ases | -0.056 |
olds | -0.054 |
els | -0.052 |
cks | -0.051 |
its | -0.049 |
Token | Go |
Token ID | 1514 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
barrel | +0.016 |
puppy | +0.016 |
Bun | +0.016 |
bunny | +0.016 |
dark | +0.016 |
Neg logit contributions | |
ases | -0.076 |
els | -0.072 |
olds | -0.072 |
cks | -0.070 |
ips | -0.069 |
Token | away |
Token ID | 1497 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ases | +0.139 |
olds | +0.129 |
els | +0.127 |
cks | +0.122 |
ips | +0.121 |
Neg logit contributions | |
barrel | -0.076 |
hut | -0.074 |
bunny | -0.073 |
dark | -0.073 |
Bun | -0.072 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ases | +0.076 |
olds | +0.071 |
els | +0.070 |
cks | +0.068 |
ips | +0.066 |
Neg logit contributions | |
barrel | -0.033 |
puppy | -0.031 |
Bun | -0.031 |
dark | -0.031 |
bunny | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
ases | +0.063 |
els | +0.059 |
olds | +0.059 |
cks | +0.057 |
ips | +0.056 |
Neg logit contributions | |
barrel | -0.024 |
he | -0.024 |
Bun | -0.023 |
dark | -0.023 |
puppy | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
ases | +0.224 |
els | +0.217 |
olds | +0.207 |
cks | +0.203 |
ips | +0.203 |
Neg logit contributions | |
he | -0.058 |
Bun | -0.057 |
dark | -0.053 |
there | -0.052 |
little | -0.052 |
Token | L |
Token ID | 43 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
ases | +0.156 |
olds | +0.146 |
els | +0.145 |
cks | +0.141 |
ips | +0.137 |
Neg logit contributions | |
barrel | -0.077 |
puppy | -0.075 |
bunny | -0.075 |
dark | -0.075 |
Bun | -0.075 |
Token | ily |
Token ID | 813 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
ases | +0.261 |
els | +0.247 |
olds | +0.245 |
cks | +0.245 |
irs | +0.233 |
Neg logit contributions | |
he | -0.180 |
barrel | -0.179 |
there | -0.178 |
bunny | -0.178 |
puppy | -0.178 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ases | +0.129 |
olds | +0.123 |
els | +0.122 |
cks | +0.117 |
ips | +0.114 |
Neg logit contributions | |
barrel | -0.054 |
hut | -0.053 |
Bun | -0.051 |
dark | -0.051 |
cabin | -0.050 |
Token | Max |
Token ID | 5436 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
ases | +0.030 |
olds | +0.027 |
els | +0.027 |
cks | +0.026 |
ips | +0.025 |
Neg logit contributions | |
barrel | -0.023 |
hut | -0.022 |
dark | -0.022 |
cabin | -0.022 |
puppy | -0.022 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ases | +0.162 |
olds | +0.153 |
els | +0.151 |
cks | +0.147 |
ips | +0.143 |
Neg logit contributions | |
barrel | -0.068 |
hut | -0.066 |
Bun | -0.065 |
dark | -0.065 |
bunny | -0.065 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ases | +0.035 |
olds | +0.034 |
els | +0.032 |
cks | +0.032 |
its | +0.030 |
Neg logit contributions | |
barrel | -0.018 |
Bun | -0.017 |
hut | -0.017 |
bunny | -0.017 |
cabin | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
ases | +0.055 |
els | +0.052 |
olds | +0.052 |
cks | +0.051 |
irs | +0.049 |
Neg logit contributions | |
barrel | -0.014 |
dark | -0.014 |
he | -0.014 |
puppy | -0.014 |
bunny | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
dark | +0.014 |
he | +0.014 |
puppy | +0.013 |
barrel | +0.013 |
bunny | +0.013 |
Neg logit contributions | |
ases | -0.054 |
els | -0.051 |
cks | -0.051 |
olds | -0.050 |
irs | -0.049 |
Token | says |
Token ID | 1139 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
little | +0.038 |
lost | +0.037 |
dark | +0.037 |
wanted | +0.037 |
scary | +0.036 |
Neg logit contributions | |
ases | -0.042 |
els | -0.038 |
irs | -0.038 |
ips | -0.037 |
ums | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ases | +0.079 |
els | +0.074 |
cks | +0.073 |
olds | +0.073 |
ips | +0.071 |
Neg logit contributions | |
he | -0.022 |
dark | -0.021 |
barrel | -0.021 |
bunny | -0.021 |
puppy | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
ases | +0.075 |
els | +0.070 |
olds | +0.070 |
cks | +0.069 |
ips | +0.067 |
Neg logit contributions | |
barrel | -0.017 |
dark | -0.016 |
he | -0.016 |
bunny | -0.016 |
puppy | -0.016 |
Token | S |
Token ID | 50 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
ases | +0.125 |
olds | +0.117 |
els | +0.116 |
cks | +0.114 |
irs | +0.110 |
Neg logit contributions | |
dark | -0.050 |
puppy | -0.050 |
boy | -0.049 |
there | -0.049 |
bunny | -0.048 |
Token | ara |
Token ID | 3301 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
ases | +0.231 |
cks | +0.216 |
olds | +0.211 |
els | +0.198 |
irs | +0.191 |
Neg logit contributions | |
barrel | -0.237 |
puppy | -0.232 |
dark | -0.229 |
hut | -0.227 |
there | -0.226 |
Token | and |
Token ID | 290 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
ases | +0.200 |
els | +0.188 |
olds | +0.188 |
cks | +0.186 |
irs | +0.184 |
Neg logit contributions | |
barrel | -0.056 |
puppy | -0.055 |
bunny | -0.054 |
dark | -0.053 |
Bun | -0.053 |
Token | Tom |
Token ID | 4186 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
barrel | +0.001 |
Bun | +0.001 |
puppy | +0.001 |
dark | +0.001 |
bunny | +0.001 |
Neg logit contributions | |
ases | -0.002 |
olds | -0.001 |
els | -0.001 |
cks | -0.001 |
ips | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ases | +0.213 |
els | +0.202 |
olds | +0.201 |
cks | +0.196 |
irs | +0.195 |
Neg logit contributions | |
barrel | -0.056 |
dark | -0.056 |
puppy | -0.055 |
he | -0.054 |
bunny | -0.054 |
Token | what |
Token ID | 644 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
ases | +0.043 |
olds | +0.040 |
els | +0.040 |
cks | +0.038 |
ips | +0.037 |
Neg logit contributions | |
barrel | -0.030 |
puppy | -0.029 |
bunny | -0.029 |
dark | -0.029 |
he | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
ases | +0.087 |
olds | +0.082 |
els | +0.081 |
cks | +0.079 |
ips | +0.077 |
Neg logit contributions | |
barrel | -0.043 |
puppy | -0.042 |
dark | -0.042 |
bunny | -0.042 |
Bun | -0.042 |
Token | Now |
Token ID | 2735 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
barrel | +0.036 |
hut | +0.034 |
dark | +0.034 |
bunny | +0.034 |
Bun | +0.034 |
Neg logit contributions | |
ases | -0.068 |
olds | -0.064 |
els | -0.061 |
cks | -0.060 |
ips | -0.059 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
ases | +0.005 |
olds | +0.005 |
els | +0.005 |
cks | +0.005 |
ips | +0.004 |
Neg logit contributions | |
barrel | -0.002 |
Bun | -0.002 |
dark | -0.002 |
hut | -0.002 |
puppy | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
ases | +0.072 |
olds | +0.067 |
els | +0.067 |
cks | +0.065 |
ips | +0.063 |
Neg logit contributions | |
barrel | -0.029 |
dark | -0.028 |
puppy | -0.028 |
Bun | -0.028 |
bunny | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
ases | +0.256 |
els | +0.247 |
olds | +0.236 |
cks | +0.234 |
ips | +0.231 |
Neg logit contributions | |
Bun | -0.076 |
he | -0.073 |
dark | -0.070 |
bunny | -0.069 |
puppy | -0.069 |
Token | L |
Token ID | 43 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
ases | +0.193 |
els | +0.181 |
olds | +0.180 |
cks | +0.175 |
ips | +0.171 |
Neg logit contributions | |
barrel | -0.089 |
Bun | -0.088 |
puppy | -0.088 |
bunny | -0.088 |
dark | -0.088 |
Token | ily |
Token ID | 813 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
ases | +0.271 |
olds | +0.253 |
els | +0.253 |
cks | +0.248 |
irs | +0.234 |
Neg logit contributions | |
barrel | -0.213 |
bunny | -0.209 |
Bun | -0.209 |
puppy | -0.208 |
dark | -0.207 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ases | +0.142 |
olds | +0.134 |
els | +0.133 |
cks | +0.130 |
ips | +0.127 |
Neg logit contributions | |
barrel | -0.051 |
bunny | -0.050 |
puppy | -0.050 |
dark | -0.049 |
Bun | -0.049 |
Token | Ben |
Token ID | 3932 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
ases | +0.038 |
cks | +0.036 |
olds | +0.036 |
els | +0.035 |
its | +0.034 |
Neg logit contributions | |
bunny | -0.022 |
dark | -0.021 |
puppy | -0.021 |
he | -0.021 |
barrel | -0.020 |
Token | are |
Token ID | 389 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ases | +0.164 |
olds | +0.153 |
els | +0.151 |
cks | +0.146 |
ips | +0.142 |
Neg logit contributions | |
barrel | -0.114 |
puppy | -0.112 |
bunny | -0.111 |
Bun | -0.111 |
dark | -0.111 |
Token | ashamed |
Token ID | 22461 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ases | +0.087 |
olds | +0.082 |
els | +0.080 |
cks | +0.079 |
ips | +0.078 |
Neg logit contributions | |
barrel | -0.036 |
Bun | -0.034 |
bunny | -0.033 |
puppy | -0.033 |
hut | -0.032 |
Token | whim |
Token ID | 29923 |
Feature activation | -8.22e+00 |
Pos logit contributions | |
barrel | +0.005 |
hut | +0.005 |
cabin | +0.005 |
dark | +0.005 |
bicycle | +0.005 |
Neg logit contributions | |
ases | -0.011 |
olds | -0.011 |
els | -0.011 |
cks | -0.010 |
ips | -0.010 |
Token | pered |
Token ID | 13653 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
olds | +0.155 |
ases | +0.154 |
irs | +0.148 |
els | +0.141 |
ips | +0.135 |
Neg logit contributions | |
dark | -0.200 |
lost | -0.198 |
hut | -0.197 |
bunny | -0.196 |
Bun | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
ases | +0.132 |
olds | +0.124 |
els | +0.121 |
cks | +0.117 |
rs | +0.114 |
Neg logit contributions | |
barrel | -0.055 |
hut | -0.051 |
bunny | -0.050 |
cabin | -0.050 |
Bun | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
barrel | +0.011 |
hut | +0.011 |
puppy | +0.011 |
dark | +0.011 |
bunny | +0.011 |
Neg logit contributions | |
ases | -0.027 |
olds | -0.026 |
els | -0.025 |
cks | -0.025 |
ips | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
ases | +0.215 |
els | +0.209 |
ips | +0.197 |
cks | +0.195 |
olds | +0.194 |
Neg logit contributions | |
he | -0.044 |
Bun | -0.042 |
there | -0.036 |
Benny | -0.036 |
little | -0.035 |
Token | L |
Token ID | 43 |
Feature activation | -9.98e+00 |
Pos logit contributions | |
ases | +0.133 |
olds | +0.125 |
els | +0.123 |
cks | +0.119 |
ips | +0.116 |
Neg logit contributions | |
barrel | -0.082 |
puppy | -0.080 |
dark | -0.079 |
hut | -0.079 |
bunny | -0.079 |
Token | ily |
Token ID | 813 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
ases | +0.253 |
olds | +0.238 |
els | +0.236 |
cks | +0.232 |
irs | +0.220 |
Neg logit contributions | |
bunny | -0.191 |
Bun | -0.189 |
barrel | -0.189 |
he | -0.186 |
dark | -0.185 |
Token | 's |
Token ID | 338 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ases | +0.114 |
olds | +0.109 |
els | +0.107 |
cks | +0.103 |
ips | +0.100 |
Neg logit contributions | |
barrel | -0.053 |
dark | -0.052 |
hut | -0.052 |
Bun | -0.050 |
cabin | -0.050 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
ases | +0.040 |
olds | +0.038 |
els | +0.037 |
cks | +0.035 |
ips | +0.035 |
Neg logit contributions | |
barrel | -0.021 |
Bun | -0.020 |
he | -0.020 |
hut | -0.020 |
dark | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ases | +0.178 |
olds | +0.166 |
els | +0.163 |
cks | +0.163 |
irs | +0.160 |
Neg logit contributions | |
bunny | -0.040 |
barrel | -0.040 |
he | -0.040 |
puppy | -0.040 |
Bun | -0.039 |
Token | dad |
Token ID | 9955 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
barrel | +0.002 |
puppy | +0.002 |
bunny | +0.002 |
he | +0.002 |
hut | +0.002 |
Neg logit contributions | |
ases | -0.003 |
olds | -0.003 |
els | -0.003 |
cks | -0.003 |
its | -0.003 |