Token | It |
Token ID | 632 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
seek | +0.038 |
moral | +0.029 |
ider | +0.028 |
ifi | +0.027 |
onna | +0.027 |
Neg logit contributions | |
aw | -0.053 |
hing | -0.050 |
ming | -0.049 |
ding | -0.048 |
flashing | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
seek | +0.007 |
One | +0.006 |
One | +0.005 |
moment | +0.005 |
moral | +0.004 |
Neg logit contributions | |
hing | -0.019 |
aw | -0.018 |
ming | -0.017 |
ong | -0.017 |
eping | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
hing | +0.011 |
ming | +0.011 |
aw | +0.010 |
flashing | +0.010 |
eping | +0.010 |
Neg logit contributions | |
seek | -0.006 |
One | -0.005 |
One | -0.005 |
onna | -0.004 |
moral | -0.004 |
Token | fortune |
Token ID | 15807 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
seek | +0.063 |
One | +0.051 |
moment | +0.051 |
One | +0.050 |
moral | +0.049 |
Neg logit contributions | |
hing | -0.081 |
ming | -0.073 |
aw | -0.072 |
eping | -0.068 |
ning | -0.067 |
Token | - |
Token ID | 12 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
seek | +0.067 |
One | +0.051 |
One | +0.050 |
moment | +0.050 |
onna | +0.049 |
Neg logit contributions | |
hing | -0.110 |
ming | -0.099 |
aw | -0.097 |
eping | -0.095 |
channels | -0.094 |
Token | te |
Token ID | 660 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
seek | +0.041 |
One | +0.037 |
One | +0.035 |
onna | +0.034 |
moral | +0.034 |
Neg logit contributions | |
hing | -0.047 |
aw | -0.043 |
ming | -0.043 |
eping | -0.041 |
flashing | -0.040 |
Token | ller |
Token ID | 6051 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
seek | +0.371 |
One | +0.338 |
One | +0.336 |
moral | +0.318 |
onna | +0.309 |
Neg logit contributions | |
hing | -0.283 |
ming | -0.261 |
aw | -0.255 |
flashing | -0.242 |
ong | -0.239 |
Token | toy |
Token ID | 13373 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
seek | +0.075 |
One | +0.064 |
One | +0.062 |
onna | +0.058 |
moment | +0.057 |
Neg logit contributions | |
hing | -0.119 |
ming | -0.107 |
aw | -0.105 |
eping | -0.103 |
ding | -0.102 |
Token | ! |
Token ID | 0 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hing | +0.028 |
ming | +0.026 |
aw | +0.025 |
eping | +0.025 |
ding | +0.025 |
Neg logit contributions | |
seek | -0.013 |
One | -0.011 |
One | -0.010 |
onna | -0.009 |
moral | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
aw | +0.063 |
hing | +0.057 |
ming | +0.057 |
ding | +0.055 |
flashing | +0.054 |
Neg logit contributions | |
seek | -0.049 |
moral | -0.038 |
ider | -0.037 |
One | -0.037 |
ifi | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
seek | +0.025 |
ider | +0.021 |
ro | +0.017 |
allowance | +0.017 |
gn | +0.017 |
Neg logit contributions | |
hing | -0.046 |
aw | -0.045 |
ming | -0.043 |
eping | -0.042 |
ong | -0.041 |
Token | imagined |
Token ID | 15758 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
seek | +0.031 |
One | +0.027 |
One | +0.026 |
onna | +0.024 |
moral | +0.024 |
Neg logit contributions | |
hing | -0.050 |
ming | -0.046 |
aw | -0.045 |
eping | -0.043 |
flashing | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
seek | +0.019 |
One | +0.017 |
One | +0.017 |
onna | +0.015 |
ifi | +0.015 |
Neg logit contributions | |
hing | -0.023 |
ming | -0.022 |
aw | -0.022 |
flashing | -0.021 |
ding | -0.021 |
Token | tart |
Token ID | 35842 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
seek | +0.041 |
One | +0.036 |
One | +0.036 |
moral | +0.034 |
moment | +0.034 |
Neg logit contributions | |
hing | -0.050 |
ming | -0.045 |
aw | -0.044 |
eping | -0.043 |
flashing | -0.042 |
Token | was |
Token ID | 373 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
seek | +0.032 |
One | +0.028 |
One | +0.027 |
onna | +0.025 |
moral | +0.025 |
Neg logit contributions | |
hing | -0.045 |
ming | -0.041 |
aw | -0.040 |
eping | -0.039 |
flashing | -0.039 |
Token | long |
Token ID | 890 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
seek | +0.030 |
One | +0.026 |
One | +0.026 |
moral | +0.023 |
moment | +0.023 |
Neg logit contributions | |
hing | -0.038 |
ming | -0.035 |
aw | -0.034 |
flashing | -0.034 |
eping | -0.034 |
Token | ago |
Token ID | 2084 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
seek | +0.021 |
One | +0.019 |
One | +0.018 |
ifi | +0.017 |
moral | +0.017 |
Neg logit contributions | |
hing | -0.033 |
ming | -0.031 |
aw | -0.030 |
flashing | -0.029 |
eping | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
seek | +0.228 |
One | +0.209 |
One | +0.204 |
moral | +0.187 |
ifi | +0.185 |
Neg logit contributions | |
hing | -0.392 |
ming | -0.373 |
aw | -0.370 |
flashing | -0.354 |
ong | -0.354 |
Token | when |
Token ID | 618 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
seek | +0.113 |
One | +0.098 |
One | +0.098 |
ifi | +0.094 |
rog | +0.092 |
Neg logit contributions | |
hing | -0.118 |
ding | -0.113 |
aw | -0.112 |
ming | -0.112 |
flashing | -0.109 |
Token | she |
Token ID | 673 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
hing | +0.013 |
aw | +0.013 |
flashing | +0.013 |
ming | +0.013 |
ding | +0.013 |
Neg logit contributions | |
seek | -0.008 |
onna | -0.007 |
One | -0.006 |
One | -0.006 |
rog | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
hing | +0.046 |
ming | +0.042 |
aw | +0.042 |
eping | +0.040 |
flashing | +0.039 |
Neg logit contributions | |
seek | -0.035 |
One | -0.031 |
One | -0.030 |
onna | -0.028 |
moral | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
hing | +0.022 |
ming | +0.019 |
aw | +0.019 |
flashing | +0.018 |
ning | +0.018 |
Neg logit contributions | |
seek | -0.017 |
One | -0.015 |
One | -0.014 |
onna | -0.014 |
moral | -0.013 |
Token | - |
Token ID | 12 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
seek | +0.227 |
One | +0.203 |
One | +0.199 |
onna | +0.190 |
moment | +0.188 |
Neg logit contributions | |
hing | -0.172 |
aw | -0.156 |
ming | -0.155 |
eping | -0.145 |
ding | -0.141 |
Token | one |
Token ID | 505 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
hing | +0.051 |
aw | +0.049 |
ming | +0.047 |
eping | +0.046 |
ding | +0.044 |
Neg logit contributions | |
seek | -0.038 |
One | -0.030 |
D | -0.029 |
moment | -0.029 |
onna | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
seek | +0.105 |
One | +0.098 |
One | +0.094 |
moral | +0.084 |
moment | +0.084 |
Neg logit contributions | |
hing | -0.158 |
ming | -0.143 |
aw | -0.138 |
eping | -0.136 |
flashing | -0.135 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
seek | +0.049 |
One | +0.039 |
One | +0.039 |
onna | +0.039 |
ifi | +0.037 |
Neg logit contributions | |
hing | -0.068 |
ming | -0.064 |
aw | -0.063 |
ding | -0.062 |
flashing | -0.061 |
Token | - |
Token ID | 12 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
seek | +0.227 |
One | +0.204 |
One | +0.200 |
onna | +0.191 |
moral | +0.189 |
Neg logit contributions | |
hing | -0.170 |
aw | -0.153 |
ming | -0.153 |
eping | -0.143 |
flashing | -0.140 |
Token | two |
Token ID | 11545 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
hing | +0.049 |
aw | +0.047 |
ming | +0.045 |
eping | +0.043 |
ding | +0.042 |
Neg logit contributions | |
seek | -0.036 |
One | -0.028 |
moment | -0.027 |
D | -0.027 |
onna | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
seek | +0.247 |
One | +0.211 |
One | +0.207 |
onna | +0.190 |
moral | +0.187 |
Neg logit contributions | |
hing | -0.397 |
ming | -0.367 |
aw | -0.364 |
eping | -0.349 |
flashing | -0.347 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
seek | +0.044 |
One | +0.036 |
One | +0.035 |
onna | +0.035 |
ifi | +0.034 |
Neg logit contributions | |
hing | -0.061 |
ming | -0.058 |
aw | -0.057 |
ding | -0.056 |
flashing | -0.055 |
Token | - |
Token ID | 12 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
seek | +0.235 |
One | +0.210 |
One | +0.206 |
onna | +0.197 |
moment | +0.195 |
Neg logit contributions | |
hing | -0.163 |
aw | -0.149 |
ming | -0.147 |
eping | -0.137 |
ding | -0.134 |
Token | three |
Token ID | 15542 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
hing | +0.031 |
aw | +0.030 |
ming | +0.029 |
ding | +0.028 |
eping | +0.027 |
Neg logit contributions | |
seek | -0.022 |
One | -0.018 |
moment | -0.016 |
D | -0.016 |
moral | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
seek | +0.224 |
One | +0.184 |
One | +0.181 |
moral | +0.174 |
onna | +0.173 |
Neg logit contributions | |
hing | -0.322 |
aw | -0.308 |
ming | -0.302 |
ong | -0.281 |
eping | -0.281 |
Token | - |
Token ID | 12 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
seek | +0.157 |
One | +0.136 |
D | +0.131 |
One | +0.128 |
etsy | +0.122 |
Neg logit contributions | |
aw | -0.188 |
hing | -0.173 |
ong | -0.168 |
ming | -0.167 |
ding | -0.167 |
Token | one |
Token ID | 505 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
aw | +0.029 |
hing | +0.029 |
ming | +0.028 |
ding | +0.027 |
ong | +0.026 |
Neg logit contributions | |
seek | -0.025 |
One | -0.022 |
One | -0.020 |
moment | -0.019 |
moral | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
seek | +0.064 |
One | +0.055 |
One | +0.053 |
onna | +0.048 |
moral | +0.047 |
Neg logit contributions | |
hing | -0.118 |
ming | -0.109 |
aw | -0.107 |
eping | -0.104 |
flashing | -0.104 |
Token | twenty |
Token ID | 8208 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
seek | +0.048 |
One | +0.040 |
One | +0.040 |
ifi | +0.038 |
onna | +0.038 |
Neg logit contributions | |
hing | -0.052 |
aw | -0.048 |
ming | -0.048 |
ding | -0.047 |
flashing | -0.045 |
Token | - |
Token ID | 12 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
seek | +0.163 |
One | +0.141 |
D | +0.136 |
One | +0.133 |
etsy | +0.126 |
Neg logit contributions | |
aw | -0.192 |
hing | -0.174 |
ong | -0.171 |
ming | -0.170 |
ding | -0.168 |
Token | two |
Token ID | 11545 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
aw | +0.024 |
hing | +0.024 |
ming | +0.023 |
ding | +0.022 |
ong | +0.021 |
Neg logit contributions | |
seek | -0.020 |
One | -0.017 |
One | -0.016 |
moment | -0.016 |
moral | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
seek | +0.270 |
One | +0.226 |
One | +0.222 |
D | +0.208 |
Tweet | +0.207 |
Neg logit contributions | |
aw | -0.346 |
hing | -0.338 |
ming | -0.329 |
ong | -0.317 |
ning | -0.312 |
Token | twenty |
Token ID | 8208 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
seek | +0.069 |
One | +0.057 |
One | +0.057 |
ifi | +0.055 |
moment | +0.054 |
Neg logit contributions | |
hing | -0.072 |
aw | -0.068 |
ding | -0.067 |
ming | -0.067 |
flashing | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
seek | +0.184 |
One | +0.160 |
D | +0.154 |
One | +0.152 |
Buzz | +0.142 |
Neg logit contributions | |
aw | -0.198 |
hing | -0.181 |
ong | -0.178 |
ming | -0.177 |
ding | -0.171 |
Token | three |
Token ID | 15542 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
aw | +0.023 |
hing | +0.021 |
ming | +0.021 |
ding | +0.020 |
ong | +0.020 |
Neg logit contributions | |
seek | -0.019 |
One | -0.017 |
moral | -0.015 |
moment | -0.015 |
D | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
seek | +0.245 |
One | +0.208 |
One | +0.203 |
moral | +0.201 |
ifi | +0.199 |
Neg logit contributions | |
aw | -0.299 |
hing | -0.289 |
ming | -0.278 |
ong | -0.270 |
ding | -0.259 |
Token | - |
Token ID | 12 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
seek | +0.260 |
One | +0.236 |
One | +0.232 |
onna | +0.220 |
moral | +0.218 |
Neg logit contributions | |
hing | -0.185 |
ming | -0.166 |
aw | -0.164 |
eping | -0.152 |
ding | -0.151 |
Token | one |
Token ID | 505 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
hing | +0.001 |
aw | +0.001 |
ming | +0.001 |
ding | +0.001 |
ong | +0.001 |
Neg logit contributions | |
seek | -0.001 |
One | -0.000 |
One | -0.000 |
moment | -0.000 |
D | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
seek | +0.077 |
One | +0.069 |
One | +0.067 |
onna | +0.059 |
moment | +0.059 |
Neg logit contributions | |
hing | -0.151 |
ming | -0.137 |
aw | -0.136 |
eping | -0.133 |
flashing | -0.132 |
Token | forty |
Token ID | 16571 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
seek | +0.072 |
One | +0.061 |
One | +0.059 |
onna | +0.057 |
ifi | +0.056 |
Neg logit contributions | |
hing | -0.091 |
ming | -0.084 |
aw | -0.083 |
ding | -0.081 |
flashing | -0.080 |
Token | - |
Token ID | 12 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
seek | +0.266 |
One | +0.241 |
One | +0.237 |
onna | +0.224 |
moral | +0.222 |
Neg logit contributions | |
hing | -0.185 |
ming | -0.166 |
aw | -0.165 |
eping | -0.152 |
ding | -0.151 |
Token | two |
Token ID | 11545 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
seek | +0.001 |
One | +0.001 |
One | +0.001 |
moment | +0.001 |
D | +0.001 |
Neg logit contributions | |
hing | -0.001 |
aw | -0.001 |
ming | -0.001 |
ding | -0.001 |
ong | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
seek | +0.242 |
One | +0.206 |
One | +0.202 |
onna | +0.185 |
moral | +0.182 |
Neg logit contributions | |
hing | -0.389 |
ming | -0.362 |
aw | -0.358 |
eping | -0.342 |
flashing | -0.340 |
Token | forty |
Token ID | 16571 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
seek | +0.068 |
One | +0.056 |
One | +0.055 |
ifi | +0.054 |
onna | +0.053 |
Neg logit contributions | |
hing | -0.075 |
ming | -0.071 |
aw | -0.069 |
ding | -0.069 |
flashing | -0.066 |
Token | - |
Token ID | 12 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
seek | +0.271 |
One | +0.246 |
One | +0.241 |
onna | +0.229 |
moment | +0.227 |
Neg logit contributions | |
hing | -0.170 |
aw | -0.157 |
ming | -0.155 |
eping | -0.141 |
ding | -0.140 |
Token | three |
Token ID | 15542 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
hing | +0.011 |
aw | +0.011 |
ming | +0.011 |
ding | +0.010 |
ong | +0.010 |
Neg logit contributions | |
seek | -0.008 |
One | -0.007 |
D | -0.006 |
moment | -0.006 |
moral | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
seek | +0.221 |
One | +0.186 |
One | +0.181 |
moral | +0.174 |
ifi | +0.172 |
Neg logit contributions | |
hing | -0.317 |
aw | -0.305 |
ming | -0.302 |
ong | -0.280 |
ding | -0.277 |
Token | - |
Token ID | 12 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
seek | +0.153 |
One | +0.128 |
onna | +0.125 |
D | +0.123 |
One | +0.120 |
Neg logit contributions | |
aw | -0.189 |
hing | -0.183 |
ming | -0.173 |
eping | -0.170 |
ding | -0.165 |
Token | eight |
Token ID | 26022 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
aw | +0.047 |
hing | +0.047 |
eping | +0.043 |
ming | +0.043 |
ding | +0.041 |
Neg logit contributions | |
seek | -0.046 |
One | -0.038 |
D | -0.036 |
moment | -0.036 |
onna | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
seek | +0.211 |
onna | +0.174 |
One | +0.173 |
emo | +0.172 |
One | +0.170 |
Neg logit contributions | |
aw | -0.256 |
ming | -0.245 |
hing | -0.239 |
ning | -0.228 |
flashing | -0.219 |
Token | twenty |
Token ID | 8208 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
seek | +0.057 |
onna | +0.045 |
ib | +0.044 |
ro | +0.043 |
ifi | +0.043 |
Neg logit contributions | |
hing | -0.067 |
ding | -0.065 |
aw | -0.065 |
ming | -0.064 |
flashing | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
seek | +0.187 |
One | +0.161 |
onna | +0.155 |
One | +0.154 |
D | +0.153 |
Neg logit contributions | |
hing | -0.178 |
aw | -0.177 |
ming | -0.165 |
eping | -0.159 |
ding | -0.153 |
Token | nine |
Token ID | 30888 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
hing | +0.041 |
aw | +0.041 |
ming | +0.038 |
eping | +0.037 |
ding | +0.036 |
Neg logit contributions | |
seek | -0.035 |
One | -0.028 |
D | -0.027 |
moment | -0.027 |
onna | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
seek | +0.242 |
One | +0.204 |
One | +0.203 |
moral | +0.188 |
onna | +0.184 |
Neg logit contributions | |
hing | -0.387 |
ming | -0.365 |
aw | -0.357 |
flashing | -0.337 |
eping | -0.337 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
seek | +0.056 |
onna | +0.045 |
One | +0.043 |
One | +0.043 |
ifi | +0.043 |
Neg logit contributions | |
hing | -0.075 |
ming | -0.070 |
ding | -0.069 |
aw | -0.069 |
flashing | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
seek | +0.231 |
One | +0.206 |
One | +0.202 |
onna | +0.194 |
moment | +0.191 |
Neg logit contributions | |
hing | -0.171 |
aw | -0.158 |
ming | -0.155 |
eping | -0.145 |
ding | -0.140 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
seek | +0.052 |
onna | +0.041 |
One | +0.041 |
One | +0.041 |
ifi | +0.040 |
Neg logit contributions | |
hing | -0.070 |
ming | -0.066 |
aw | -0.065 |
ding | -0.064 |
flashing | -0.063 |
Token | - |
Token ID | 12 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
seek | +0.227 |
One | +0.203 |
One | +0.199 |
onna | +0.190 |
moment | +0.188 |
Neg logit contributions | |
hing | -0.172 |
aw | -0.156 |
ming | -0.155 |
eping | -0.145 |
ding | -0.141 |
Token | - |
Token ID | 12 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
seek | +0.193 |
One | +0.172 |
One | +0.169 |
D | +0.161 |
onna | +0.158 |
Neg logit contributions | |
hing | -0.158 |
aw | -0.156 |
ming | -0.151 |
ding | -0.140 |
ong | -0.138 |
Token | one |
Token ID | 505 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
aw | +0.039 |
hing | +0.038 |
ming | +0.037 |
ding | +0.035 |
ong | +0.034 |
Neg logit contributions | |
seek | -0.032 |
One | -0.027 |
moral | -0.025 |
moment | -0.025 |
D | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
seek | +0.054 |
One | +0.046 |
One | +0.045 |
onna | +0.040 |
moment | +0.040 |
Neg logit contributions | |
hing | -0.102 |
ming | -0.094 |
aw | -0.092 |
eping | -0.090 |
flashing | -0.089 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
seek | +0.039 |
One | +0.032 |
One | +0.031 |
onna | +0.031 |
ifi | +0.031 |
Neg logit contributions | |
hing | -0.045 |
ming | -0.043 |
aw | -0.042 |
ding | -0.041 |
flashing | -0.039 |
Token | - |
Token ID | 12 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
seek | +0.179 |
One | +0.159 |
One | +0.156 |
D | +0.149 |
onna | +0.146 |
Neg logit contributions | |
hing | -0.155 |
aw | -0.154 |
ming | -0.149 |
ding | -0.139 |
ong | -0.137 |
Token | two |
Token ID | 11545 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
aw | +0.041 |
hing | +0.040 |
ming | +0.039 |
ding | +0.037 |
ong | +0.035 |
Neg logit contributions | |
seek | -0.033 |
One | -0.028 |
moment | -0.026 |
moral | -0.026 |
D | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
seek | +0.252 |
One | +0.210 |
One | +0.208 |
onna | +0.192 |
D | +0.189 |
Neg logit contributions | |
hing | -0.347 |
aw | -0.338 |
ming | -0.334 |
ong | -0.312 |
ding | -0.312 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
seek | +0.069 |
ifi | +0.056 |
One | +0.055 |
One | +0.054 |
emo | +0.054 |
Neg logit contributions | |
hing | -0.064 |
ming | -0.062 |
ding | -0.062 |
aw | -0.061 |
ning | -0.057 |
Token | - |
Token ID | 12 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
seek | +0.233 |
One | +0.212 |
One | +0.205 |
D | +0.202 |
onna | +0.194 |
Neg logit contributions | |
aw | -0.143 |
hing | -0.138 |
ming | -0.135 |
ong | -0.122 |
ding | -0.121 |
Token | three |
Token ID | 15542 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
aw | +0.048 |
hing | +0.045 |
ming | +0.044 |
ding | +0.042 |
ong | +0.040 |
Neg logit contributions | |
seek | -0.039 |
One | -0.035 |
moral | -0.032 |
D | -0.031 |
moment | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
seek | +0.219 |
One | +0.184 |
One | +0.182 |
moral | +0.177 |
ifi | +0.175 |
Neg logit contributions | |
hing | -0.278 |
aw | -0.278 |
ming | -0.268 |
ong | -0.251 |
ding | -0.246 |
Token | showed |
Token ID | 3751 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
seek | +0.045 |
One | +0.039 |
One | +0.039 |
onna | +0.036 |
moral | +0.035 |
Neg logit contributions | |
hing | -0.066 |
ming | -0.062 |
aw | -0.060 |
eping | -0.058 |
ding | -0.057 |
Token | him |
Token ID | 683 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Lily | +0.021 |
One | +0.020 |
D | +0.017 |
seek | +0.017 |
one | +0.016 |
Neg logit contributions | |
hing | -0.045 |
aw | -0.042 |
eping | -0.042 |
ding | -0.041 |
flashing | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
hing | +0.021 |
ming | +0.019 |
aw | +0.019 |
eping | +0.018 |
flashing | +0.018 |
Neg logit contributions | |
seek | -0.018 |
One | -0.016 |
One | -0.016 |
onna | -0.015 |
moral | -0.015 |
Token | other |
Token ID | 584 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
seek | +0.070 |
One | +0.062 |
One | +0.062 |
onna | +0.057 |
ifi | +0.056 |
Neg logit contributions | |
hing | -0.069 |
ming | -0.063 |
aw | -0.060 |
flashing | -0.059 |
eping | -0.058 |
Token | bath |
Token ID | 7837 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
seek | +0.048 |
One | +0.043 |
One | +0.042 |
onna | +0.039 |
moral | +0.039 |
Neg logit contributions | |
hing | -0.049 |
ming | -0.044 |
aw | -0.044 |
eping | -0.042 |
flashing | -0.041 |
Token | ro |
Token ID | 305 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
seek | +0.065 |
One | +0.055 |
One | +0.053 |
moment | +0.051 |
onna | +0.050 |
Neg logit contributions | |
hing | -0.097 |
aw | -0.088 |
ming | -0.088 |
eping | -0.086 |
ding | -0.085 |
Token | bes |
Token ID | 12636 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
One | +0.217 |
seek | +0.210 |
One | +0.207 |
moral | +0.186 |
ifi | +0.181 |
Neg logit contributions | |
hing | -0.361 |
ming | -0.357 |
eping | -0.338 |
aw | -0.336 |
ning | -0.317 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
seek | +0.081 |
One | +0.068 |
One | +0.065 |
moral | +0.055 |
moment | +0.055 |
Neg logit contributions | |
hing | -0.225 |
ming | -0.208 |
aw | -0.205 |
ding | -0.201 |
eping | -0.201 |
Token | She |
Token ID | 1375 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
hing | +0.016 |
ming | +0.016 |
aw | +0.015 |
channels | +0.015 |
ding | +0.015 |
Neg logit contributions | |
seek | -0.014 |
ifi | -0.011 |
moment | -0.010 |
moral | -0.010 |
One | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
seek | +0.020 |
One | +0.017 |
One | +0.017 |
onna | +0.016 |
moment | +0.016 |
Neg logit contributions | |
hing | -0.027 |
ming | -0.026 |
aw | -0.025 |
eping | -0.024 |
flashing | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
seek | +0.079 |
One | +0.069 |
One | +0.068 |
moment | +0.064 |
moral | +0.064 |
Neg logit contributions | |
hing | -0.095 |
ming | -0.088 |
aw | -0.086 |
flashing | -0.083 |
eping | -0.083 |
Token | - |
Token ID | 12 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
seek | +0.187 |
One | +0.169 |
One | +0.165 |
onna | +0.156 |
moral | +0.154 |
Neg logit contributions | |
hing | -0.151 |
aw | -0.139 |
ming | -0.139 |
ding | -0.128 |
eping | -0.128 |
Token | one |
Token ID | 505 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
hing | +0.050 |
aw | +0.050 |
ming | +0.048 |
ding | +0.046 |
ong | +0.044 |
Neg logit contributions | |
seek | -0.040 |
One | -0.033 |
moral | -0.032 |
moment | -0.032 |
D | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
seek | +0.040 |
One | +0.035 |
One | +0.034 |
onna | +0.030 |
moral | +0.030 |
Neg logit contributions | |
hing | -0.078 |
ming | -0.072 |
aw | -0.071 |
eping | -0.069 |
flashing | -0.068 |
Token | forty |
Token ID | 16571 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
seek | +0.020 |
One | +0.017 |
One | +0.016 |
onna | +0.016 |
ifi | +0.015 |
Neg logit contributions | |
hing | -0.025 |
ming | -0.023 |
aw | -0.023 |
ding | -0.022 |
flashing | -0.022 |
Token | - |
Token ID | 12 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
seek | +0.176 |
One | +0.158 |
One | +0.155 |
onna | +0.146 |
moral | +0.145 |
Neg logit contributions | |
hing | -0.151 |
ming | -0.139 |
aw | -0.139 |
ding | -0.128 |
eping | -0.128 |
Token | two |
Token ID | 11545 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
hing | +0.048 |
aw | +0.047 |
ming | +0.046 |
ding | +0.044 |
ong | +0.041 |
Neg logit contributions | |
seek | -0.039 |
One | -0.032 |
moment | -0.031 |
moral | -0.031 |
D | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
seek | +0.238 |
One | +0.199 |
One | +0.196 |
onna | +0.182 |
moral | +0.178 |
Neg logit contributions | |
hing | -0.354 |
aw | -0.336 |
ming | -0.336 |
eping | -0.314 |
ding | -0.314 |
Token | forty |
Token ID | 16571 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
seek | +0.061 |
ifi | +0.049 |
One | +0.049 |
One | +0.047 |
D | +0.047 |
Neg logit contributions | |
hing | -0.059 |
ming | -0.057 |
ding | -0.056 |
aw | -0.055 |
ning | -0.052 |
Token | - |
Token ID | 12 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
seek | +0.233 |
One | +0.212 |
One | +0.207 |
D | +0.196 |
onna | +0.196 |
Neg logit contributions | |
hing | -0.143 |
aw | -0.137 |
ming | -0.133 |
ding | -0.120 |
ong | -0.119 |
Token | three |
Token ID | 15542 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
aw | +0.056 |
hing | +0.053 |
ming | +0.052 |
ding | +0.049 |
ong | +0.046 |
Neg logit contributions | |
seek | -0.046 |
One | -0.040 |
moral | -0.038 |
D | -0.037 |
moment | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
seek | +0.204 |
One | +0.171 |
One | +0.168 |
moral | +0.162 |
ifi | +0.161 |
Neg logit contributions | |
hing | -0.277 |
aw | -0.271 |
ming | -0.265 |
ong | -0.246 |
ding | -0.244 |
Token | - |
Token ID | 12 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
seek | +0.223 |
One | +0.196 |
D | +0.190 |
One | +0.189 |
onna | +0.180 |
Neg logit contributions | |
aw | -0.181 |
hing | -0.172 |
ming | -0.163 |
eping | -0.156 |
ong | -0.154 |
Token | eight |
Token ID | 26022 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
aw | +0.019 |
hing | +0.018 |
ming | +0.017 |
ding | +0.016 |
eping | +0.016 |
Neg logit contributions | |
seek | -0.016 |
One | -0.014 |
moment | -0.013 |
moral | -0.013 |
allowance | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
seek | +0.231 |
One | +0.201 |
One | +0.192 |
moral | +0.191 |
Yesterday | +0.187 |
Neg logit contributions | |
aw | -0.241 |
ming | -0.238 |
hing | -0.229 |
ning | -0.222 |
flashing | -0.210 |
Token | twenty |
Token ID | 8208 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
seek | +0.081 |
ifi | +0.067 |
etsy | +0.066 |
emo | +0.065 |
ro | +0.062 |
Neg logit contributions | |
ding | -0.060 |
aw | -0.057 |
hing | -0.055 |
ming | -0.054 |
flashing | -0.050 |
Token | - |
Token ID | 12 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
seek | +0.195 |
One | +0.169 |
D | +0.164 |
One | +0.164 |
Tweet | +0.154 |
Neg logit contributions | |
aw | -0.175 |
hing | -0.164 |
ming | -0.159 |
ong | -0.152 |
eping | -0.151 |
Token | nine |
Token ID | 30888 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
aw | +0.033 |
hing | +0.031 |
ming | +0.030 |
ding | +0.029 |
ong | +0.028 |
Neg logit contributions | |
seek | -0.028 |
One | -0.023 |
moment | -0.022 |
moral | -0.022 |
D | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
seek | +0.236 |
One | +0.204 |
One | +0.200 |
moral | +0.187 |
onna | +0.176 |
Neg logit contributions | |
hing | -0.357 |
ming | -0.342 |
aw | -0.336 |
ong | -0.312 |
flashing | -0.312 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
seek | +0.062 |
ifi | +0.051 |
emo | +0.050 |
etsy | +0.049 |
onna | +0.048 |
Neg logit contributions | |
ding | -0.051 |
hing | -0.050 |
aw | -0.049 |
ming | -0.049 |
ning | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
seek | +0.209 |
One | +0.186 |
One | +0.183 |
D | +0.175 |
moral | +0.171 |
Neg logit contributions | |
hing | -0.160 |
aw | -0.160 |
ming | -0.153 |
ding | -0.141 |
ong | -0.141 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
seek | +0.053 |
ifi | +0.043 |
emo | +0.042 |
One | +0.042 |
onna | +0.041 |
Neg logit contributions | |
hing | -0.049 |
ding | -0.047 |
ming | -0.047 |
aw | -0.046 |
ning | -0.044 |
Token | - |
Token ID | 12 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
seek | +0.193 |
One | +0.172 |
One | +0.169 |
D | +0.161 |
onna | +0.158 |
Neg logit contributions | |
hing | -0.158 |
aw | -0.156 |
ming | -0.151 |
ding | -0.140 |
ong | -0.138 |
Token | another |
Token ID | 1194 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
seek | +0.034 |
orse | +0.032 |
emo | +0.032 |
ider | +0.032 |
ifi | +0.030 |
Neg logit contributions | |
flashing | -0.028 |
out | -0.027 |
ding | -0.027 |
hing | -0.026 |
channels | -0.026 |
Token | hole |
Token ID | 7604 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
seek | +0.029 |
One | +0.026 |
One | +0.025 |
onna | +0.023 |
moral | +0.023 |
Neg logit contributions | |
hing | -0.034 |
ming | -0.031 |
aw | -0.031 |
eping | -0.030 |
flashing | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
hing | +0.193 |
aw | +0.181 |
ming | +0.181 |
flashing | +0.172 |
eping | +0.171 |
Neg logit contributions | |
seek | -0.105 |
One | -0.088 |
One | -0.088 |
moral | -0.078 |
onna | -0.076 |
Token | said |
Token ID | 531 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
hing | +0.035 |
ming | +0.032 |
aw | +0.032 |
eping | +0.031 |
flashing | +0.030 |
Neg logit contributions | |
seek | -0.026 |
One | -0.023 |
One | -0.022 |
onna | -0.021 |
moral | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
hing | +0.045 |
aw | +0.042 |
ming | +0.042 |
ding | +0.041 |
ong | +0.041 |
Neg logit contributions | |
seek | -0.024 |
One | -0.020 |
One | -0.018 |
ifi | -0.017 |
moral | -0.017 |
Token | two |
Token ID | 11545 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
hing | +0.026 |
ming | +0.024 |
aw | +0.023 |
ding | +0.022 |
eping | +0.022 |
Neg logit contributions | |
seek | -0.018 |
One | -0.016 |
onna | -0.015 |
moral | -0.015 |
ifi | -0.015 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
seek | +0.245 |
One | +0.212 |
One | +0.210 |
onna | +0.193 |
moment | +0.190 |
Neg logit contributions | |
hing | -0.341 |
aw | -0.324 |
ming | -0.323 |
ong | -0.303 |
eping | -0.302 |
Token | She |
Token ID | 1375 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
seek | +0.077 |
ifi | +0.060 |
One | +0.053 |
moral | +0.051 |
orse | +0.051 |
Neg logit contributions | |
hing | -0.102 |
aw | -0.100 |
ming | -0.098 |
channels | -0.097 |
ding | -0.096 |
Token | did |
Token ID | 750 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
seek | +0.028 |
One | +0.025 |
One | +0.024 |
moment | +0.023 |
onna | +0.023 |
Neg logit contributions | |
hing | -0.039 |
ming | -0.036 |
aw | -0.036 |
eping | -0.034 |
flashing | -0.034 |
Token | this |
Token ID | 428 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
seek | +0.054 |
ifi | +0.043 |
ib | +0.042 |
One | +0.042 |
etsy | +0.042 |
Neg logit contributions | |
hing | -0.091 |
ming | -0.091 |
ding | -0.089 |
aw | -0.088 |
ong | -0.087 |
Token | until |
Token ID | 1566 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
seek | +0.027 |
One | +0.021 |
One | +0.021 |
onna | +0.020 |
ifi | +0.019 |
Neg logit contributions | |
hing | -0.055 |
ming | -0.052 |
aw | -0.051 |
ding | -0.049 |
ning | -0.049 |
Token | " |
Token ID | 366 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
aw | +0.006 |
ding | +0.005 |
hing | +0.005 |
flashing | +0.005 |
ming | +0.005 |
Neg logit contributions | |
seek | -0.005 |
moral | -0.004 |
allowance | -0.004 |
ifi | -0.004 |
One | -0.004 |
Token | I |
Token ID | 40 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
hing | +0.091 |
aw | +0.083 |
ding | +0.079 |
ming | +0.076 |
eping | +0.072 |
Neg logit contributions | |
seek | -0.074 |
onna | -0.061 |
One | -0.061 |
allowance | -0.061 |
moment | -0.059 |
Token | 'm |
Token ID | 1101 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
hing | +0.009 |
ming | +0.008 |
aw | +0.008 |
eping | +0.008 |
flashing | +0.008 |
Neg logit contributions | |
seek | -0.006 |
One | -0.006 |
One | -0.006 |
moral | -0.005 |
moment | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
seek | +0.011 |
One | +0.009 |
One | +0.009 |
onna | +0.009 |
moral | +0.009 |
Neg logit contributions | |
hing | -0.012 |
ming | -0.011 |
aw | -0.011 |
eping | -0.010 |
flashing | -0.010 |
Token | tight |
Token ID | 5381 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
seek | +0.022 |
One | +0.020 |
One | +0.019 |
onna | +0.018 |
moral | +0.018 |
Neg logit contributions | |
hing | -0.029 |
ming | -0.026 |
aw | -0.026 |
eping | -0.025 |
flashing | -0.025 |
Token | ro |
Token ID | 305 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
seek | +0.044 |
One | +0.040 |
One | +0.040 |
moral | +0.037 |
onna | +0.035 |
Neg logit contributions | |
hing | -0.056 |
ming | -0.051 |
aw | -0.051 |
flashing | -0.049 |
ding | -0.049 |
Token | pe |
Token ID | 431 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
One | +0.169 |
seek | +0.158 |
One | +0.157 |
moral | +0.138 |
Yesterday | +0.128 |
Neg logit contributions | |
hing | -0.407 |
ming | -0.385 |
aw | -0.380 |
eping | -0.367 |
ning | -0.358 |
Token | walk |
Token ID | 2513 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
seek | +0.151 |
One | +0.135 |
One | +0.131 |
onna | +0.122 |
moral | +0.122 |
Neg logit contributions | |
hing | -0.170 |
ming | -0.153 |
aw | -0.150 |
eping | -0.147 |
ong | -0.144 |
Token | er |
Token ID | 263 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
seek | +0.046 |
One | +0.040 |
One | +0.040 |
moral | +0.038 |
onna | +0.037 |
Neg logit contributions | |
hing | -0.062 |
aw | -0.057 |
ming | -0.057 |
ding | -0.054 |
flashing | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
seek | +0.073 |
One | +0.064 |
One | +0.063 |
moral | +0.059 |
onna | +0.057 |
Neg logit contributions | |
hing | -0.105 |
ming | -0.097 |
aw | -0.095 |
eping | -0.091 |
flashing | -0.090 |
Token | Do |
Token ID | 2141 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
hing | +0.013 |
aw | +0.012 |
ding | +0.012 |
ming | +0.012 |
flashing | +0.011 |
Neg logit contributions | |
seek | -0.012 |
moment | -0.010 |
moral | -0.010 |
One | -0.009 |
onna | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
seek | +0.012 |
onna | +0.010 |
ib | +0.010 |
ifi | +0.010 |
One | +0.010 |
Neg logit contributions | |
hing | -0.015 |
flashing | -0.013 |
ming | -0.013 |
aw | -0.013 |
eping | -0.012 |
Token | been |
Token ID | 587 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
seek | +0.079 |
One | +0.071 |
One | +0.069 |
moral | +0.060 |
onna | +0.059 |
Neg logit contributions | |
hing | -0.138 |
ming | -0.128 |
aw | -0.123 |
eping | -0.119 |
ding | -0.118 |
Token | made |
Token ID | 925 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
seek | +0.066 |
One | +0.059 |
One | +0.058 |
onna | +0.054 |
moral | +0.053 |
Neg logit contributions | |
hing | -0.084 |
ming | -0.077 |
aw | -0.075 |
eping | -0.074 |
flashing | -0.073 |
Token | many |
Token ID | 867 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
hing | +0.007 |
aw | +0.006 |
ming | +0.006 |
flashing | +0.006 |
ding | +0.006 |
Neg logit contributions | |
seek | -0.005 |
One | -0.005 |
One | -0.005 |
moment | -0.004 |
next | -0.004 |
Token | years |
Token ID | 812 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
hing | +0.022 |
ming | +0.020 |
aw | +0.020 |
ong | +0.020 |
ding | +0.020 |
Neg logit contributions | |
seek | -0.015 |
One | -0.013 |
One | -0.013 |
moral | -0.012 |
next | -0.011 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
seek | +0.115 |
One | +0.095 |
One | +0.093 |
moment | +0.086 |
Buzz | +0.085 |
Neg logit contributions | |
hing | -0.155 |
aw | -0.151 |
ong | -0.145 |
ming | -0.144 |
flashing | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
seek | +0.212 |
One | +0.191 |
One | +0.186 |
onna | +0.176 |
ifi | +0.175 |
Neg logit contributions | |
hing | -0.360 |
ming | -0.343 |
aw | -0.340 |
eping | -0.331 |
flashing | -0.329 |
Token | but |
Token ID | 475 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
seek | +0.042 |
One | +0.038 |
onna | +0.036 |
One | +0.036 |
moral | +0.035 |
Neg logit contributions | |
hing | -0.059 |
aw | -0.058 |
flashing | -0.058 |
ming | -0.057 |
eping | -0.056 |
Token | it |
Token ID | 340 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
hing | +0.042 |
flashing | +0.041 |
aw | +0.041 |
ding | +0.040 |
ming | +0.039 |
Neg logit contributions | |
seek | -0.034 |
onna | -0.032 |
One | -0.030 |
ib | -0.029 |
ro | -0.029 |
Token | still |
Token ID | 991 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
hing | +0.002 |
ming | +0.002 |
aw | +0.002 |
eping | +0.002 |
flashing | +0.002 |
Neg logit contributions | |
seek | -0.001 |
One | -0.001 |
One | -0.001 |
onna | -0.001 |
moral | -0.001 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
seek | +0.039 |
One | +0.033 |
One | +0.033 |
onna | +0.029 |
moral | +0.029 |
Neg logit contributions | |
hing | -0.070 |
ming | -0.065 |
aw | -0.064 |
eping | -0.062 |
flashing | -0.061 |
Token | brother |
Token ID | 3956 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
hing | +0.031 |
ming | +0.028 |
aw | +0.027 |
eping | +0.026 |
flashing | +0.026 |
Neg logit contributions | |
seek | -0.036 |
One | -0.032 |
One | -0.032 |
onna | -0.030 |
moment | -0.029 |
Token | would |
Token ID | 561 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
hing | +0.027 |
eping | +0.024 |
ming | +0.024 |
ding | +0.024 |
flashing | +0.024 |
Neg logit contributions | |
seek | -0.017 |
One | -0.017 |
One | -0.016 |
D | -0.015 |
Lily | -0.014 |
Token | wear |
Token ID | 5806 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
hing | +0.049 |
ming | +0.045 |
aw | +0.044 |
flashing | +0.042 |
eping | +0.042 |
Neg logit contributions | |
seek | -0.037 |
One | -0.032 |
One | -0.032 |
onna | -0.030 |
moment | -0.030 |
Token | their |
Token ID | 511 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
seek | +0.051 |
One | +0.046 |
One | +0.044 |
Lily | +0.042 |
D | +0.042 |
Neg logit contributions | |
hing | -0.075 |
aw | -0.067 |
ding | -0.065 |
ming | -0.065 |
ong | -0.065 |
Token | bath |
Token ID | 7837 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
hing | +0.014 |
ming | +0.013 |
aw | +0.013 |
flashing | +0.013 |
channels | +0.012 |
Neg logit contributions | |
seek | -0.012 |
One | -0.010 |
One | -0.010 |
onna | -0.010 |
ifi | -0.010 |
Token | ro |
Token ID | 305 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
seek | +0.036 |
One | +0.030 |
One | +0.029 |
moment | +0.028 |
ro | +0.027 |
Neg logit contributions | |
hing | -0.049 |
aw | -0.045 |
ming | -0.044 |
eping | -0.044 |
ding | -0.044 |
Token | bes |
Token ID | 12636 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
One | +0.203 |
seek | +0.188 |
One | +0.185 |
moral | +0.172 |
onna | +0.165 |
Neg logit contributions | |
hing | -0.367 |
ming | -0.362 |
eping | -0.332 |
aw | -0.330 |
ning | -0.316 |
Token | together |
Token ID | 1978 |
Feature activation | -3.60e-04 |
Pos logit contributions | |
seek | +0.107 |
One | +0.094 |
One | +0.092 |
moment | +0.082 |
moral | +0.081 |
Neg logit contributions | |
hing | -0.161 |
ming | -0.145 |
aw | -0.144 |
eping | -0.142 |
flashing | -0.141 |
Token | and |
Token ID | 290 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
hing | +0.000 |
aw | +0.000 |
ming | +0.000 |
eping | +0.000 |
ding | +0.000 |
Neg logit contributions | |
seek | -0.000 |
One | -0.000 |
One | -0.000 |
moment | -0.000 |
moral | -0.000 |
Token | play |
Token ID | 711 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
hing | +0.058 |
ming | +0.053 |
aw | +0.053 |
eping | +0.051 |
flashing | +0.050 |
Neg logit contributions | |
seek | -0.034 |
One | -0.029 |
One | -0.028 |
onna | -0.026 |
moral | -0.026 |
Token | games |
Token ID | 1830 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
seek | +0.036 |
One | +0.032 |
One | +0.032 |
moral | +0.029 |
moment | +0.029 |
Neg logit contributions | |
hing | -0.040 |
ming | -0.036 |
aw | -0.035 |
flashing | -0.034 |
eping | -0.034 |
Token | found |
Token ID | 1043 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
seek | +0.081 |
One | +0.069 |
One | +0.067 |
onna | +0.060 |
moral | +0.060 |
Neg logit contributions | |
hing | -0.140 |
ming | -0.126 |
aw | -0.123 |
ding | -0.120 |
eping | -0.119 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
seek | +0.000 |
One | +0.000 |
One | +0.000 |
Lily | +0.000 |
D | +0.000 |
Neg logit contributions | |
hing | -0.001 |
ming | -0.001 |
eping | -0.001 |
aw | -0.001 |
ding | -0.001 |
Token | truck |
Token ID | 7779 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
seek | +0.061 |
One | +0.054 |
One | +0.052 |
moral | +0.050 |
moment | +0.049 |
Neg logit contributions | |
hing | -0.081 |
ming | -0.074 |
aw | -0.072 |
eping | -0.069 |
flashing | -0.068 |
Token | many |
Token ID | 867 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
seek | +0.047 |
One | +0.040 |
One | +0.039 |
onna | +0.035 |
moral | +0.035 |
Neg logit contributions | |
hing | -0.085 |
ming | -0.078 |
aw | -0.077 |
eping | -0.075 |
flashing | -0.074 |
Token | years |
Token ID | 812 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
hing | +0.019 |
ming | +0.018 |
aw | +0.017 |
ding | +0.017 |
ong | +0.016 |
Neg logit contributions | |
seek | -0.015 |
One | -0.014 |
One | -0.013 |
moral | -0.012 |
moment | -0.012 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
seek | +0.099 |
One | +0.084 |
One | +0.081 |
ifi | +0.073 |
moral | +0.073 |
Neg logit contributions | |
aw | -0.133 |
hing | -0.133 |
ming | -0.126 |
ong | -0.124 |
flashing | -0.123 |
Token | and |
Token ID | 290 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
seek | +0.213 |
One | +0.196 |
One | +0.190 |
onna | +0.174 |
ifi | +0.173 |
Neg logit contributions | |
hing | -0.357 |
aw | -0.338 |
ming | -0.338 |
eping | -0.321 |
flashing | -0.321 |
Token | worked |
Token ID | 3111 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
hing | +0.030 |
ming | +0.028 |
aw | +0.027 |
flashing | +0.026 |
eping | +0.026 |
Neg logit contributions | |
seek | -0.015 |
One | -0.013 |
One | -0.013 |
onna | -0.012 |
moral | -0.011 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
seek | +0.029 |
One | +0.026 |
One | +0.026 |
onna | +0.024 |
moral | +0.024 |
Neg logit contributions | |
hing | -0.034 |
ming | -0.032 |
aw | -0.031 |
eping | -0.030 |
flashing | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
hing | +0.078 |
ming | +0.072 |
aw | +0.071 |
ding | +0.068 |
eping | +0.068 |
Neg logit contributions | |
seek | -0.049 |
One | -0.043 |
One | -0.042 |
onna | -0.038 |
moment | -0.038 |
Token | fix |
Token ID | 4259 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
seek | +0.008 |
One | +0.007 |
One | +0.007 |
onna | +0.006 |
moral | +0.006 |
Neg logit contributions | |
hing | -0.011 |
ming | -0.010 |
aw | -0.009 |
eping | -0.009 |
flashing | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
seek | +0.265 |
One | +0.241 |
One | +0.236 |
onna | +0.224 |
moral | +0.222 |
Neg logit contributions | |
hing | -0.163 |
aw | -0.149 |
ming | -0.147 |
eping | -0.133 |
ding | -0.133 |
Token | six |
Token ID | 19412 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
hing | +0.007 |
aw | +0.007 |
ming | +0.007 |
ding | +0.007 |
ong | +0.006 |
Neg logit contributions | |
seek | -0.006 |
One | -0.005 |
One | -0.005 |
moment | -0.005 |
moral | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
seek | +0.172 |
One | +0.151 |
One | +0.142 |
onna | +0.129 |
moral | +0.127 |
Neg logit contributions | |
hing | -0.373 |
ming | -0.338 |
eping | -0.329 |
aw | -0.325 |
flashing | -0.324 |
Token | forty |
Token ID | 16571 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
seek | +0.050 |
One | +0.042 |
One | +0.040 |
ifi | +0.040 |
onna | +0.040 |
Neg logit contributions | |
hing | -0.056 |
ming | -0.052 |
aw | -0.051 |
ding | -0.050 |
flashing | -0.049 |
Token | - |
Token ID | 12 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
seek | +0.257 |
One | +0.233 |
One | +0.229 |
onna | +0.217 |
moral | +0.215 |
Neg logit contributions | |
hing | -0.170 |
ming | -0.153 |
aw | -0.153 |
eping | -0.139 |
ding | -0.138 |
Token | seven |
Token ID | 26548 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
hing | +0.005 |
aw | +0.004 |
ming | +0.004 |
ding | +0.004 |
ong | +0.004 |
Neg logit contributions | |
seek | -0.004 |
One | -0.003 |
moral | -0.003 |
moment | -0.003 |
One | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
seek | +0.226 |
One | +0.184 |
One | +0.183 |
moment | +0.170 |
onna | +0.169 |
Neg logit contributions | |
hing | -0.352 |
aw | -0.339 |
ming | -0.332 |
ding | -0.311 |
eping | -0.310 |
Token | forty |
Token ID | 16571 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
seek | +0.088 |
ifi | +0.070 |
ro | +0.068 |
emo | +0.067 |
moment | +0.067 |
Neg logit contributions | |
hing | -0.079 |
ding | -0.075 |
ming | -0.075 |
aw | -0.075 |
flashing | -0.070 |
Token | - |
Token ID | 12 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
seek | +0.271 |
One | +0.246 |
One | +0.242 |
onna | +0.229 |
moment | +0.227 |
Neg logit contributions | |
hing | -0.172 |
aw | -0.157 |
ming | -0.155 |
eping | -0.141 |
ding | -0.140 |
Token | eight |
Token ID | 26022 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
hing | +0.020 |
aw | +0.020 |
ming | +0.019 |
ding | +0.018 |
ong | +0.017 |
Neg logit contributions | |
seek | -0.016 |
One | -0.013 |
moment | -0.012 |
D | -0.012 |
moral | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
seek | +0.208 |
One | +0.173 |
One | +0.171 |
moral | +0.163 |
ifi | +0.163 |
Neg logit contributions | |
hing | -0.259 |
ming | -0.258 |
aw | -0.255 |
ning | -0.239 |
flashing | -0.232 |
Token | - |
Token ID | 12 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
seek | +0.241 |
One | +0.218 |
One | +0.214 |
onna | +0.203 |
moral | +0.201 |
Neg logit contributions | |
hing | -0.168 |
ming | -0.151 |
aw | -0.151 |
eping | -0.139 |
ding | -0.138 |
Token | six |
Token ID | 19412 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
hing | +0.019 |
aw | +0.018 |
ming | +0.018 |
ding | +0.017 |
ong | +0.017 |
Neg logit contributions | |
seek | -0.014 |
One | -0.012 |
One | -0.011 |
moment | -0.010 |
moral | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
seek | +0.171 |
One | +0.150 |
One | +0.141 |
onna | +0.127 |
moral | +0.126 |
Neg logit contributions | |
hing | -0.372 |
ming | -0.337 |
eping | -0.327 |
aw | -0.324 |
flashing | -0.323 |
Token | thirty |
Token ID | 12277 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
seek | +0.043 |
One | +0.036 |
One | +0.035 |
onna | +0.034 |
ifi | +0.034 |
Neg logit contributions | |
hing | -0.055 |
ming | -0.051 |
ding | -0.050 |
aw | -0.050 |
flashing | -0.049 |
Token | - |
Token ID | 12 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
seek | +0.233 |
One | +0.210 |
One | +0.207 |
onna | +0.196 |
moral | +0.194 |
Neg logit contributions | |
hing | -0.168 |
ming | -0.151 |
aw | -0.149 |
eping | -0.139 |
flashing | -0.138 |
Token | seven |
Token ID | 26548 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
hing | +0.023 |
aw | +0.022 |
ming | +0.022 |
ding | +0.021 |
ong | +0.020 |
Neg logit contributions | |
seek | -0.016 |
One | -0.014 |
One | -0.012 |
moment | -0.012 |
moral | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
seek | +0.224 |
One | +0.181 |
One | +0.181 |
onna | +0.168 |
moment | +0.168 |
Neg logit contributions | |
hing | -0.355 |
aw | -0.340 |
ming | -0.334 |
eping | -0.314 |
ding | -0.313 |
Token | thirty |
Token ID | 12277 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
seek | +0.086 |
ifi | +0.068 |
emo | +0.067 |
One | +0.066 |
moment | +0.066 |
Neg logit contributions | |
hing | -0.084 |
ding | -0.081 |
aw | -0.080 |
ming | -0.079 |
flashing | -0.077 |
Token | - |
Token ID | 12 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
seek | +0.264 |
One | +0.239 |
One | +0.235 |
onna | +0.223 |
moral | +0.221 |
Neg logit contributions | |
hing | -0.172 |
aw | -0.156 |
ming | -0.154 |
eping | -0.142 |
ding | -0.140 |
Token | eight |
Token ID | 26022 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
hing | +0.025 |
aw | +0.024 |
ming | +0.023 |
ding | +0.022 |
eping | +0.021 |
Neg logit contributions | |
seek | -0.019 |
One | -0.015 |
moment | -0.014 |
D | -0.014 |
moral | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
seek | +0.209 |
One | +0.174 |
One | +0.171 |
moral | +0.163 |
onna | +0.161 |
Neg logit contributions | |
hing | -0.275 |
ming | -0.270 |
aw | -0.268 |
ning | -0.251 |
flashing | -0.247 |
Token | - |
Token ID | 12 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
seek | +0.271 |
One | +0.246 |
One | +0.242 |
onna | +0.229 |
moment | +0.227 |
Neg logit contributions | |
hing | -0.172 |
aw | -0.157 |
ming | -0.155 |
eping | -0.141 |
ding | -0.140 |
Token | eight |
Token ID | 26022 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
hing | +0.020 |
aw | +0.020 |
ming | +0.019 |
ding | +0.018 |
ong | +0.017 |
Neg logit contributions | |
seek | -0.016 |
One | -0.013 |
moment | -0.012 |
D | -0.012 |
moral | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
seek | +0.208 |
One | +0.173 |
One | +0.171 |
moral | +0.163 |
ifi | +0.163 |
Neg logit contributions | |
hing | -0.259 |
ming | -0.258 |
aw | -0.255 |
ning | -0.239 |
flashing | -0.232 |
Token | forty |
Token ID | 16571 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
seek | +0.066 |
ifi | +0.054 |
emo | +0.052 |
rog | +0.051 |
ro | +0.051 |
Neg logit contributions | |
hing | -0.059 |
ding | -0.059 |
ming | -0.058 |
aw | -0.057 |
flashing | -0.054 |
Token | - |
Token ID | 12 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
seek | +0.255 |
One | +0.231 |
One | +0.227 |
onna | +0.215 |
moral | +0.213 |
Neg logit contributions | |
hing | -0.164 |
aw | -0.150 |
ming | -0.148 |
eping | -0.135 |
ding | -0.134 |
Token | nine |
Token ID | 30888 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
hing | +0.020 |
aw | +0.020 |
ming | +0.019 |
ding | +0.018 |
ong | +0.018 |
Neg logit contributions | |
seek | -0.016 |
One | -0.013 |
moment | -0.012 |
D | -0.012 |
moral | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
seek | +0.219 |
One | +0.184 |
One | +0.183 |
moral | +0.167 |
onna | +0.163 |
Neg logit contributions | |
hing | -0.363 |
ming | -0.343 |
aw | -0.336 |
flashing | -0.318 |
eping | -0.317 |
Token | fifty |
Token ID | 15334 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
seek | +0.053 |
One | +0.042 |
ifi | +0.041 |
onna | +0.041 |
One | +0.041 |
Neg logit contributions | |
hing | -0.059 |
ming | -0.056 |
aw | -0.054 |
ding | -0.054 |
flashing | -0.052 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
seek | +0.231 |
One | +0.207 |
One | +0.203 |
onna | +0.192 |
moment | +0.191 |
Neg logit contributions | |
hing | -0.175 |
aw | -0.160 |
ming | -0.159 |
eping | -0.147 |
ding | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
seek | +0.012 |
One | +0.009 |
ib | +0.008 |
ifi | +0.008 |
moment | +0.008 |
Neg logit contributions | |
aw | -0.019 |
hing | -0.019 |
ding | -0.018 |
ming | -0.018 |
flashing | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e-03 |
Pos logit contributions | |
hing | +0.024 |
aw | +0.024 |
ming | +0.022 |
ding | +0.022 |
ay | +0.021 |
Neg logit contributions | |
seek | -0.013 |
moment | -0.010 |
ider | -0.010 |
allowance | -0.010 |
ib | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
seek | +0.264 |
One | +0.239 |
One | +0.235 |
onna | +0.223 |
moral | +0.221 |
Neg logit contributions | |
hing | -0.172 |
aw | -0.156 |
ming | -0.154 |
eping | -0.142 |
ding | -0.140 |
Token | eight |
Token ID | 26022 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
hing | +0.025 |
aw | +0.024 |
ming | +0.023 |
ding | +0.022 |
eping | +0.021 |
Neg logit contributions | |
seek | -0.019 |
One | -0.015 |
moment | -0.014 |
D | -0.014 |
moral | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
seek | +0.209 |
One | +0.174 |
One | +0.171 |
moral | +0.163 |
onna | +0.161 |
Neg logit contributions | |
hing | -0.275 |
ming | -0.270 |
aw | -0.268 |
ning | -0.251 |
flashing | -0.247 |
Token | thirty |
Token ID | 12277 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
seek | +0.066 |
ifi | +0.053 |
emo | +0.052 |
onna | +0.050 |
ro | +0.050 |
Neg logit contributions | |
hing | -0.065 |
ding | -0.064 |
aw | -0.063 |
ming | -0.062 |
flashing | -0.060 |
Token | - |
Token ID | 12 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
seek | +0.246 |
One | +0.222 |
One | +0.219 |
onna | +0.208 |
moral | +0.206 |
Neg logit contributions | |
hing | -0.165 |
aw | -0.149 |
ming | -0.149 |
eping | -0.137 |
ding | -0.135 |
Token | nine |
Token ID | 30888 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
hing | +0.028 |
aw | +0.027 |
ming | +0.026 |
ding | +0.025 |
ong | +0.024 |
Neg logit contributions | |
seek | -0.020 |
One | -0.016 |
moment | -0.015 |
D | -0.015 |
moral | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
seek | +0.209 |
One | +0.176 |
One | +0.174 |
moral | +0.157 |
onna | +0.156 |
Neg logit contributions | |
hing | -0.373 |
ming | -0.348 |
aw | -0.342 |
flashing | -0.328 |
eping | -0.327 |
Token | forty |
Token ID | 16571 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
seek | +0.044 |
One | +0.034 |
onna | +0.034 |
One | +0.034 |
ifi | +0.034 |
Neg logit contributions | |
hing | -0.054 |
ming | -0.050 |
aw | -0.050 |
ding | -0.049 |
flashing | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
seek | +0.246 |
One | +0.222 |
One | +0.219 |
onna | +0.207 |
moral | +0.206 |
Neg logit contributions | |
hing | -0.179 |
ming | -0.160 |
aw | -0.158 |
eping | -0.147 |
flashing | -0.146 |
Token | forty |
Token ID | 16571 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
seek | +0.073 |
One | +0.060 |
One | +0.058 |
ifi | +0.058 |
onna | +0.057 |
Neg logit contributions | |
hing | -0.084 |
ming | -0.079 |
aw | -0.078 |
ding | -0.077 |
flashing | -0.075 |
Token | - |
Token ID | 12 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
seek | +0.260 |
One | +0.236 |
One | +0.232 |
onna | +0.220 |
moral | +0.218 |
Neg logit contributions | |
hing | -0.185 |
ming | -0.166 |
aw | -0.164 |
eping | -0.152 |
ding | -0.151 |
Token | count |
Token ID | 954 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
seek | +0.032 |
One | +0.027 |
One | +0.027 |
onna | +0.025 |
moment | +0.025 |
Neg logit contributions | |
hing | -0.039 |
aw | -0.037 |
ming | -0.036 |
eping | -0.034 |
flashing | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
seek | +0.039 |
One | +0.033 |
One | +0.032 |
onna | +0.029 |
moral | +0.029 |
Neg logit contributions | |
hing | -0.067 |
ming | -0.062 |
aw | -0.061 |
flashing | -0.059 |
eping | -0.059 |
Token | " |
Token ID | 366 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
hing | +0.010 |
aw | +0.010 |
ding | +0.010 |
flashing | +0.010 |
ming | +0.010 |
Neg logit contributions | |
seek | -0.005 |
ifi | -0.004 |
rog | -0.003 |
moral | -0.003 |
moment | -0.003 |
Token | One |
Token ID | 3198 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
hing | +0.101 |
aw | +0.094 |
ming | +0.091 |
ding | +0.091 |
channels | +0.087 |
Neg logit contributions | |
seek | -0.063 |
onna | -0.053 |
One | -0.051 |
D | -0.049 |
ifi | -0.048 |
Token | ... |
Token ID | 986 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
seek | +0.090 |
One | +0.076 |
One | +0.075 |
onna | +0.069 |
moral | +0.067 |
Neg logit contributions | |
hing | -0.144 |
ming | -0.134 |
aw | -0.132 |
ding | -0.127 |
eping | -0.126 |
Token | two |
Token ID | 11545 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
hing | +0.042 |
aw | +0.040 |
ming | +0.038 |
ding | +0.038 |
ong | +0.036 |
Neg logit contributions | |
seek | -0.036 |
ifi | -0.030 |
D | -0.029 |
onna | -0.028 |
moment | -0.028 |
Token | ..." |
Token ID | 9313 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
seek | +0.229 |
One | +0.199 |
One | +0.197 |
onna | +0.177 |
moral | +0.176 |
Neg logit contributions | |
hing | -0.340 |
ming | -0.325 |
aw | -0.321 |
eping | -0.302 |
ong | -0.301 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
seek | +0.010 |
One | +0.007 |
ifi | +0.007 |
rog | +0.007 |
moral | +0.006 |
Neg logit contributions | |
hing | -0.022 |
ming | -0.021 |
aw | -0.021 |
flashing | -0.021 |
ding | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
hing | +0.014 |
aw | +0.014 |
ming | +0.013 |
ding | +0.013 |
flashing | +0.013 |
Neg logit contributions | |
seek | -0.007 |
gn | -0.004 |
rog | -0.004 |
moment | -0.004 |
ifi | -0.004 |
Token | Tom |
Token ID | 13787 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
seek | +0.002 |
onna | +0.002 |
One | +0.002 |
Buzz | +0.002 |
rog | +0.002 |
Neg logit contributions | |
hing | -0.004 |
aw | -0.004 |
ming | -0.004 |
ding | -0.004 |
eping | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
seek | +0.044 |
One | +0.039 |
One | +0.039 |
onna | +0.036 |
moment | +0.035 |
Neg logit contributions | |
hing | -0.049 |
ming | -0.044 |
aw | -0.044 |
flashing | -0.042 |
eping | -0.042 |
Token | was |
Token ID | 373 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
hing | +0.085 |
ming | +0.078 |
aw | +0.076 |
flashing | +0.074 |
eping | +0.074 |
Neg logit contributions | |
seek | -0.052 |
One | -0.045 |
One | -0.044 |
onna | -0.040 |
moral | -0.039 |
Token | back |
Token ID | 736 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
seek | +0.009 |
One | +0.008 |
One | +0.008 |
moral | +0.007 |
moment | +0.007 |
Neg logit contributions | |
hing | -0.014 |
ming | -0.013 |
aw | -0.013 |
flashing | -0.012 |
eping | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
seek | +0.031 |
One | +0.027 |
One | +0.026 |
onna | +0.024 |
moral | +0.024 |
Neg logit contributions | |
hing | -0.045 |
ming | -0.042 |
aw | -0.041 |
eping | -0.040 |
flashing | -0.039 |
Token | H |
Token ID | 367 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
aw | +0.066 |
hing | +0.063 |
ding | +0.061 |
ming | +0.059 |
channels | +0.058 |
Neg logit contributions | |
seek | -0.051 |
moral | -0.041 |
moment | -0.040 |
ifi | -0.038 |
allowance | -0.038 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
seek | +0.109 |
moment | +0.095 |
Buzz | +0.095 |
One | +0.093 |
One | +0.091 |
Neg logit contributions | |
hing | -0.069 |
aw | -0.062 |
ming | -0.061 |
ong | -0.059 |
rol | -0.053 |
Token | ay |
Token ID | 323 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
hing | +0.113 |
ming | +0.099 |
aw | +0.095 |
eping | +0.093 |
flashing | +0.092 |
Neg logit contributions | |
seek | -0.166 |
One | -0.155 |
One | -0.152 |
onna | -0.142 |
moral | -0.142 |
Token | ! |
Token ID | 0 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
hing | +0.385 |
ming | +0.356 |
aw | +0.349 |
ong | +0.326 |
flashing | +0.324 |
Neg logit contributions | |
seek | -0.391 |
One | -0.348 |
One | -0.345 |
onna | -0.320 |
moment | -0.319 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
hing | +0.172 |
ay | +0.169 |
aw | +0.165 |
ming | +0.158 |
ding | +0.149 |
Neg logit contributions | |
seek | -0.140 |
onna | -0.116 |
ifi | -0.111 |
moment | -0.110 |
rog | -0.107 |
Token | Once |
Token ID | 7454 |
Feature activation | -6.95e-02 |
Pos logit contributions | |
hing | +0.174 |
aw | +0.164 |
ay | +0.153 |
ming | +0.152 |
hed | +0.147 |
Neg logit contributions | |
seek | -0.134 |
ifi | -0.119 |
onna | -0.109 |
ider | -0.109 |
moral | -0.108 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
hing | +0.004 |
ong | +0.004 |
aw | +0.004 |
ay | +0.004 |
ding | +0.004 |
Neg logit contributions | |
seek | -0.003 |
gn | -0.002 |
ro | -0.002 |
ider | -0.002 |
One | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
hing | +0.063 |
aw | +0.063 |
eping | +0.058 |
flashing | +0.057 |
ong | +0.055 |
Neg logit contributions | |
seek | -0.064 |
onna | -0.062 |
ifi | -0.059 |
rog | -0.059 |
allowance | -0.055 |
Token | head |
Token ID | 1182 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
hing | +0.038 |
ming | +0.035 |
aw | +0.034 |
eping | +0.033 |
flashing | +0.033 |
Neg logit contributions | |
seek | -0.030 |
One | -0.027 |
One | -0.026 |
moral | -0.024 |
onna | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
hing | +0.060 |
aw | +0.056 |
ming | +0.054 |
eping | +0.054 |
channels | +0.053 |
Neg logit contributions | |
seek | -0.024 |
One | -0.021 |
One | -0.019 |
moment | -0.018 |
next | -0.017 |
Token | say |
Token ID | 910 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
hing | +0.066 |
aw | +0.064 |
eping | +0.060 |
ming | +0.059 |
rol | +0.059 |
Neg logit contributions | |
seek | -0.038 |
One | -0.029 |
moment | -0.028 |
have | -0.026 |
moral | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
hing | +0.075 |
aw | +0.068 |
eping | +0.067 |
ming | +0.067 |
channels | +0.066 |
Neg logit contributions | |
seek | -0.031 |
One | -0.028 |
One | -0.026 |
moral | -0.025 |
moment | -0.024 |
Token | ok |
Token ID | 482 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
hing | +0.070 |
ming | +0.065 |
aw | +0.063 |
eping | +0.061 |
ding | +0.060 |
Neg logit contributions | |
seek | -0.049 |
One | -0.043 |
One | -0.041 |
onna | -0.039 |
moral | -0.038 |
Token | ay |
Token ID | 323 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
hing | +0.035 |
aw | +0.030 |
flashing | +0.030 |
eping | +0.029 |
ming | +0.028 |
Neg logit contributions | |
seek | -0.126 |
One | -0.120 |
One | -0.118 |
moment | -0.115 |
" | -0.113 |
Token | " |
Token ID | 1 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
hing | +0.461 |
aw | +0.439 |
flashing | +0.429 |
eping | +0.425 |
channels | +0.425 |
Neg logit contributions | |
seek | -0.245 |
One | -0.209 |
One | -0.199 |
" | -0.194 |
moral | -0.192 |
Token | when |
Token ID | 618 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
seek | +0.024 |
One | +0.021 |
One | +0.021 |
onna | +0.019 |
ifi | +0.019 |
Neg logit contributions | |
hing | -0.037 |
ming | -0.035 |
aw | -0.034 |
ding | -0.032 |
eping | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
hing | +0.098 |
flashing | +0.095 |
ming | +0.095 |
ding | +0.094 |
ning | +0.086 |
Neg logit contributions | |
seek | -0.069 |
rog | -0.063 |
onna | -0.062 |
ifi | -0.062 |
One | -0.061 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
hing | +0.141 |
aw | +0.132 |
eping | +0.126 |
ming | +0.126 |
rol | +0.120 |
Neg logit contributions | |
seek | -0.031 |
One | -0.022 |
moral | -0.021 |
next | -0.020 |
Lily | -0.018 |
Token | my |
Token ID | 1820 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
hing | +0.064 |
aw | +0.058 |
channels | +0.056 |
inking | +0.055 |
ong | +0.055 |
Neg logit contributions | |
seek | -0.025 |
One | -0.024 |
One | -0.023 |
first | -0.022 |
next | -0.022 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
seek | +0.104 |
One | +0.087 |
moral | +0.080 |
One | +0.079 |
Yesterday | +0.077 |
Neg logit contributions | |
ming | -0.134 |
hing | -0.134 |
aw | -0.129 |
ning | -0.127 |
flashing | -0.122 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
seek | +0.041 |
One | +0.034 |
One | +0.033 |
onna | +0.030 |
moral | +0.029 |
Neg logit contributions | |
hing | -0.084 |
ming | -0.079 |
aw | -0.077 |
eping | -0.075 |
flashing | -0.075 |
Token | said |
Token ID | 531 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hing | +0.013 |
ming | +0.011 |
aw | +0.011 |
eping | +0.011 |
channels | +0.011 |
Neg logit contributions | |
seek | -0.007 |
One | -0.006 |
One | -0.006 |
D | -0.006 |
Lily | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
hing | +0.073 |
ming | +0.068 |
aw | +0.067 |
ding | +0.066 |
flashing | +0.065 |
Neg logit contributions | |
seek | -0.040 |
One | -0.033 |
One | -0.032 |
moral | -0.029 |
onna | -0.028 |
Token | ok |
Token ID | 482 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
hing | +0.045 |
ming | +0.041 |
aw | +0.040 |
ning | +0.038 |
ding | +0.037 |
Neg logit contributions | |
seek | -0.035 |
One | -0.033 |
moral | -0.031 |
onna | -0.030 |
allowance | -0.030 |
Token | ay |
Token ID | 323 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
hing | +0.060 |
ming | +0.052 |
aw | +0.049 |
ong | +0.047 |
ning | +0.047 |
Neg logit contributions | |
seek | -0.082 |
One | -0.074 |
One | -0.073 |
onna | -0.070 |
moral | -0.069 |
Token | ." |
Token ID | 526 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
hing | +0.420 |
ming | +0.381 |
aw | +0.364 |
ong | +0.360 |
ning | +0.351 |
Neg logit contributions | |
seek | -0.330 |
One | -0.297 |
One | -0.277 |
onna | -0.260 |
Yesterday | -0.258 |
Token | |
Token ID | 220 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
seek | +0.059 |
One | +0.047 |
moral | +0.046 |
onna | +0.044 |
emo | +0.044 |
Neg logit contributions | |
hing | -0.087 |
aw | -0.084 |
ming | -0.083 |
flashing | -0.081 |
ding | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
hing | +0.005 |
ming | +0.004 |
aw | +0.004 |
ong | +0.004 |
ning | +0.004 |
Neg logit contributions | |
seek | -0.002 |
One | -0.001 |
moral | -0.001 |
moment | -0.001 |
ifi | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
hing | +0.015 |
aw | +0.014 |
ming | +0.014 |
flashing | +0.013 |
channels | +0.013 |
Neg logit contributions | |
seek | -0.009 |
gn | -0.007 |
ider | -0.006 |
allowance | -0.006 |
ib | -0.006 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
seek | +0.001 |
onna | +0.001 |
ib | +0.001 |
gn | +0.001 |
emo | +0.001 |
Neg logit contributions | |
hing | -0.002 |
aw | -0.002 |
ming | -0.002 |
ding | -0.002 |
eping | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
hing | +0.101 |
ming | +0.093 |
aw | +0.092 |
flashing | +0.090 |
ding | +0.090 |
Neg logit contributions | |
seek | -0.061 |
One | -0.053 |
One | -0.052 |
onna | -0.050 |
ifi | -0.047 |
Token | shouted |
Token ID | 17293 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
hing | +0.023 |
ming | +0.021 |
aw | +0.020 |
eping | +0.020 |
flashing | +0.020 |
Neg logit contributions | |
seek | -0.014 |
One | -0.012 |
One | -0.012 |
onna | -0.011 |
moral | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
hing | +0.088 |
ming | +0.081 |
aw | +0.080 |
eping | +0.079 |
flashing | +0.078 |
Neg logit contributions | |
seek | -0.039 |
One | -0.034 |
One | -0.030 |
D | -0.028 |
Lily | -0.028 |
Token | " |
Token ID | 366 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
seek | +0.009 |
ifi | +0.007 |
One | +0.007 |
onna | +0.007 |
One | +0.007 |
Neg logit contributions | |
hing | -0.012 |
ding | -0.012 |
ming | -0.012 |
flashing | -0.011 |
ning | -0.011 |
Token | Spr |
Token ID | 38454 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
hing | +0.087 |
ming | +0.079 |
aw | +0.079 |
ding | +0.074 |
eping | +0.074 |
Neg logit contributions | |
seek | -0.063 |
One | -0.056 |
onna | -0.053 |
One | -0.052 |
moral | -0.051 |
Token | ay |
Token ID | 323 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
seek | +0.099 |
One | +0.096 |
One | +0.095 |
onna | +0.090 |
moral | +0.090 |
Neg logit contributions | |
hing | -0.024 |
ming | -0.019 |
flashing | -0.017 |
aw | -0.017 |
eping | -0.016 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
hing | +0.471 |
channels | +0.459 |
flashing | +0.443 |
aw | +0.437 |
ming | +0.436 |
Neg logit contributions | |
seek | -0.226 |
One | -0.180 |
One | -0.171 |
" | -0.167 |
Lily | -0.156 |
Token | as |
Token ID | 355 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
seek | +0.014 |
One | +0.011 |
onna | +0.010 |
moral | +0.010 |
moment | +0.010 |
Neg logit contributions | |
hing | -0.022 |
aw | -0.022 |
ming | -0.021 |
ding | -0.020 |
ong | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
hing | +0.070 |
flashing | +0.068 |
ding | +0.064 |
aw | +0.063 |
ong | +0.060 |
Neg logit contributions | |
ider | -0.073 |
One | -0.072 |
seek | -0.071 |
ro | -0.067 |
onna | -0.067 |
Token | pretended |
Token ID | 36766 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
hing | +0.104 |
ming | +0.096 |
aw | +0.094 |
ding | +0.091 |
flashing | +0.091 |
Neg logit contributions | |
seek | -0.085 |
One | -0.075 |
One | -0.074 |
moral | -0.066 |
onna | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
seek | +0.010 |
One | +0.009 |
One | +0.008 |
moment | +0.007 |
Lily | +0.007 |
Neg logit contributions | |
hing | -0.025 |
ming | -0.023 |
aw | -0.022 |
eping | -0.022 |
channels | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
hing | +0.072 |
ming | +0.067 |
aw | +0.066 |
eping | +0.063 |
flashing | +0.063 |
Neg logit contributions | |
seek | -0.038 |
One | -0.033 |
One | -0.032 |
onna | -0.028 |
moral | -0.028 |
Token | dad |
Token ID | 9955 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
hing | +0.063 |
ming | +0.057 |
aw | +0.055 |
eping | +0.054 |
flashing | +0.054 |
Neg logit contributions | |
seek | -0.046 |
One | -0.041 |
One | -0.039 |
moral | -0.037 |
onna | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
hing | +0.222 |
ming | +0.207 |
aw | +0.203 |
eping | +0.198 |
flashing | +0.198 |
Neg logit contributions | |
seek | -0.124 |
One | -0.107 |
One | -0.104 |
moment | -0.095 |
moral | -0.094 |
Token | h |
Token ID | 289 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
hing | +0.060 |
ming | +0.055 |
aw | +0.054 |
eping | +0.052 |
flashing | +0.052 |
Neg logit contributions | |
seek | -0.036 |
One | -0.031 |
One | -0.030 |
moral | -0.028 |
moment | -0.028 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
hing | +0.158 |
ming | +0.142 |
aw | +0.137 |
flashing | +0.134 |
eping | +0.133 |
Neg logit contributions | |
seek | -0.145 |
One | -0.129 |
One | -0.128 |
onna | -0.123 |
moral | -0.118 |
Token | ay |
Token ID | 323 |
Feature activation | -6.92e+00 |
Pos logit contributions | |
hing | +0.084 |
ming | +0.071 |
flashing | +0.066 |
eping | +0.065 |
aw | +0.061 |
Neg logit contributions | |
One | -0.179 |
One | -0.176 |
seek | -0.175 |
moral | -0.163 |
moment | -0.162 |
Token | ! |
Token ID | 0 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
hing | +0.409 |
ming | +0.363 |
flashing | +0.353 |
eping | +0.352 |
aw | +0.350 |
Neg logit contributions | |
seek | -0.293 |
One | -0.255 |
One | -0.250 |
moral | -0.234 |
onna | -0.232 |
Token |
|
Token ID | 198 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
hing | +0.180 |
aw | +0.176 |
flashing | +0.168 |
ding | +0.167 |
channels | +0.167 |
Neg logit contributions | |
seek | -0.094 |
One | -0.066 |
rog | -0.062 |
moment | -0.061 |
One | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
hing | +0.026 |
aw | +0.024 |
ming | +0.024 |
flashing | +0.023 |
ding | +0.023 |
Neg logit contributions | |
seek | -0.013 |
One | -0.010 |
ro | -0.010 |
onna | -0.009 |
ifi | -0.009 |
Token | They |
Token ID | 2990 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
hing | +0.002 |
aw | +0.002 |
ming | +0.002 |
ding | +0.002 |
eping | +0.002 |
Neg logit contributions | |
seek | -0.002 |
One | -0.001 |
onna | -0.001 |
D | -0.001 |
ro | -0.001 |
Token | pulled |
Token ID | 5954 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
hing | +0.014 |
ming | +0.013 |
aw | +0.013 |
eping | +0.012 |
ning | +0.012 |
Neg logit contributions | |
seek | -0.013 |
One | -0.011 |
One | -0.011 |
moral | -0.010 |
onna | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
hing | +0.110 |
aw | +0.104 |
ming | +0.095 |
hed | +0.094 |
ay | +0.092 |
Neg logit contributions | |
seek | -0.122 |
ifi | -0.109 |
onna | -0.103 |
moral | -0.099 |
allowance | -0.098 |
Token | shouted |
Token ID | 17293 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
hing | +0.032 |
ming | +0.029 |
aw | +0.029 |
eping | +0.028 |
ding | +0.028 |
Neg logit contributions | |
seek | -0.021 |
One | -0.018 |
One | -0.018 |
onna | -0.016 |
moral | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
hing | +0.057 |
ming | +0.052 |
aw | +0.052 |
eping | +0.050 |
flashing | +0.050 |
Neg logit contributions | |
seek | -0.036 |
One | -0.031 |
One | -0.030 |
onna | -0.027 |
moral | -0.027 |
Token | h |
Token ID | 71 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
hing | +0.099 |
ming | +0.089 |
aw | +0.087 |
ding | +0.084 |
eping | +0.082 |
Neg logit contributions | |
seek | -0.079 |
One | -0.072 |
onna | -0.068 |
One | -0.067 |
ifi | -0.064 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
seek | +0.070 |
One | +0.061 |
One | +0.060 |
moral | +0.056 |
moment | +0.054 |
Neg logit contributions | |
hing | -0.080 |
aw | -0.073 |
ming | -0.072 |
ong | -0.070 |
ding | -0.068 |
Token | ay |
Token ID | 323 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
hing | +0.042 |
ming | +0.031 |
aw | +0.028 |
flashing | +0.027 |
eping | +0.027 |
Neg logit contributions | |
seek | -0.182 |
One | -0.175 |
One | -0.172 |
onna | -0.164 |
moral | -0.163 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
hing | +0.416 |
ming | +0.380 |
aw | +0.374 |
eping | +0.366 |
flashing | +0.364 |
Neg logit contributions | |
seek | -0.284 |
One | -0.249 |
One | -0.240 |
onna | -0.222 |
moral | -0.220 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
hing | +0.039 |
aw | +0.038 |
ming | +0.037 |
ding | +0.036 |
ong | +0.036 |
Neg logit contributions | |
seek | -0.020 |
One | -0.016 |
moral | -0.015 |
One | -0.014 |
onna | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
aw | +0.091 |
hing | +0.090 |
ming | +0.083 |
eping | +0.082 |
ong | +0.080 |
Neg logit contributions | |
seek | -0.056 |
ider | -0.044 |
allowance | -0.043 |
moment | -0.043 |
ifi | -0.041 |
Token | The |
Token ID | 464 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
hing | +0.062 |
aw | +0.059 |
ming | +0.056 |
eping | +0.054 |
ding | +0.053 |
Neg logit contributions | |
seek | -0.040 |
One | -0.039 |
onna | -0.038 |
moment | -0.037 |
allowance | -0.037 |
Token | jet |
Token ID | 12644 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
seek | +0.027 |
One | +0.025 |
One | +0.024 |
onna | +0.023 |
ifi | +0.022 |
Neg logit contributions | |
hing | -0.033 |
ming | -0.030 |
aw | -0.030 |
ding | -0.029 |
flashing | -0.028 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
seek | +0.062 |
One | +0.054 |
One | +0.054 |
onna | +0.049 |
moment | +0.048 |
Neg logit contributions | |
hing | -0.092 |
ming | -0.086 |
aw | -0.085 |
eping | -0.080 |
ding | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
seek | +0.035 |
One | +0.030 |
One | +0.028 |
moral | +0.025 |
onna | +0.025 |
Neg logit contributions | |
hing | -0.077 |
ming | -0.071 |
aw | -0.070 |
eping | -0.068 |
flashing | -0.068 |
Token | " |
Token ID | 366 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
hing | +0.025 |
aw | +0.024 |
ming | +0.024 |
ding | +0.023 |
channels | +0.022 |
Neg logit contributions | |
seek | -0.025 |
ifi | -0.019 |
One | -0.019 |
rog | -0.018 |
moment | -0.018 |
Token | H |
Token ID | 39 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
hing | +0.112 |
aw | +0.100 |
ming | +0.092 |
ding | +0.092 |
eping | +0.078 |
Neg logit contributions | |
seek | -0.109 |
onna | -0.109 |
allowance | -0.105 |
One | -0.095 |
rog | -0.093 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
hing | +0.027 |
aw | +0.025 |
ong | +0.025 |
inking | +0.024 |
ee | +0.024 |
Neg logit contributions | |
seek | -0.026 |
moral | -0.023 |
One | -0.023 |
One | -0.023 |
Lily | -0.022 |
Token | ay |
Token ID | 323 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
hing | +0.040 |
ming | +0.028 |
aw | +0.025 |
flashing | +0.023 |
eping | +0.023 |
Neg logit contributions | |
seek | -0.195 |
One | -0.186 |
One | -0.184 |
onna | -0.175 |
moral | -0.175 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
hing | +0.455 |
ming | +0.418 |
aw | +0.412 |
eping | +0.405 |
flashing | +0.403 |
Neg logit contributions | |
seek | -0.242 |
One | -0.207 |
One | -0.197 |
moral | -0.180 |
onna | -0.179 |
Token | we |
Token ID | 356 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
hing | +0.090 |
ming | +0.084 |
aw | +0.082 |
ding | +0.080 |
flashing | +0.079 |
Neg logit contributions | |
seek | -0.051 |
One | -0.044 |
One | -0.044 |
onna | -0.040 |
moral | -0.038 |
Token | took |
Token ID | 1718 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
hing | +0.031 |
ming | +0.029 |
aw | +0.028 |
flashing | +0.027 |
ning | +0.027 |
Neg logit contributions | |
seek | -0.031 |
One | -0.028 |
One | -0.027 |
moral | -0.025 |
moment | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
hing | +0.008 |
ming | +0.008 |
eping | +0.007 |
ning | +0.007 |
flashing | +0.007 |
Neg logit contributions | |
seek | -0.004 |
One | -0.004 |
Lily | -0.004 |
One | -0.004 |
D | -0.004 |
Token | taxi |
Token ID | 17536 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
hing | +0.059 |
aw | +0.054 |
ming | +0.054 |
eping | +0.051 |
ning | +0.051 |
Neg logit contributions | |
seek | -0.040 |
One | -0.035 |
One | -0.034 |
moment | -0.033 |
onna | -0.032 |
Token | but |
Token ID | 475 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
seek | +0.048 |
One | +0.039 |
ifi | +0.037 |
moment | +0.037 |
One | +0.037 |
Neg logit contributions | |
aw | -0.070 |
ming | -0.068 |
hing | -0.067 |
ding | -0.067 |
flashing | -0.067 |
Token | she |
Token ID | 673 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
hing | +0.092 |
ming | +0.087 |
aw | +0.086 |
flashing | +0.083 |
ding | +0.083 |
Neg logit contributions | |
seek | -0.038 |
One | -0.032 |
One | -0.032 |
onna | -0.028 |
moral | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
hing | +0.030 |
aw | +0.029 |
ming | +0.029 |
eping | +0.027 |
ding | +0.027 |
Neg logit contributions | |
seek | -0.022 |
One | -0.020 |
One | -0.020 |
moment | -0.018 |
onna | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
hing | +0.025 |
aw | +0.025 |
ming | +0.024 |
ding | +0.024 |
ong | +0.023 |
Neg logit contributions | |
seek | -0.020 |
One | -0.018 |
One | -0.016 |
moral | -0.016 |
ifi | -0.016 |
Token | ok |
Token ID | 482 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
hing | +0.041 |
aw | +0.038 |
ming | +0.037 |
ding | +0.034 |
ning | +0.034 |
Neg logit contributions | |
seek | -0.031 |
One | -0.027 |
onna | -0.026 |
gn | -0.024 |
moral | -0.024 |
Token | ay |
Token ID | 323 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
hing | +0.030 |
ming | +0.025 |
aw | +0.024 |
eping | +0.021 |
flashing | +0.021 |
Neg logit contributions | |
seek | -0.086 |
One | -0.080 |
One | -0.079 |
onna | -0.076 |
moral | -0.076 |
Token | " |
Token ID | 1 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
hing | +0.408 |
ming | +0.372 |
aw | +0.363 |
ding | +0.346 |
ong | +0.346 |
Neg logit contributions | |
seek | -0.302 |
One | -0.266 |
One | -0.261 |
onna | -0.241 |
moment | -0.237 |
Token | and |
Token ID | 290 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
seek | +0.029 |
One | +0.024 |
One | +0.024 |
onna | +0.021 |
moral | +0.021 |
Neg logit contributions | |
hing | -0.057 |
ming | -0.053 |
aw | -0.053 |
ding | -0.050 |
eping | -0.050 |
Token | bought |
Token ID | 5839 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
hing | +0.049 |
aw | +0.047 |
ming | +0.046 |
ding | +0.046 |
flashing | +0.043 |
Neg logit contributions | |
seek | -0.036 |
One | -0.032 |
One | -0.030 |
moment | -0.029 |
ifi | -0.028 |
Token | him |
Token ID | 683 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
seek | +0.052 |
One | +0.042 |
onna | +0.041 |
One | +0.040 |
moment | +0.040 |
Neg logit contributions | |
hing | -0.060 |
aw | -0.059 |
ming | -0.057 |
ding | -0.053 |
ong | -0.053 |
Token | one |
Token ID | 530 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
aw | +0.072 |
ming | +0.069 |
hing | +0.069 |
ning | +0.063 |
ong | +0.062 |
Neg logit contributions | |
seek | -0.062 |
onna | -0.053 |
moment | -0.051 |
One | -0.051 |
ider | -0.050 |
Token | cheered |
Token ID | 34767 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
hing | +0.013 |
ming | +0.012 |
aw | +0.012 |
eping | +0.012 |
channels | +0.012 |
Neg logit contributions | |
seek | -0.010 |
One | -0.008 |
One | -0.007 |
moment | -0.007 |
D | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
hing | +0.132 |
ming | +0.120 |
aw | +0.120 |
eping | +0.117 |
flashing | +0.116 |
Neg logit contributions | |
seek | -0.079 |
One | -0.069 |
One | -0.066 |
moment | -0.061 |
moral | -0.060 |
Token | " |
Token ID | 366 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
hing | +0.025 |
ming | +0.024 |
aw | +0.023 |
flashing | +0.023 |
ding | +0.023 |
Neg logit contributions | |
seek | -0.018 |
One | -0.015 |
One | -0.015 |
ifi | -0.014 |
onna | -0.014 |
Token | H |
Token ID | 39 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
hing | +0.109 |
ming | +0.099 |
aw | +0.099 |
ding | +0.091 |
ning | +0.091 |
Neg logit contributions | |
seek | -0.082 |
One | -0.073 |
onna | -0.072 |
One | -0.066 |
moral | -0.065 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
hing | +0.027 |
aw | +0.024 |
ong | +0.024 |
inking | +0.024 |
ee | +0.022 |
Neg logit contributions | |
seek | -0.030 |
One | -0.028 |
One | -0.027 |
moral | -0.027 |
Lily | -0.026 |
Token | ay |
Token ID | 323 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
hing | +0.038 |
ming | +0.027 |
aw | +0.024 |
eping | +0.021 |
flashing | +0.021 |
Neg logit contributions | |
seek | -0.194 |
One | -0.184 |
One | -0.181 |
onna | -0.174 |
moral | -0.173 |
Token | ! |
Token ID | 0 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
hing | +0.402 |
ming | +0.367 |
channels | +0.367 |
aw | +0.364 |
eping | +0.360 |
Neg logit contributions | |
seek | -0.285 |
One | -0.235 |
One | -0.227 |
moral | -0.214 |
" | -0.214 |
Token | The |
Token ID | 383 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
hing | +0.139 |
ming | +0.123 |
aw | +0.122 |
ding | +0.119 |
ay | +0.117 |
Neg logit contributions | |
seek | -0.127 |
One | -0.108 |
moment | -0.101 |
moral | -0.101 |
onna | -0.101 |
Token | fairy |
Token ID | 25607 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
seek | +0.043 |
onna | +0.041 |
One | +0.041 |
One | +0.040 |
ifi | +0.040 |
Neg logit contributions | |
hing | -0.041 |
ding | -0.035 |
ming | -0.035 |
flashing | -0.034 |
aw | -0.034 |
Token | has |
Token ID | 468 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
seek | +0.006 |
One | +0.005 |
moment | +0.005 |
One | +0.004 |
moral | +0.004 |
Neg logit contributions | |
hing | -0.007 |
ming | -0.007 |
flashing | -0.007 |
eping | -0.007 |
aw | -0.007 |
Token | saved |
Token ID | 7448 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
seek | +0.033 |
One | +0.028 |
One | +0.027 |
onna | +0.025 |
moment | +0.025 |
Neg logit contributions | |
hing | -0.047 |
ming | -0.043 |
aw | -0.042 |
ding | -0.040 |
eping | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
seek | +0.053 |
One | +0.047 |
One | +0.046 |
onna | +0.042 |
moral | +0.042 |
Neg logit contributions | |
hing | -0.072 |
ming | -0.066 |
aw | -0.065 |
eping | -0.062 |
flashing | -0.062 |
Token | said |
Token ID | 531 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
seek | +0.016 |
One | +0.014 |
One | +0.014 |
onna | +0.012 |
moral | +0.012 |
Neg logit contributions | |
hing | -0.024 |
ming | -0.022 |
aw | -0.022 |
eping | -0.021 |
flashing | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
hing | +0.055 |
ming | +0.051 |
aw | +0.050 |
ding | +0.049 |
flashing | +0.048 |
Neg logit contributions | |
seek | -0.035 |
One | -0.030 |
One | -0.030 |
moral | -0.027 |
onna | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
seek | +0.017 |
ifi | +0.015 |
One | +0.014 |
rog | +0.013 |
onna | +0.013 |
Neg logit contributions | |
ding | -0.016 |
hing | -0.016 |
ming | -0.015 |
flashing | -0.015 |
ning | -0.015 |
Token | Spr |
Token ID | 38454 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
hing | +0.088 |
aw | +0.080 |
ming | +0.079 |
ding | +0.075 |
eping | +0.074 |
Neg logit contributions | |
seek | -0.058 |
onna | -0.052 |
One | -0.051 |
moral | -0.045 |
allowance | -0.045 |
Token | ay |
Token ID | 323 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
seek | +0.101 |
One | +0.095 |
One | +0.094 |
onna | +0.090 |
moral | +0.090 |
Neg logit contributions | |
hing | -0.027 |
ming | -0.021 |
aw | -0.019 |
flashing | -0.017 |
eping | -0.017 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
hing | +0.412 |
ming | +0.379 |
aw | +0.372 |
eping | +0.359 |
flashing | +0.358 |
Neg logit contributions | |
seek | -0.282 |
One | -0.246 |
One | -0.241 |
onna | -0.221 |
moral | -0.219 |
Token | To |
Token ID | 1675 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
seek | +0.009 |
One | +0.008 |
One | +0.007 |
moral | +0.007 |
onna | +0.006 |
Neg logit contributions | |
hing | -0.020 |
aw | -0.019 |
ming | -0.019 |
ding | -0.018 |
flashing | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
hing | +0.025 |
ming | +0.023 |
aw | +0.023 |
eping | +0.022 |
flashing | +0.022 |
Neg logit contributions | |
seek | -0.012 |
One | -0.010 |
One | -0.010 |
onna | -0.009 |
moral | -0.009 |
Token | surprise |
Token ID | 5975 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
hing | +0.093 |
ming | +0.081 |
aw | +0.079 |
eping | +0.078 |
flashing | +0.076 |
Neg logit contributions | |
seek | -0.087 |
One | -0.080 |
One | -0.078 |
moral | -0.078 |
next | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
hing | +0.132 |
ming | +0.122 |
aw | +0.120 |
eping | +0.117 |
flashing | +0.116 |
Neg logit contributions | |
seek | -0.064 |
One | -0.054 |
One | -0.052 |
onna | -0.047 |
moment | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
seek | +0.036 |
One | +0.034 |
One | +0.033 |
moral | +0.031 |
onna | +0.030 |
Neg logit contributions | |
aw | -0.043 |
hing | -0.043 |
ming | -0.042 |
ong | -0.039 |
flashing | -0.038 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
hing | +0.032 |
ming | +0.031 |
aw | +0.030 |
flashing | +0.030 |
ding | +0.029 |
Neg logit contributions | |
seek | -0.020 |
One | -0.017 |
One | -0.017 |
onna | -0.015 |
ifi | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
hing | +0.001 |
ming | +0.001 |
aw | +0.001 |
ding | +0.001 |
flashing | +0.001 |
Neg logit contributions | |
seek | -0.001 |
One | -0.001 |
One | -0.001 |
moral | -0.000 |
onna | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
hing | +0.044 |
aw | +0.044 |
ming | +0.043 |
ding | +0.041 |
flashing | +0.041 |
Neg logit contributions | |
seek | -0.032 |
One | -0.027 |
One | -0.025 |
ifi | -0.024 |
ib | -0.023 |
Token | ok |
Token ID | 482 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
hing | +0.035 |
ming | +0.032 |
aw | +0.032 |
ning | +0.030 |
eping | +0.030 |
Neg logit contributions | |
seek | -0.028 |
One | -0.027 |
onna | -0.025 |
moral | -0.024 |
One | -0.023 |
Token | ay |
Token ID | 323 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
hing | +0.034 |
ming | +0.028 |
aw | +0.027 |
eping | +0.025 |
flashing | +0.025 |
Neg logit contributions | |
seek | -0.087 |
One | -0.081 |
One | -0.080 |
moment | -0.076 |
onna | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
hing | +0.419 |
ming | +0.385 |
aw | +0.377 |
ding | +0.361 |
eping | +0.359 |
Neg logit contributions | |
seek | -0.278 |
One | -0.242 |
One | -0.241 |
onna | -0.219 |
moral | -0.213 |
Token | pick |
Token ID | 2298 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
hing | +0.077 |
ming | +0.072 |
aw | +0.071 |
ding | +0.069 |
flashing | +0.068 |
Neg logit contributions | |
seek | -0.044 |
One | -0.037 |
One | -0.037 |
onna | -0.033 |
moment | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
seek | +0.027 |
One | +0.024 |
One | +0.023 |
onna | +0.021 |
moral | +0.021 |
Neg logit contributions | |
hing | -0.036 |
ming | -0.033 |
aw | -0.032 |
flashing | -0.032 |
eping | -0.031 |
Token | rose |
Token ID | 8278 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
hing | +0.007 |
aw | +0.007 |
ming | +0.007 |
ding | +0.007 |
ong | +0.007 |
Neg logit contributions | |
seek | -0.006 |
One | -0.005 |
One | -0.005 |
onna | -0.005 |
emo | -0.004 |
Token | ". |
Token ID | 1911 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
seek | +0.088 |
One | +0.079 |
One | +0.079 |
moral | +0.071 |
onna | +0.070 |
Neg logit contributions | |
hing | -0.114 |
ming | -0.106 |
aw | -0.105 |
ning | -0.100 |
ding | -0.100 |
Token | away |
Token ID | 1497 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
hing | +0.006 |
ming | +0.005 |
aw | +0.005 |
flashing | +0.005 |
ding | +0.005 |
Neg logit contributions | |
seek | -0.011 |
One | -0.010 |
One | -0.010 |
moral | -0.010 |
onna | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
hing | +0.060 |
ming | +0.056 |
aw | +0.055 |
flashing | +0.054 |
ding | +0.053 |
Neg logit contributions | |
seek | -0.033 |
One | -0.029 |
One | -0.029 |
moral | -0.026 |
ifi | -0.025 |
Token | " |
Token ID | 366 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
aw | +0.048 |
hing | +0.045 |
ding | +0.044 |
ming | +0.042 |
flashing | +0.041 |
Neg logit contributions | |
seek | -0.039 |
moral | -0.030 |
ider | -0.029 |
One | -0.029 |
moment | -0.028 |
Token | H |
Token ID | 39 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
hing | +0.116 |
aw | +0.107 |
ming | +0.099 |
ding | +0.097 |
eping | +0.090 |
Neg logit contributions | |
seek | -0.101 |
onna | -0.099 |
One | -0.094 |
allowance | -0.092 |
ib | -0.085 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
hing | +0.025 |
aw | +0.025 |
ong | +0.024 |
inking | +0.023 |
ay | +0.021 |
Neg logit contributions | |
seek | -0.032 |
Lily | -0.029 |
One | -0.029 |
moral | -0.028 |
moment | -0.028 |
Token | ay |
Token ID | 323 |
Feature activation | -6.72e+00 |
Pos logit contributions | |
hing | +0.046 |
ming | +0.034 |
aw | +0.031 |
flashing | +0.029 |
eping | +0.029 |
Neg logit contributions | |
seek | -0.190 |
One | -0.181 |
One | -0.179 |
onna | -0.170 |
moral | -0.169 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
hing | +0.416 |
ming | +0.379 |
aw | +0.369 |
channels | +0.367 |
eping | +0.366 |
Neg logit contributions | |
seek | -0.273 |
One | -0.233 |
One | -0.226 |
onna | -0.209 |
moral | -0.208 |
Token | Jane |
Token ID | 12091 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
hing | +0.023 |
aw | +0.023 |
ming | +0.022 |
ding | +0.022 |
ong | +0.021 |
Neg logit contributions | |
seek | -0.016 |
One | -0.014 |
moral | -0.013 |
moment | -0.012 |
ifi | -0.012 |
Token | shouted |
Token ID | 17293 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
hing | +0.024 |
ming | +0.023 |
aw | +0.023 |
ong | +0.021 |
ding | +0.021 |
Neg logit contributions | |
seek | -0.023 |
One | -0.021 |
One | -0.021 |
moral | -0.019 |
ifi | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
hing | +0.091 |
ming | +0.086 |
ding | +0.082 |
aw | +0.082 |
ong | +0.081 |
Neg logit contributions | |
seek | -0.069 |
One | -0.062 |
ifi | -0.056 |
One | -0.056 |
moral | -0.054 |
Token | joy |
Token ID | 8716 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
seek | +0.005 |
One | +0.004 |
One | +0.004 |
moral | +0.004 |
Lily | +0.004 |
Neg logit contributions | |
hing | -0.007 |
ning | -0.007 |
ming | -0.007 |
aw | -0.007 |
eping | -0.007 |
Token | whispered |
Token ID | 25029 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
hing | +0.049 |
ming | +0.046 |
aw | +0.045 |
eping | +0.044 |
flashing | +0.043 |
Neg logit contributions | |
seek | -0.024 |
One | -0.020 |
One | -0.020 |
onna | -0.018 |
moral | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
seek | +0.027 |
One | +0.024 |
One | +0.023 |
moment | +0.021 |
onna | +0.021 |
Neg logit contributions | |
hing | -0.044 |
ming | -0.039 |
aw | -0.039 |
eping | -0.038 |
flashing | -0.037 |
Token | " |
Token ID | 366 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
seek | +0.013 |
One | +0.010 |
ifi | +0.010 |
One | +0.010 |
ib | +0.010 |
Neg logit contributions | |
hing | -0.021 |
ding | -0.020 |
ming | -0.020 |
flashing | -0.019 |
aw | -0.019 |
Token | S |
Token ID | 50 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
hing | +0.090 |
aw | +0.082 |
ming | +0.082 |
ding | +0.077 |
eping | +0.077 |
Neg logit contributions | |
seek | -0.057 |
One | -0.051 |
onna | -0.049 |
rog | -0.045 |
ifi | -0.045 |
Token | omed |
Token ID | 12657 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
seek | +0.017 |
One | +0.015 |
One | +0.014 |
onna | +0.014 |
moral | +0.013 |
Neg logit contributions | |
hing | -0.018 |
aw | -0.016 |
ming | -0.016 |
eping | -0.015 |
ong | -0.015 |
Token | ay |
Token ID | 323 |
Feature activation | -6.71e+00 |
Pos logit contributions | |
seek | +0.089 |
One | +0.088 |
One | +0.085 |
" | +0.080 |
moral | +0.079 |
Neg logit contributions | |
hing | -0.046 |
aw | -0.041 |
ming | -0.040 |
eping | -0.040 |
flashing | -0.037 |
Token | I |
Token ID | 314 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
hing | +0.378 |
ming | +0.344 |
aw | +0.338 |
eping | +0.325 |
flashing | +0.324 |
Neg logit contributions | |
seek | -0.310 |
One | -0.274 |
One | -0.269 |
onna | -0.249 |
moral | -0.247 |
Token | 'll |
Token ID | 1183 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
seek | +0.010 |
One | +0.009 |
One | +0.009 |
moral | +0.008 |
onna | +0.008 |
Neg logit contributions | |
hing | -0.014 |
ming | -0.013 |
aw | -0.013 |
eping | -0.012 |
flashing | -0.012 |
Token | do |
Token ID | 466 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
hing | +0.042 |
ming | +0.038 |
aw | +0.037 |
flashing | +0.036 |
eping | +0.036 |
Neg logit contributions | |
seek | -0.030 |
One | -0.026 |
One | -0.026 |
onna | -0.023 |
moral | -0.023 |
Token | something |
Token ID | 1223 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
hing | +0.058 |
ming | +0.055 |
aw | +0.053 |
eping | +0.051 |
flashing | +0.051 |
Neg logit contributions | |
seek | -0.036 |
One | -0.031 |
One | -0.030 |
onna | -0.028 |
ifi | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hing | +0.040 |
aw | +0.036 |
ming | +0.036 |
eping | +0.035 |
flashing | +0.034 |
Neg logit contributions | |
seek | -0.029 |
One | -0.025 |
One | -0.024 |
onna | -0.023 |
moment | -0.023 |
Token | yellow |
Token ID | 7872 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
hing | +0.137 |
ming | +0.127 |
aw | +0.123 |
eping | +0.120 |
flashing | +0.118 |
Neg logit contributions | |
seek | -0.088 |
One | -0.077 |
One | -0.074 |
moment | -0.069 |
moral | -0.068 |
Token | flowers |
Token ID | 12734 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
seek | +0.009 |
One | +0.008 |
One | +0.008 |
onna | +0.007 |
moral | +0.007 |
Neg logit contributions | |
hing | -0.011 |
aw | -0.010 |
ming | -0.010 |
flashing | -0.010 |
ding | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
seek | +0.018 |
One | +0.015 |
One | +0.015 |
onna | +0.014 |
moment | +0.014 |
Neg logit contributions | |
hing | -0.027 |
ming | -0.025 |
aw | -0.025 |
eping | -0.024 |
flashing | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
hing | +0.002 |
aw | +0.002 |
ming | +0.002 |
ding | +0.002 |
flashing | +0.002 |
Neg logit contributions | |
seek | -0.002 |
One | -0.001 |
moral | -0.001 |
ifi | -0.001 |
onna | -0.001 |
Token | Spr |
Token ID | 38454 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
hing | +0.086 |
aw | +0.078 |
ming | +0.074 |
ding | +0.073 |
eping | +0.070 |
Neg logit contributions | |
seek | -0.075 |
onna | -0.070 |
One | -0.067 |
allowance | -0.063 |
rog | -0.061 |
Token | ay |
Token ID | 323 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
seek | +0.102 |
One | +0.092 |
One | +0.091 |
onna | +0.088 |
moral | +0.088 |
Neg logit contributions | |
hing | -0.037 |
ming | -0.030 |
aw | -0.029 |
eping | -0.026 |
ong | -0.025 |
Token | these |
Token ID | 777 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
hing | +0.396 |
ming | +0.361 |
aw | +0.354 |
ding | +0.338 |
ong | +0.336 |
Neg logit contributions | |
seek | -0.297 |
One | -0.262 |
One | -0.260 |
onna | -0.236 |
moral | -0.235 |
Token | everyday |
Token ID | 10908 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
seek | +0.053 |
One | +0.047 |
One | +0.047 |
onna | +0.043 |
moral | +0.043 |
Neg logit contributions | |
hing | -0.063 |
ming | -0.057 |
aw | -0.056 |
eping | -0.054 |
flashing | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
seek | +0.033 |
One | +0.029 |
One | +0.029 |
onna | +0.026 |
moral | +0.026 |
Neg logit contributions | |
hing | -0.048 |
ming | -0.044 |
aw | -0.043 |
flashing | -0.041 |
ding | -0.041 |
Token | just |
Token ID | 655 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
hing | +0.045 |
ming | +0.042 |
aw | +0.041 |
eping | +0.039 |
flashing | +0.039 |
Neg logit contributions | |
seek | -0.028 |
One | -0.024 |
One | -0.024 |
onna | -0.022 |
moral | -0.022 |
Token | like |
Token ID | 588 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
hing | +0.049 |
ming | +0.044 |
aw | +0.043 |
ding | +0.042 |
flashing | +0.042 |
Neg logit contributions | |
seek | -0.041 |
One | -0.036 |
One | -0.036 |
onna | -0.034 |
moral | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
hing | +0.109 |
aw | +0.108 |
ding | +0.102 |
ming | +0.101 |
flashing | +0.097 |
Neg logit contributions | |
seek | -0.076 |
moral | -0.060 |
moment | -0.059 |
ifi | -0.059 |
onna | -0.058 |
Token | says |
Token ID | 1139 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
hing | +0.012 |
ming | +0.011 |
aw | +0.011 |
eping | +0.010 |
flashing | +0.010 |
Neg logit contributions | |
seek | -0.008 |
One | -0.007 |
One | -0.007 |
onna | -0.006 |
moral | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
hing | +0.042 |
aw | +0.041 |
ming | +0.040 |
ding | +0.039 |
flashing | +0.038 |
Neg logit contributions | |
seek | -0.028 |
One | -0.024 |
One | -0.023 |
moral | -0.021 |
moment | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
seek | +0.001 |
One | +0.001 |
One | +0.001 |
ifi | +0.001 |
onna | +0.001 |
Neg logit contributions | |
hing | -0.002 |
ming | -0.002 |
ding | -0.002 |
aw | -0.002 |
flashing | -0.002 |
Token | Spr |
Token ID | 38454 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
hing | +0.107 |
aw | +0.099 |
ming | +0.096 |
ding | +0.093 |
ning | +0.083 |
Neg logit contributions | |
seek | -0.084 |
onna | -0.083 |
One | -0.079 |
allowance | -0.078 |
moral | -0.074 |
Token | ay |
Token ID | 323 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
seek | +0.113 |
One | +0.108 |
One | +0.106 |
onna | +0.101 |
moral | +0.101 |
Neg logit contributions | |
hing | -0.033 |
ming | -0.026 |
aw | -0.025 |
flashing | -0.024 |
eping | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
hing | +0.397 |
ming | +0.362 |
flashing | +0.357 |
channels | +0.356 |
aw | +0.356 |
Neg logit contributions | |
seek | -0.275 |
One | -0.238 |
One | -0.230 |
moral | -0.213 |
moment | -0.211 |
Token | spray |
Token ID | 11662 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
hing | +0.049 |
ming | +0.045 |
aw | +0.044 |
ding | +0.043 |
flashing | +0.042 |
Neg logit contributions | |
seek | -0.042 |
One | -0.037 |
One | -0.036 |
onna | -0.033 |
moment | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
hing | +0.081 |
eping | +0.076 |
ming | +0.075 |
flashing | +0.073 |
channels | +0.072 |
Neg logit contributions | |
seek | -0.050 |
One | -0.046 |
Lily | -0.045 |
D | -0.044 |
One | -0.043 |
Token | spray |
Token ID | 11662 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
hing | +0.055 |
ming | +0.051 |
aw | +0.049 |
eping | +0.048 |
channels | +0.047 |
Neg logit contributions | |
seek | -0.046 |
One | -0.040 |
One | -0.039 |
moral | -0.037 |
onna | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
hing | +0.076 |
eping | +0.071 |
ming | +0.071 |
flashing | +0.068 |
aw | +0.068 |
Neg logit contributions | |
seek | -0.044 |
One | -0.040 |
Lily | -0.038 |
One | -0.038 |
D | -0.037 |
Token | cheered |
Token ID | 34767 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
hing | +0.197 |
channels | +0.188 |
ming | +0.182 |
ong | +0.180 |
aw | +0.178 |
Neg logit contributions | |
seek | -0.073 |
had | -0.062 |
moment | -0.051 |
Lily | -0.049 |
Buzz | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
hing | +0.122 |
ming | +0.112 |
aw | +0.111 |
eping | +0.108 |
flashing | +0.107 |
Neg logit contributions | |
seek | -0.073 |
One | -0.064 |
One | -0.061 |
moment | -0.057 |
moral | -0.056 |
Token | " |
Token ID | 366 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
hing | +0.048 |
ming | +0.045 |
aw | +0.044 |
flashing | +0.044 |
ding | +0.043 |
Neg logit contributions | |
seek | -0.027 |
onna | -0.021 |
One | -0.021 |
ifi | -0.020 |
moment | -0.019 |
Token | H |
Token ID | 39 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
hing | +0.111 |
aw | +0.098 |
ming | +0.098 |
ding | +0.091 |
eping | +0.091 |
Neg logit contributions | |
seek | -0.090 |
onna | -0.084 |
One | -0.084 |
allowance | -0.074 |
ifi | -0.074 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
hing | +0.031 |
aw | +0.028 |
ong | +0.026 |
ay | +0.026 |
inking | +0.025 |
Neg logit contributions | |
seek | -0.032 |
moment | -0.028 |
One | -0.027 |
onna | -0.027 |
Lily | -0.027 |
Token | ay |
Token ID | 323 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
hing | +0.041 |
ming | +0.030 |
aw | +0.026 |
flashing | +0.026 |
eping | +0.025 |
Neg logit contributions | |
seek | -0.185 |
One | -0.179 |
One | -0.176 |
moral | -0.166 |
onna | -0.166 |
Token | for |
Token ID | 329 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
hing | +0.398 |
ming | +0.366 |
channels | +0.357 |
aw | +0.355 |
flashing | +0.353 |
Neg logit contributions | |
seek | -0.276 |
One | -0.234 |
One | -0.225 |
moral | -0.209 |
moment | -0.208 |
Token | Blue |
Token ID | 4518 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
hing | +0.162 |
ming | +0.148 |
aw | +0.145 |
channels | +0.140 |
eping | +0.138 |
Neg logit contributions | |
seek | -0.110 |
One | -0.087 |
One | -0.086 |
Lily | -0.082 |
Buzz | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
seek | +0.073 |
One | +0.066 |
One | +0.065 |
moral | +0.060 |
onna | +0.059 |
Neg logit contributions | |
hing | -0.095 |
ming | -0.088 |
aw | -0.088 |
eping | -0.083 |
ong | -0.082 |
Token | his |
Token ID | 465 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
hing | +0.068 |
ming | +0.062 |
aw | +0.062 |
eping | +0.060 |
ong | +0.059 |
Neg logit contributions | |
seek | -0.040 |
One | -0.034 |
One | -0.032 |
moral | -0.030 |
moment | -0.030 |
Token | mighty |
Token ID | 18680 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
hing | +0.069 |
ming | +0.063 |
aw | +0.060 |
flashing | +0.059 |
eping | +0.059 |
Neg logit contributions | |
seek | -0.074 |
One | -0.069 |
One | -0.068 |
ifi | -0.066 |
onna | -0.066 |
Token | � |
Token ID | 95 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
seek | +0.082 |
moment | +0.072 |
moral | +0.071 |
One | +0.070 |
One | +0.068 |
Neg logit contributions | |
hing | -0.092 |
aw | -0.085 |
ming | -0.083 |
ong | -0.078 |
ding | -0.078 |
Token | € |
Token ID | 26391 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
seek | +0.081 |
moral | +0.072 |
One | +0.071 |
onna | +0.071 |
moment | +0.071 |
Neg logit contributions | |
hing | -0.087 |
aw | -0.079 |
ming | -0.078 |
ding | -0.071 |
eping | -0.071 |
Token | � |
Token ID | 129 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
seek | +0.132 |
moral | +0.118 |
ifi | +0.108 |
One | +0.108 |
One | +0.108 |
Neg logit contributions | |
aw | -0.235 |
hing | -0.235 |
ming | -0.231 |
ding | -0.214 |
ong | -0.212 |
Token | � |
Token ID | 241 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
seek | +0.144 |
moment | +0.129 |
One | +0.122 |
moral | +0.121 |
One | +0.121 |
Neg logit contributions | |
hing | -0.114 |
aw | -0.109 |
ming | -0.103 |
eping | -0.099 |
ong | -0.096 |
Token | ok |
Token ID | 482 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
aw | +0.045 |
hing | +0.043 |
flashing | +0.040 |
ding | +0.039 |
ming | +0.039 |
Neg logit contributions | |
seek | -0.036 |
rog | -0.031 |
moral | -0.031 |
ib | -0.029 |
gn | -0.029 |
Token | ay |
Token ID | 323 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
hing | +0.024 |
ming | +0.022 |
aw | +0.022 |
eping | +0.021 |
flashing | +0.021 |
Neg logit contributions | |
seek | -0.019 |
One | -0.017 |
One | -0.017 |
onna | -0.015 |
moral | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
hing | +0.383 |
ming | +0.354 |
aw | +0.345 |
ning | +0.326 |
ding | +0.326 |
Neg logit contributions | |
seek | -0.282 |
One | -0.255 |
One | -0.246 |
onna | -0.229 |
moral | -0.226 |
Token | â |
Token ID | 22940 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
hing | +0.044 |
aw | +0.041 |
ming | +0.041 |
ding | +0.040 |
ay | +0.039 |
Neg logit contributions | |
seek | -0.040 |
moment | -0.034 |
onna | -0.033 |
ifi | -0.032 |
moral | -0.032 |
Token | € |
Token ID | 26391 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
hing | +0.043 |
aw | +0.038 |
ming | +0.037 |
ding | +0.034 |
eping | +0.034 |
Neg logit contributions | |
seek | -0.038 |
onna | -0.034 |
One | -0.034 |
One | -0.033 |
moral | -0.032 |
Token | |
Token ID | 220 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
seek | +0.098 |
moral | +0.085 |
One | +0.079 |
ifi | +0.077 |
One | +0.076 |
Neg logit contributions | |
hing | -0.187 |
aw | -0.185 |
ming | -0.181 |
ding | -0.170 |
ong | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
seek | +0.015 |
ifi | +0.010 |
One | +0.009 |
moment | +0.009 |
moral | +0.009 |
Neg logit contributions | |
hing | -0.039 |
ming | -0.037 |
aw | -0.036 |
ong | -0.035 |
ding | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
seek | +0.090 |
One | +0.080 |
One | +0.078 |
onna | +0.072 |
moral | +0.070 |
Neg logit contributions | |
hing | -0.128 |
ming | -0.122 |
aw | -0.120 |
ding | -0.111 |
eping | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
hing | +0.032 |
ming | +0.029 |
aw | +0.029 |
ding | +0.028 |
flashing | +0.028 |
Neg logit contributions | |
seek | -0.019 |
One | -0.016 |
One | -0.016 |
onna | -0.014 |
moral | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
seek | +0.010 |
One | +0.008 |
ifi | +0.008 |
One | +0.008 |
ib | +0.008 |
Neg logit contributions | |
hing | -0.015 |
ding | -0.014 |
ming | -0.014 |
flashing | -0.013 |
aw | -0.013 |
Token | H |
Token ID | 39 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
hing | +0.088 |
ming | +0.080 |
aw | +0.080 |
ding | +0.076 |
ning | +0.072 |
Neg logit contributions | |
seek | -0.060 |
onna | -0.056 |
One | -0.054 |
allowance | -0.051 |
moral | -0.050 |
Token | oor |
Token ID | 2675 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
hing | +0.005 |
aw | +0.005 |
ong | +0.005 |
ay | +0.004 |
inking | +0.004 |
Neg logit contributions | |
seek | -0.006 |
gn | -0.005 |
moment | -0.005 |
moral | -0.005 |
One | -0.005 |
Token | ay |
Token ID | 323 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
hing | +0.037 |
ming | +0.026 |
aw | +0.024 |
eping | +0.023 |
flashing | +0.023 |
Neg logit contributions | |
seek | -0.158 |
One | -0.152 |
One | -0.150 |
moment | -0.142 |
moral | -0.141 |
Token | ! |
Token ID | 0 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
hing | +0.382 |
ming | +0.346 |
aw | +0.342 |
eping | +0.335 |
flashing | +0.332 |
Neg logit contributions | |
seek | -0.276 |
One | -0.237 |
One | -0.230 |
moral | -0.211 |
moment | -0.211 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
hing | +0.136 |
ming | +0.124 |
ding | +0.122 |
aw | +0.121 |
ay | +0.117 |
Neg logit contributions | |
seek | -0.105 |
One | -0.087 |
moral | -0.083 |
onna | -0.083 |
moment | -0.082 |
Token | 's |
Token ID | 338 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
seek | +0.063 |
One | +0.059 |
One | +0.058 |
Lily | +0.052 |
moment | +0.052 |
Neg logit contributions | |
hing | -0.089 |
flashing | -0.079 |
channels | -0.078 |
eping | -0.077 |
ming | -0.077 |
Token | throw |
Token ID | 3714 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
hing | +0.212 |
ming | +0.196 |
aw | +0.195 |
eping | +0.187 |
flashing | +0.186 |
Neg logit contributions | |
seek | -0.179 |
One | -0.158 |
One | -0.152 |
moral | -0.140 |
moment | -0.137 |
Token | my |
Token ID | 616 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
seek | +0.011 |
One | +0.009 |
One | +0.009 |
moment | +0.008 |
moral | +0.008 |
Neg logit contributions | |
hing | -0.015 |
ming | -0.013 |
aw | -0.013 |
eping | -0.013 |
flashing | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
hing | +0.027 |
aw | +0.027 |
flashing | +0.025 |
ding | +0.024 |
ning | +0.024 |
Neg logit contributions | |
seek | -0.021 |
onna | -0.016 |
One | -0.015 |
ifi | -0.015 |
moment | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
hing | +0.002 |
aw | +0.002 |
ming | +0.002 |
eping | +0.002 |
flashing | +0.002 |
Neg logit contributions | |
seek | -0.001 |
ider | -0.001 |
ro | -0.001 |
moment | -0.001 |
gn | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
onna | +0.005 |
seek | +0.005 |
One | +0.005 |
allowance | +0.004 |
ro | +0.004 |
Neg logit contributions | |
hing | -0.009 |
aw | -0.009 |
eping | -0.009 |
ming | -0.008 |
ding | -0.008 |
Token | H |
Token ID | 39 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
onna | +0.005 |
seek | +0.005 |
One | +0.005 |
allowance | +0.004 |
ib | +0.004 |
Neg logit contributions | |
hing | -0.006 |
aw | -0.006 |
ming | -0.005 |
ding | -0.005 |
flashing | -0.005 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
hing | +0.009 |
aw | +0.008 |
ong | +0.008 |
inking | +0.007 |
ay | +0.007 |
Neg logit contributions | |
seek | -0.010 |
moral | -0.009 |
moment | -0.008 |
One | -0.008 |
Lily | -0.008 |
Token | ay |
Token ID | 323 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
hing | +0.042 |
ming | +0.033 |
flashing | +0.029 |
eping | +0.028 |
aw | +0.028 |
Neg logit contributions | |
seek | -0.174 |
One | -0.171 |
One | -0.168 |
moral | -0.158 |
moment | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
hing | +0.430 |
ming | +0.393 |
aw | +0.385 |
channels | +0.384 |
eping | +0.382 |
Neg logit contributions | |
seek | -0.226 |
One | -0.190 |
One | -0.181 |
moral | -0.162 |
moment | -0.162 |
Token | h |
Token ID | 289 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
hing | +0.056 |
ding | +0.052 |
aw | +0.052 |
flashing | +0.049 |
ming | +0.049 |
Neg logit contributions | |
seek | -0.035 |
One | -0.032 |
onna | -0.031 |
One | -0.030 |
ib | -0.027 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
hing | +0.135 |
ming | +0.122 |
aw | +0.118 |
eping | +0.115 |
flashing | +0.114 |
Neg logit contributions | |
seek | -0.138 |
One | -0.125 |
One | -0.123 |
onna | -0.117 |
moral | -0.113 |
Token | ay |
Token ID | 323 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
hing | +0.041 |
ming | +0.030 |
aw | +0.026 |
eping | +0.023 |
flashing | +0.023 |
Neg logit contributions | |
seek | -0.203 |
One | -0.193 |
One | -0.191 |
onna | -0.182 |
moral | -0.182 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
hing | +0.418 |
channels | +0.380 |
ming | +0.378 |
eping | +0.371 |
aw | +0.368 |
Neg logit contributions | |
seek | -0.255 |
One | -0.220 |
One | -0.211 |
" | -0.192 |
moral | -0.191 |
Token | spicy |
Token ID | 26880 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
seek | +0.116 |
One | +0.102 |
One | +0.100 |
onna | +0.091 |
moral | +0.091 |
Neg logit contributions | |
hing | -0.150 |
ming | -0.138 |
aw | -0.136 |
eping | -0.133 |
flashing | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
hing | +0.197 |
ming | +0.180 |
eping | +0.178 |
aw | +0.177 |
ding | +0.176 |
Neg logit contributions | |
seek | -0.063 |
One | -0.053 |
onna | -0.045 |
One | -0.045 |
ro | -0.043 |
Token | " |
Token ID | 366 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
hing | +0.039 |
ming | +0.036 |
aw | +0.036 |
ding | +0.034 |
flashing | +0.034 |
Neg logit contributions | |
seek | -0.027 |
One | -0.022 |
One | -0.021 |
moral | -0.020 |
moment | -0.020 |
Token | H |
Token ID | 39 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
hing | +0.106 |
aw | +0.097 |
ming | +0.094 |
ding | +0.093 |
eping | +0.091 |
Neg logit contributions | |
seek | -0.078 |
One | -0.069 |
onna | -0.066 |
gn | -0.060 |
rog | -0.060 |
Token | oor |
Token ID | 2675 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ong | +0.019 |
hing | +0.019 |
aw | +0.019 |
inking | +0.018 |
ee | +0.017 |
Neg logit contributions | |
seek | -0.019 |
One | -0.017 |
One | -0.017 |
Tweet | -0.017 |
gn | -0.016 |
Token | ay |
Token ID | 323 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
hing | +0.039 |
ming | +0.029 |
aw | +0.025 |
flashing | +0.025 |
eping | +0.024 |
Neg logit contributions | |
seek | -0.169 |
One | -0.165 |
One | -0.162 |
moral | -0.153 |
onna | -0.153 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
hing | +0.401 |
ming | +0.366 |
aw | +0.361 |
channels | +0.358 |
flashing | +0.357 |
Neg logit contributions | |
seek | -0.250 |
One | -0.210 |
One | -0.199 |
onna | -0.188 |
moral | -0.186 |
Token | said |
Token ID | 531 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
hing | +0.017 |
ming | +0.016 |
aw | +0.015 |
eping | +0.015 |
ning | +0.015 |
Neg logit contributions | |
seek | -0.008 |
One | -0.007 |
One | -0.006 |
onna | -0.005 |
moment | -0.005 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
hing | +0.146 |
ming | +0.134 |
aw | +0.132 |
eping | +0.128 |
flashing | +0.127 |
Neg logit contributions | |
seek | -0.080 |
One | -0.069 |
One | -0.066 |
onna | -0.060 |
moral | -0.059 |
Token | my |
Token ID | 1820 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
hing | +0.062 |
ming | +0.059 |
ding | +0.053 |
ning | +0.052 |
flashing | +0.050 |
Neg logit contributions | |
seek | -0.107 |
One | -0.095 |
ifi | -0.093 |
One | -0.092 |
moral | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
hing | +0.114 |
ming | +0.111 |
ding | +0.103 |
aw | +0.103 |
flashing | +0.102 |
Neg logit contributions | |
seek | -0.071 |
One | -0.065 |
One | -0.060 |
moral | -0.057 |
ifi | -0.056 |
Token | cookies |
Token ID | 14746 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
seek | +0.035 |
One | +0.031 |
One | +0.030 |
moral | +0.029 |
moment | +0.029 |
Neg logit contributions | |
hing | -0.038 |
ming | -0.035 |
aw | -0.034 |
eping | -0.032 |
flashing | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
seek | +0.065 |
One | +0.051 |
One | +0.048 |
moment | +0.042 |
onna | +0.042 |
Neg logit contributions | |
hing | -0.197 |
ming | -0.183 |
aw | -0.181 |
eping | -0.178 |
flashing | -0.176 |
Token | but |
Token ID | 475 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
seek | +0.020 |
One | +0.017 |
One | +0.016 |
onna | +0.015 |
moral | +0.014 |
Neg logit contributions | |
hing | -0.042 |
aw | -0.040 |
ming | -0.039 |
flashing | -0.039 |
ding | -0.039 |
Token | they |
Token ID | 484 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
hing | +0.098 |
aw | +0.092 |
ming | +0.092 |
ding | +0.092 |
flashing | +0.092 |
Neg logit contributions | |
seek | -0.051 |
One | -0.045 |
One | -0.045 |
onna | -0.042 |
ib | -0.039 |
Token | were |
Token ID | 547 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
hing | +0.053 |
ming | +0.048 |
aw | +0.048 |
eping | +0.046 |
flashing | +0.046 |
Neg logit contributions | |
seek | -0.038 |
One | -0.034 |
One | -0.033 |
onna | -0.030 |
moral | -0.030 |
Token | not |
Token ID | 407 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
hing | +0.101 |
ming | +0.094 |
aw | +0.093 |
eping | +0.091 |
flashing | +0.090 |
Neg logit contributions | |
seek | -0.048 |
One | -0.041 |
One | -0.040 |
onna | -0.035 |
moment | -0.035 |
Token | used |
Token ID | 973 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
seek | +0.143 |
One | +0.127 |
One | +0.125 |
moral | +0.113 |
onna | +0.113 |
Neg logit contributions | |
hing | -0.194 |
ming | -0.178 |
aw | -0.176 |
eping | -0.171 |
flashing | -0.169 |
Token | to |
Token ID | 284 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
seek | +0.035 |
One | +0.030 |
One | +0.030 |
moral | +0.027 |
onna | +0.027 |
Neg logit contributions | |
hing | -0.053 |
ming | -0.049 |
aw | -0.048 |
flashing | -0.046 |
eping | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
seek | +0.013 |
One | +0.012 |
One | +0.011 |
moral | +0.011 |
onna | +0.010 |
Neg logit contributions | |
hing | -0.017 |
ming | -0.016 |
aw | -0.015 |
flashing | -0.015 |
eping | -0.015 |
Token | spice |
Token ID | 25721 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
hing | +0.022 |
ming | +0.020 |
aw | +0.020 |
eping | +0.019 |
flashing | +0.018 |
Neg logit contributions | |
seek | -0.020 |
One | -0.018 |
One | -0.017 |
moral | -0.017 |
moment | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
hing | +0.071 |
ming | +0.066 |
eping | +0.066 |
flashing | +0.065 |
aw | +0.063 |
Neg logit contributions | |
seek | -0.017 |
One | -0.014 |
onna | -0.013 |
One | -0.012 |
moment | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
hing | +0.007 |
out | +0.007 |
ding | +0.007 |
aw | +0.006 |
eping | +0.006 |
Neg logit contributions | |
seek | -0.006 |
onna | -0.006 |
ro | -0.006 |
gn | -0.005 |
ib | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
seek | +0.025 |
One | +0.022 |
One | +0.021 |
moment | +0.018 |
onna | +0.018 |
Neg logit contributions | |
hing | -0.056 |
ming | -0.053 |
aw | -0.051 |
eping | -0.050 |
flashing | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
hing | +0.048 |
aw | +0.047 |
eping | +0.044 |
flashing | +0.043 |
ming | +0.043 |
Neg logit contributions | |
seek | -0.042 |
onna | -0.038 |
ro | -0.035 |
ider | -0.034 |
rog | -0.034 |
Token | little |
Token ID | 1310 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
seek | +0.010 |
One | +0.009 |
One | +0.008 |
onna | +0.008 |
ifi | +0.008 |
Neg logit contributions | |
hing | -0.013 |
ding | -0.012 |
aw | -0.012 |
ming | -0.012 |
eping | -0.012 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
seek | +0.017 |
One | +0.014 |
One | +0.014 |
moment | +0.012 |
moral | +0.012 |
Neg logit contributions | |
hing | -0.028 |
ming | -0.026 |
aw | -0.026 |
eping | -0.025 |
flashing | -0.025 |
Token | named |
Token ID | 3706 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
hing | +0.016 |
aw | +0.016 |
ming | +0.015 |
ning | +0.014 |
eping | +0.014 |
Neg logit contributions | |
seek | -0.015 |
allowance | -0.013 |
moral | -0.013 |
moment | -0.013 |
onna | -0.012 |
Token | Benny |
Token ID | 44275 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
moral | +0.198 |
ider | +0.195 |
seek | +0.184 |
edly | +0.180 |
moment | +0.178 |
Neg logit contributions | |
hing | -0.158 |
ning | -0.155 |
out | -0.152 |
ming | -0.148 |
cient | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
seek | +0.034 |
ider | +0.027 |
onna | +0.027 |
allowance | +0.026 |
moral | +0.026 |
Neg logit contributions | |
hing | -0.048 |
aw | -0.044 |
ming | -0.043 |
eping | -0.042 |
ning | -0.040 |
Token | Benny |
Token ID | 44275 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
seek | +0.023 |
ifi | +0.021 |
ider | +0.020 |
moral | +0.020 |
onna | +0.019 |
Neg logit contributions | |
hing | -0.035 |
ming | -0.031 |
ning | -0.029 |
channels | -0.028 |
ay | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
seek | +0.019 |
ider | +0.018 |
onna | +0.017 |
allowance | +0.017 |
moral | +0.017 |
Neg logit contributions | |
hing | -0.011 |
aw | -0.010 |
ming | -0.009 |
eping | -0.009 |
flashing | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
seek | +0.007 |
One | +0.006 |
One | +0.006 |
onna | +0.006 |
moral | +0.006 |
Neg logit contributions | |
hing | -0.008 |
ming | -0.008 |
aw | -0.008 |
eping | -0.007 |
flashing | -0.007 |
Token | Jane |
Token ID | 41083 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
allowance | +0.020 |
onna | +0.020 |
ib | +0.018 |
seek | +0.018 |
ider | +0.017 |
Neg logit contributions | |
aw | -0.031 |
hing | -0.029 |
arre | -0.028 |
ming | -0.026 |
ding | -0.025 |
Token | answered |
Token ID | 9373 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
seek | +0.046 |
One | +0.041 |
One | +0.040 |
ifi | +0.037 |
onna | +0.037 |
Neg logit contributions | |
hing | -0.059 |
ming | -0.055 |
aw | -0.055 |
ding | -0.051 |
eping | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
seek | +0.021 |
One | +0.018 |
One | +0.018 |
onna | +0.016 |
moral | +0.016 |
Neg logit contributions | |
hing | -0.037 |
ming | -0.035 |
aw | -0.034 |
flashing | -0.033 |
eping | -0.033 |
Token | � |
Token ID | 6184 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
seek | +0.010 |
One | +0.008 |
ifi | +0.008 |
ib | +0.008 |
rog | +0.007 |
Neg logit contributions | |
hing | -0.013 |
ding | -0.012 |
ming | -0.012 |
aw | -0.012 |
flashing | -0.012 |
Token | � |
Token ID | 95 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
seek | +0.087 |
One | +0.076 |
moment | +0.075 |
One | +0.075 |
moral | +0.074 |
Neg logit contributions | |
hing | -0.091 |
aw | -0.084 |
ming | -0.082 |
ong | -0.077 |
ding | -0.076 |
Token | € |
Token ID | 26391 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
seek | +0.089 |
One | +0.077 |
One | +0.077 |
onna | +0.075 |
moral | +0.074 |
Neg logit contributions | |
hing | -0.094 |
ming | -0.086 |
aw | -0.085 |
eping | -0.078 |
ding | -0.078 |
Token | � |
Token ID | 129 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
seek | +0.153 |
One | +0.134 |
One | +0.133 |
moral | +0.126 |
onna | +0.124 |
Neg logit contributions | |
hing | -0.193 |
ming | -0.180 |
aw | -0.179 |
flashing | -0.167 |
ding | -0.167 |
Token | � |
Token ID | 241 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
seek | +0.125 |
One | +0.106 |
moment | +0.106 |
One | +0.104 |
onna | +0.102 |
Neg logit contributions | |
hing | -0.107 |
aw | -0.098 |
ming | -0.096 |
eping | -0.092 |
ong | -0.090 |
Token | It |
Token ID | 1026 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
aw | +0.061 |
hing | +0.053 |
flashing | +0.052 |
ee | +0.048 |
ding | +0.048 |
Neg logit contributions | |
seek | -0.055 |
moral | -0.048 |
rog | -0.048 |
Buzz | -0.047 |
One | -0.045 |
Token | â |
Token ID | 22940 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
seek | +0.023 |
One | +0.021 |
One | +0.020 |
onna | +0.019 |
moment | +0.018 |
Neg logit contributions | |
hing | -0.029 |
ming | -0.026 |
aw | -0.026 |
eping | -0.025 |
flashing | -0.024 |
Token | € |
Token ID | 26391 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
seek | +0.028 |
onna | +0.024 |
One | +0.024 |
One | +0.024 |
moral | +0.023 |
Neg logit contributions | |
hing | -0.032 |
aw | -0.029 |
ming | -0.029 |
ding | -0.026 |
ong | -0.026 |
Token | this |
Token ID | 428 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
hing | +0.047 |
ming | +0.046 |
aw | +0.044 |
flashing | +0.042 |
ding | +0.042 |
Neg logit contributions | |
seek | -0.031 |
One | -0.027 |
One | -0.027 |
ifi | -0.025 |
onna | -0.025 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
seek | +0.034 |
One | +0.030 |
One | +0.030 |
onna | +0.027 |
ifi | +0.027 |
Neg logit contributions | |
hing | -0.045 |
ming | -0.042 |
aw | -0.041 |
ding | -0.040 |
ong | -0.039 |
Token | She |
Token ID | 1375 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
seek | +0.005 |
One | +0.003 |
moral | +0.003 |
One | +0.003 |
onna | +0.003 |
Neg logit contributions | |
hing | -0.012 |
aw | -0.012 |
ming | -0.012 |
ong | -0.011 |
ding | -0.011 |
Token | started |
Token ID | 2067 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
hing | +0.022 |
ming | +0.021 |
aw | +0.021 |
eping | +0.020 |
ding | +0.019 |
Neg logit contributions | |
seek | -0.017 |
One | -0.015 |
One | -0.015 |
onna | -0.014 |
ifi | -0.014 |
Token | climbing |
Token ID | 14281 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
hing | +0.017 |
ming | +0.016 |
aw | +0.015 |
eping | +0.015 |
flashing | +0.015 |
Neg logit contributions | |
seek | -0.010 |
One | -0.009 |
One | -0.009 |
onna | -0.008 |
moral | -0.008 |
Token | again |
Token ID | 757 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
seek | +0.082 |
One | +0.073 |
One | +0.072 |
moral | +0.070 |
ifi | +0.070 |
Neg logit contributions | |
hing | -0.078 |
ming | -0.074 |
aw | -0.071 |
flashing | -0.070 |
ning | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
seek | +0.116 |
One | +0.104 |
One | +0.102 |
moral | +0.096 |
ifi | +0.095 |
Neg logit contributions | |
hing | -0.205 |
ming | -0.195 |
aw | -0.190 |
flashing | -0.184 |
eping | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
aw | +0.032 |
hing | +0.032 |
ming | +0.031 |
ding | +0.030 |
ong | +0.030 |
Neg logit contributions | |
seek | -0.020 |
moral | -0.015 |
One | -0.014 |
allowance | -0.014 |
ifi | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
hing | +0.017 |
aw | +0.016 |
ming | +0.016 |
ong | +0.015 |
eping | +0.015 |
Neg logit contributions | |
seek | -0.009 |
ider | -0.007 |
allowance | -0.007 |
ro | -0.007 |
gn | -0.006 |
Token | Finally |
Token ID | 11158 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
hing | +0.003 |
aw | +0.003 |
ming | +0.003 |
ding | +0.003 |
eping | +0.003 |
Neg logit contributions | |
seek | -0.002 |
One | -0.002 |
onna | -0.002 |
allowance | -0.002 |
D | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
hing | +0.007 |
aw | +0.007 |
ming | +0.007 |
flashing | +0.006 |
ding | +0.006 |
Neg logit contributions | |
seek | -0.005 |
One | -0.005 |
onna | -0.005 |
One | -0.005 |
moral | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
seek | +0.029 |
One | +0.024 |
One | +0.024 |
moral | +0.022 |
onna | +0.022 |
Neg logit contributions | |
hing | -0.054 |
ming | -0.051 |
aw | -0.050 |
flashing | -0.049 |
eping | -0.049 |
Token | But |
Token ID | 887 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
seek | +0.014 |
One | +0.012 |
moral | +0.011 |
onna | +0.010 |
moment | +0.010 |
Neg logit contributions | |
aw | -0.019 |
hing | -0.018 |
ding | -0.016 |
flashing | -0.016 |
ong | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
seek | +0.016 |
onna | +0.015 |
One | +0.015 |
ib | +0.014 |
opener | +0.014 |
Neg logit contributions | |
aw | -0.019 |
hing | -0.017 |
ding | -0.017 |
out | -0.016 |
ning | -0.016 |
Token | cave |
Token ID | 11527 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
hing | +0.014 |
ming | +0.012 |
aw | +0.012 |
eping | +0.012 |
flashing | +0.012 |
Neg logit contributions | |
seek | -0.011 |
One | -0.009 |
One | -0.009 |
onna | -0.009 |
moral | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
hing | +0.050 |
ming | +0.046 |
aw | +0.046 |
eping | +0.044 |
flashing | +0.044 |
Neg logit contributions | |
seek | -0.024 |
One | -0.020 |
One | -0.019 |
onna | -0.017 |
moment | -0.017 |
Token | indeed |
Token ID | 5600 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
seek | +0.078 |
One | +0.069 |
One | +0.068 |
onna | +0.063 |
moral | +0.062 |
Neg logit contributions | |
hing | -0.092 |
ming | -0.083 |
aw | -0.080 |
eping | -0.077 |
ding | -0.077 |
Token | been |
Token ID | 587 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
seek | +0.136 |
One | +0.122 |
One | +0.120 |
moral | +0.109 |
onna | +0.109 |
Neg logit contributions | |
hing | -0.185 |
ming | -0.170 |
aw | -0.168 |
flashing | -0.164 |
eping | -0.163 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
seek | +0.029 |
One | +0.027 |
One | +0.026 |
moral | +0.024 |
onna | +0.024 |
Neg logit contributions | |
hing | -0.033 |
ming | -0.031 |
aw | -0.030 |
eping | -0.030 |
flashing | -0.030 |
Token | perfect |
Token ID | 2818 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
seek | +0.069 |
One | +0.060 |
One | +0.059 |
moral | +0.056 |
moment | +0.055 |
Neg logit contributions | |
hing | -0.083 |
ming | -0.075 |
aw | -0.074 |
eping | -0.071 |
flashing | -0.070 |
Token | spot |
Token ID | 4136 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
hing | +0.024 |
ming | +0.022 |
aw | +0.022 |
flashing | +0.021 |
eping | +0.021 |
Neg logit contributions | |
seek | -0.019 |
One | -0.017 |
One | -0.017 |
onna | -0.015 |
moral | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
seek | +0.015 |
One | +0.014 |
One | +0.014 |
moral | +0.013 |
onna | +0.012 |
Neg logit contributions | |
hing | -0.017 |
ming | -0.016 |
aw | -0.016 |
flashing | -0.015 |
ong | -0.015 |
Token | special |
Token ID | 2041 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
hing | +0.043 |
ming | +0.038 |
aw | +0.038 |
eping | +0.036 |
flashing | +0.036 |
Neg logit contributions | |
seek | -0.036 |
One | -0.032 |
One | -0.032 |
moral | -0.030 |
moment | -0.030 |
Token | drink |
Token ID | 4144 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hing | +0.079 |
ming | +0.072 |
aw | +0.071 |
eping | +0.068 |
flashing | +0.068 |
Neg logit contributions | |
seek | -0.065 |
One | -0.057 |
One | -0.056 |
moment | -0.052 |
moral | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
seek | +0.028 |
One | +0.023 |
One | +0.022 |
onna | +0.019 |
moral | +0.019 |
Neg logit contributions | |
hing | -0.077 |
ming | -0.072 |
aw | -0.071 |
eping | -0.068 |
flashing | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
seek | +0.005 |
ifi | +0.003 |
ider | +0.003 |
One | +0.003 |
moral | +0.003 |
Neg logit contributions | |
hing | -0.010 |
aw | -0.009 |
ming | -0.009 |
ay | -0.009 |
channels | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
seek | +0.014 |
ider | +0.011 |
ib | +0.010 |
allowance | +0.010 |
ro | +0.010 |
Neg logit contributions | |
hing | -0.027 |
aw | -0.025 |
ming | -0.024 |
eping | -0.024 |
ong | -0.024 |
Token | The |
Token ID | 464 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
seek | +0.020 |
onna | +0.018 |
One | +0.017 |
D | +0.017 |
ib | +0.016 |
Neg logit contributions | |
hing | -0.041 |
ming | -0.037 |
aw | -0.036 |
eping | -0.035 |
ding | -0.035 |
Token | spider |
Token ID | 19230 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
seek | +0.060 |
One | +0.055 |
One | +0.052 |
onna | +0.052 |
ifi | +0.050 |
Neg logit contributions | |
hing | -0.073 |
ming | -0.067 |
aw | -0.064 |
ding | -0.064 |
eping | -0.063 |
Token | was |
Token ID | 373 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
hing | +0.006 |
ming | +0.006 |
aw | +0.005 |
eping | +0.005 |
ding | +0.005 |
Neg logit contributions | |
seek | -0.004 |
One | -0.004 |
One | -0.004 |
onna | -0.003 |
moral | -0.003 |
Token | so |
Token ID | 523 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
hing | +0.025 |
ming | +0.023 |
aw | +0.023 |
eping | +0.022 |
flashing | +0.022 |
Neg logit contributions | |
seek | -0.018 |
One | -0.016 |
One | -0.016 |
onna | -0.015 |
moral | -0.014 |
Token | happy |
Token ID | 3772 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
seek | +0.018 |
One | +0.015 |
One | +0.015 |
onna | +0.014 |
moment | +0.014 |
Neg logit contributions | |
hing | -0.033 |
ming | -0.031 |
aw | -0.030 |
flashing | -0.029 |
eping | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
seek | +0.003 |
One | +0.003 |
One | +0.003 |
moral | +0.002 |
onna | +0.002 |
Neg logit contributions | |
hing | -0.004 |
ming | -0.004 |
aw | -0.004 |
flashing | -0.004 |
ning | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
seek | +0.049 |
One | +0.043 |
One | +0.042 |
moral | +0.039 |
ifi | +0.038 |
Neg logit contributions | |
hing | -0.067 |
ming | -0.063 |
flashing | -0.060 |
aw | -0.060 |
eping | -0.059 |
Token | restored |
Token ID | 15032 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
hing | +0.020 |
ming | +0.019 |
aw | +0.019 |
flashing | +0.018 |
eping | +0.018 |
Neg logit contributions | |
seek | -0.015 |
One | -0.013 |
One | -0.013 |
onna | -0.012 |
ifi | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
hing | +0.052 |
ming | +0.051 |
aw | +0.049 |
ning | +0.049 |
flashing | +0.049 |
Neg logit contributions | |
seek | -0.040 |
One | -0.035 |
One | -0.032 |
onna | -0.031 |
ider | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
seek | +0.008 |
One | +0.007 |
One | +0.007 |
ifi | +0.006 |
moral | +0.006 |
Neg logit contributions | |
hing | -0.011 |
ming | -0.011 |
aw | -0.010 |
flashing | -0.010 |
eping | -0.010 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
seek | +0.019 |
One | +0.016 |
One | +0.016 |
onna | +0.015 |
moral | +0.014 |
Neg logit contributions | |
hing | -0.046 |
ming | -0.042 |
flashing | -0.042 |
ding | -0.041 |
aw | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
seek | +0.058 |
One | +0.051 |
ifi | +0.048 |
One | +0.048 |
onna | +0.047 |
Neg logit contributions | |
hing | -0.082 |
ming | -0.080 |
eping | -0.073 |
ning | -0.073 |
aw | -0.072 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
seek | +0.010 |
ifi | +0.008 |
One | +0.008 |
pe | +0.008 |
rog | +0.008 |
Neg logit contributions | |
channels | -0.011 |
aw | -0.011 |
ding | -0.011 |
ay | -0.010 |
hing | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
seek | +0.053 |
One | +0.047 |
One | +0.047 |
ifi | +0.042 |
onna | +0.042 |
Neg logit contributions | |
hing | -0.081 |
ming | -0.077 |
aw | -0.074 |
eping | -0.071 |
flashing | -0.070 |
Token | so |
Token ID | 523 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
hing | +0.027 |
ming | +0.025 |
aw | +0.024 |
eping | +0.023 |
flashing | +0.023 |
Neg logit contributions | |
seek | -0.024 |
One | -0.022 |
One | -0.021 |
onna | -0.020 |
moral | -0.020 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
seek | +0.025 |
One | +0.021 |
One | +0.021 |
onna | +0.019 |
moral | +0.018 |
Neg logit contributions | |
hing | -0.045 |
ming | -0.041 |
aw | -0.041 |
eping | -0.040 |
ding | -0.039 |
Token | ! |
Token ID | 0 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
seek | +0.005 |
One | +0.004 |
One | +0.004 |
moral | +0.004 |
ifi | +0.004 |
Neg logit contributions | |
hing | -0.007 |
ming | -0.006 |
aw | -0.006 |
flashing | -0.006 |
ning | -0.006 |
Token | white |
Token ID | 2330 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
hing | +0.070 |
ming | +0.065 |
aw | +0.064 |
eping | +0.061 |
flashing | +0.061 |
Neg logit contributions | |
seek | -0.043 |
One | -0.037 |
One | -0.036 |
onna | -0.033 |
moment | -0.033 |
Token | marble |
Token ID | 30623 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
hing | +0.004 |
ming | +0.004 |
aw | +0.004 |
flashing | +0.004 |
eping | +0.003 |
Neg logit contributions | |
seek | -0.003 |
One | -0.003 |
One | -0.003 |
onna | -0.003 |
moral | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
seek | +0.089 |
One | +0.078 |
One | +0.077 |
moral | +0.070 |
onna | +0.070 |
Neg logit contributions | |
hing | -0.129 |
ming | -0.119 |
aw | -0.117 |
flashing | -0.112 |
eping | -0.112 |
Token | perfect |
Token ID | 2818 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
seek | +0.055 |
One | +0.050 |
One | +0.050 |
onna | +0.046 |
moral | +0.045 |
Neg logit contributions | |
hing | -0.078 |
ming | -0.073 |
aw | -0.071 |
flashing | -0.070 |
eping | -0.069 |
Token | for |
Token ID | 329 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
hing | +0.109 |
ming | +0.100 |
aw | +0.098 |
flashing | +0.094 |
eping | +0.094 |
Neg logit contributions | |
seek | -0.077 |
One | -0.068 |
One | -0.067 |
onna | -0.061 |
moral | -0.061 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
hing | +0.059 |
ming | +0.054 |
aw | +0.053 |
flashing | +0.051 |
eping | +0.051 |
Neg logit contributions | |
seek | -0.051 |
One | -0.045 |
One | -0.045 |
onna | -0.042 |
moral | -0.041 |
Token | games |
Token ID | 1830 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
seek | +0.011 |
One | +0.010 |
One | +0.010 |
onna | +0.010 |
ifi | +0.009 |
Neg logit contributions | |
hing | -0.016 |
ming | -0.015 |
aw | -0.015 |
eping | -0.014 |
flashing | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
hing | +0.020 |
ming | +0.018 |
aw | +0.018 |
flashing | +0.017 |
eping | +0.017 |
Neg logit contributions | |
seek | -0.010 |
One | -0.009 |
One | -0.009 |
moral | -0.008 |
onna | -0.008 |
Token | everyone |
Token ID | 2506 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
hing | +0.036 |
ming | +0.033 |
aw | +0.032 |
eping | +0.031 |
flashing | +0.031 |
Neg logit contributions | |
seek | -0.028 |
One | -0.024 |
One | -0.024 |
onna | -0.022 |
moral | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
hing | +0.193 |
ming | +0.179 |
aw | +0.178 |
eping | +0.173 |
ong | +0.172 |
Neg logit contributions | |
seek | -0.087 |
One | -0.067 |
One | -0.064 |
moment | -0.062 |
onna | -0.058 |
Token | delighted |
Token ID | 20707 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
hing | +0.035 |
ming | +0.032 |
aw | +0.031 |
eping | +0.030 |
flashing | +0.030 |
Neg logit contributions | |
seek | -0.032 |
One | -0.029 |
One | -0.028 |
onna | -0.026 |
moral | -0.026 |
Token | nice |
Token ID | 3621 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
hing | +0.081 |
ming | +0.074 |
aw | +0.073 |
flashing | +0.069 |
ding | +0.068 |
Neg logit contributions | |
seek | -0.057 |
One | -0.049 |
One | -0.048 |
moral | -0.044 |
onna | -0.044 |
Token | or |
Token ID | 393 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
hing | +0.007 |
ming | +0.007 |
aw | +0.006 |
eping | +0.006 |
flashing | +0.006 |
Neg logit contributions | |
seek | -0.002 |
One | -0.002 |
One | -0.002 |
onna | -0.002 |
moment | -0.002 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
seek | +0.137 |
One | +0.119 |
One | +0.117 |
moral | +0.109 |
onna | +0.109 |
Neg logit contributions | |
hing | -0.166 |
ming | -0.150 |
aw | -0.148 |
eping | -0.142 |
flashing | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
seek | +0.007 |
One | +0.006 |
One | +0.006 |
moment | +0.004 |
Lily | +0.004 |
Neg logit contributions | |
hing | -0.032 |
ming | -0.030 |
eping | -0.029 |
flashing | -0.029 |
aw | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
aw | +0.014 |
ding | +0.013 |
hing | +0.013 |
channels | +0.013 |
flashing | +0.012 |
Neg logit contributions | |
seek | -0.012 |
moment | -0.009 |
ifi | -0.009 |
moral | -0.009 |
allowance | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
seek | +0.012 |
ider | +0.010 |
allowance | +0.009 |
ro | +0.009 |
moment | +0.009 |
Neg logit contributions | |
aw | -0.014 |
hing | -0.012 |
eping | -0.012 |
ay | -0.012 |
ding | -0.012 |
Token | " |
Token ID | 1 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
onna | +0.016 |
allowance | +0.015 |
seek | +0.015 |
Buzz | +0.014 |
Nancy | +0.014 |
Neg logit contributions | |
aw | -0.022 |
hing | -0.018 |
eping | -0.018 |
ding | -0.018 |
ming | -0.017 |
Token | Come |
Token ID | 16773 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
seek | +0.014 |
One | +0.013 |
onna | +0.013 |
ib | +0.012 |
D | +0.012 |
Neg logit contributions | |
hing | -0.018 |
aw | -0.017 |
ding | -0.016 |
ming | -0.016 |
flashing | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
hing | +0.009 |
ming | +0.008 |
aw | +0.008 |
eping | +0.008 |
flashing | +0.008 |
Neg logit contributions | |
seek | -0.009 |
One | -0.008 |
One | -0.008 |
onna | -0.007 |
moral | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
hing | +0.015 |
ming | +0.013 |
aw | +0.013 |
eping | +0.013 |
flashing | +0.013 |
Neg logit contributions | |
seek | -0.008 |
One | -0.007 |
One | -0.006 |
onna | -0.006 |
moral | -0.006 |
Token | fox |
Token ID | 21831 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
hing | +0.080 |
aw | +0.075 |
ding | +0.075 |
ming | +0.073 |
ong | +0.071 |
Neg logit contributions | |
seek | -0.051 |
One | -0.047 |
One | -0.045 |
onna | -0.042 |
moment | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
seek | +0.042 |
One | +0.035 |
One | +0.033 |
onna | +0.030 |
moment | +0.029 |
Neg logit contributions | |
hing | -0.106 |
ming | -0.098 |
aw | -0.097 |
eping | -0.094 |
flashing | -0.094 |
Token | smile |
Token ID | 8212 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
seek | +0.006 |
One | +0.006 |
One | +0.005 |
moment | +0.005 |
moral | +0.005 |
Neg logit contributions | |
hing | -0.009 |
ming | -0.008 |
aw | -0.008 |
eping | -0.008 |
ning | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
hing | +0.034 |
ming | +0.031 |
aw | +0.031 |
eping | +0.030 |
flashing | +0.030 |
Neg logit contributions | |
seek | -0.010 |
One | -0.008 |
One | -0.007 |
moment | -0.006 |
moral | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
aw | +0.027 |
hing | +0.027 |
ding | +0.025 |
ming | +0.025 |
flashing | +0.025 |
Neg logit contributions | |
seek | -0.014 |
One | -0.010 |
moment | -0.010 |
moral | -0.010 |
onna | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
seek | +0.005 |
ider | +0.004 |
allowance | +0.004 |
ro | +0.003 |
gn | +0.003 |
Neg logit contributions | |
hing | -0.007 |
aw | -0.007 |
ong | -0.006 |
eping | -0.006 |
ming | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
seek | +0.010 |
onna | +0.010 |
allowance | +0.009 |
One | +0.009 |
moment | +0.009 |
Neg logit contributions | |
hing | -0.021 |
aw | -0.020 |
ding | -0.019 |
eping | -0.019 |
ming | -0.019 |
Token | Thank |
Token ID | 10449 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
seek | +0.015 |
One | +0.013 |
onna | +0.013 |
allowance | +0.013 |
ifi | +0.012 |
Neg logit contributions | |
hing | -0.017 |
aw | -0.016 |
ming | -0.015 |
ding | -0.015 |
flashing | -0.014 |
Token | you |
Token ID | 345 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
hing | +0.026 |
aw | +0.024 |
ming | +0.023 |
ding | +0.022 |
eping | +0.021 |
Neg logit contributions | |
seek | -0.025 |
One | -0.022 |
One | -0.021 |
onna | -0.021 |
moral | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
seek | +0.030 |
One | +0.025 |
One | +0.024 |
onna | +0.024 |
ro | +0.024 |
Neg logit contributions | |
hing | -0.034 |
aw | -0.033 |
ming | -0.032 |
ding | -0.031 |
ong | -0.031 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
hing | +0.038 |
aw | +0.035 |
ming | +0.034 |
ding | +0.034 |
ong | +0.033 |
Neg logit contributions | |
seek | -0.033 |
One | -0.029 |
One | -0.029 |
moment | -0.027 |
onna | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
hing | +0.082 |
ming | +0.077 |
aw | +0.076 |
ning | +0.072 |
ding | +0.071 |
Neg logit contributions | |
seek | -0.068 |
One | -0.059 |
One | -0.059 |
moral | -0.055 |
onna | -0.054 |
Token | his |
Token ID | 465 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
seek | +0.022 |
ider | +0.020 |
One | +0.019 |
moment | +0.018 |
ro | +0.018 |
Neg logit contributions | |
hing | -0.023 |
ming | -0.021 |
ding | -0.020 |
flashing | -0.020 |
ning | -0.020 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
hing | +0.035 |
ming | +0.033 |
aw | +0.032 |
ning | +0.031 |
eping | +0.031 |
Neg logit contributions | |
seek | -0.041 |
One | -0.038 |
One | -0.038 |
onna | -0.036 |
moment | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
hing | +0.007 |
ming | +0.006 |
aw | +0.006 |
flashing | +0.006 |
ding | +0.006 |
Neg logit contributions | |
seek | -0.004 |
One | -0.003 |
One | -0.003 |
onna | -0.003 |
ifi | -0.003 |
Token | thanked |
Token ID | 26280 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
hing | +0.057 |
ming | +0.053 |
aw | +0.052 |
eping | +0.051 |
flashing | +0.050 |
Neg logit contributions | |
seek | -0.029 |
One | -0.024 |
One | -0.023 |
onna | -0.021 |
moral | -0.021 |
Token | them |
Token ID | 606 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
hing | +0.039 |
ming | +0.033 |
aw | +0.030 |
ding | +0.030 |
flashing | +0.029 |
Neg logit contributions | |
seek | -0.064 |
ider | -0.058 |
onna | -0.058 |
One | -0.056 |
ib | -0.054 |
Token | for |
Token ID | 329 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
hing | +0.041 |
ming | +0.039 |
aw | +0.034 |
ong | +0.033 |
ning | +0.033 |
Neg logit contributions | |
seek | -0.059 |
One | -0.051 |
One | -0.050 |
ifi | -0.050 |
onna | -0.049 |
Token | coming |
Token ID | 2406 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
hing | +0.118 |
ming | +0.107 |
aw | +0.107 |
ong | +0.101 |
eping | +0.099 |
Neg logit contributions | |
seek | -0.103 |
One | -0.089 |
One | -0.089 |
moral | -0.084 |
moment | -0.082 |
Token | to |
Token ID | 284 |
Feature activation | -7.65e-02 |
Pos logit contributions | |
out | +0.061 |
hing | +0.058 |
ming | +0.054 |
flashing | +0.052 |
eping | +0.050 |
Neg logit contributions | |
seek | -0.103 |
One | -0.101 |
ifi | -0.095 |
One | -0.094 |
Yesterday | -0.094 |
Token | his |
Token ID | 465 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
hing | +0.004 |
ming | +0.004 |
aw | +0.004 |
flashing | +0.004 |
eping | +0.004 |
Neg logit contributions | |
seek | -0.003 |
One | -0.003 |
One | -0.003 |
onna | -0.003 |
moment | -0.003 |
Token | tea |
Token ID | 8887 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
hing | +0.044 |
ming | +0.041 |
aw | +0.040 |
flashing | +0.037 |
ning | +0.037 |
Neg logit contributions | |
seek | -0.059 |
One | -0.054 |
One | -0.054 |
onna | -0.052 |
ifi | -0.050 |
Token | party |
Token ID | 2151 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
seek | +0.105 |
One | +0.095 |
One | +0.093 |
onna | +0.087 |
moral | +0.087 |
Neg logit contributions | |
hing | -0.088 |
ming | -0.078 |
aw | -0.076 |
eping | -0.074 |
flashing | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
seek | +0.054 |
One | +0.044 |
One | +0.043 |
onna | +0.037 |
moral | +0.037 |
Neg logit contributions | |
hing | -0.143 |
ming | -0.134 |
aw | -0.132 |
flashing | -0.127 |
eping | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
aw | +0.008 |
hing | +0.008 |
ming | +0.008 |
ding | +0.008 |
flashing | +0.008 |
Neg logit contributions | |
seek | -0.005 |
moral | -0.004 |
ider | -0.004 |
One | -0.004 |
moment | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
seek | +0.000 |
ider | +0.000 |
ib | +0.000 |
allowance | +0.000 |
ro | +0.000 |
Neg logit contributions | |
hing | -0.000 |
aw | -0.000 |
ming | -0.000 |
eping | -0.000 |
ay | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
seek | +0.007 |
ib | +0.007 |
One | +0.007 |
onna | +0.007 |
moment | +0.006 |
Neg logit contributions | |
hing | -0.013 |
aw | -0.012 |
ming | -0.012 |
eping | -0.011 |
ding | -0.011 |
Token | vet |
Token ID | 20202 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
seek | +0.053 |
onna | +0.050 |
One | +0.047 |
ib | +0.045 |
D | +0.044 |
Neg logit contributions | |
hing | -0.050 |
aw | -0.049 |
ming | -0.048 |
ambulance | -0.047 |
emergency | -0.046 |
Token | said |
Token ID | 531 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
seek | +0.120 |
One | +0.108 |
One | +0.106 |
onna | +0.097 |
moral | +0.095 |
Neg logit contributions | |
hing | -0.150 |
ming | -0.142 |
aw | -0.139 |
eping | -0.131 |
ding | -0.129 |
Token | that |
Token ID | 326 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
hing | +0.033 |
ming | +0.031 |
aw | +0.031 |
ding | +0.029 |
flashing | +0.029 |
Neg logit contributions | |
seek | -0.027 |
One | -0.023 |
One | -0.023 |
moral | -0.021 |
moment | -0.021 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
hing | +0.056 |
ming | +0.053 |
aw | +0.051 |
flashing | +0.050 |
ning | +0.050 |
Neg logit contributions | |
seek | -0.033 |
One | -0.028 |
One | -0.028 |
onna | -0.026 |
moral | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
seek | +0.050 |
One | +0.044 |
One | +0.042 |
onna | +0.040 |
moral | +0.039 |
Neg logit contributions | |
hing | -0.071 |
ming | -0.067 |
aw | -0.067 |
eping | -0.062 |
ning | -0.061 |
Token | fine |
Token ID | 3734 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
hing | +0.007 |
ming | +0.007 |
eping | +0.007 |
aw | +0.007 |
flashing | +0.007 |
Neg logit contributions | |
seek | -0.007 |
One | -0.006 |
One | -0.006 |
onna | -0.006 |
ib | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
seek | +0.006 |
One | +0.005 |
One | +0.005 |
onna | +0.004 |
moral | +0.004 |
Neg logit contributions | |
hing | -0.011 |
ming | -0.010 |
aw | -0.010 |
eping | -0.010 |
flashing | -0.010 |
Token | Max |
Token ID | 5436 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
hing | +0.041 |
aw | +0.038 |
eping | +0.037 |
ming | +0.036 |
ong | +0.036 |
Neg logit contributions | |
seek | -0.025 |
One | -0.022 |
One | -0.021 |
moment | -0.019 |
moral | -0.019 |
Token | would |
Token ID | 561 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
hing | +0.028 |
ming | +0.025 |
aw | +0.025 |
eping | +0.024 |
flashing | +0.024 |
Neg logit contributions | |
seek | -0.017 |
One | -0.014 |
One | -0.014 |
onna | -0.013 |
moral | -0.013 |
Token | always |
Token ID | 1464 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
hing | +0.039 |
ming | +0.036 |
aw | +0.036 |
eping | +0.035 |
flashing | +0.035 |
Neg logit contributions | |
seek | -0.026 |
One | -0.023 |
One | -0.022 |
onna | -0.020 |
moral | -0.020 |
Token | w |
Token ID | 266 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
hing | +0.031 |
aw | +0.028 |
ming | +0.028 |
ong | +0.027 |
flashing | +0.027 |
Neg logit contributions | |
seek | -0.017 |
One | -0.014 |
One | -0.014 |
moment | -0.013 |
moral | -0.012 |
Token | ag |
Token ID | 363 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
flashing | +0.099 |
hing | +0.099 |
ding | +0.098 |
ning | +0.095 |
ming | +0.091 |
Neg logit contributions | |
seek | -0.136 |
One | -0.130 |
One | -0.127 |
ib | -0.124 |
moral | -0.123 |
Token | his |
Token ID | 465 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
hing | +0.086 |
ming | +0.079 |
aw | +0.078 |
eping | +0.076 |
flashing | +0.075 |
Neg logit contributions | |
seek | -0.052 |
One | -0.045 |
One | -0.044 |
onna | -0.040 |
moral | -0.039 |
Token | tail |
Token ID | 7894 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
hing | +0.051 |
ming | +0.047 |
aw | +0.046 |
eping | +0.045 |
flashing | +0.045 |
Neg logit contributions | |
seek | -0.037 |
One | -0.032 |
One | -0.032 |
onna | -0.030 |
moral | -0.029 |
Token | when |
Token ID | 618 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
hing | +0.037 |
aw | +0.034 |
ming | +0.034 |
eping | +0.034 |
ding | +0.034 |
Neg logit contributions | |
seek | -0.016 |
One | -0.013 |
One | -0.013 |
moment | -0.011 |
moral | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
hing | +0.084 |
ming | +0.080 |
aw | +0.077 |
flashing | +0.077 |
ding | +0.076 |
Neg logit contributions | |
seek | -0.030 |
One | -0.024 |
One | -0.024 |
onna | -0.021 |
ifi | -0.021 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
hing | +0.122 |
ming | +0.111 |
aw | +0.108 |
flashing | +0.107 |
ding | +0.107 |
Neg logit contributions | |
seek | -0.082 |
One | -0.072 |
One | -0.070 |
moral | -0.063 |
onna | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
hing | +0.113 |
eping | +0.099 |
ding | +0.099 |
ming | +0.098 |
ong | +0.098 |
Neg logit contributions | |
seek | -0.039 |
Lily | -0.039 |
One | -0.038 |
D | -0.035 |
One | -0.031 |
Token | what |
Token ID | 644 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
hing | +0.054 |
ming | +0.051 |
channels | +0.050 |
eping | +0.048 |
ning | +0.048 |
Neg logit contributions | |
seek | -0.037 |
Lily | -0.037 |
Sara | -0.034 |
D | -0.033 |
first | -0.032 |
Token | are |
Token ID | 389 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
hing | +0.007 |
ming | +0.007 |
ning | +0.006 |
flashing | +0.006 |
channels | +0.006 |
Neg logit contributions | |
seek | -0.007 |
One | -0.006 |
One | -0.006 |
Lily | -0.006 |
moral | -0.006 |
Token | you |
Token ID | 345 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
hing | +0.148 |
ming | +0.134 |
aw | +0.126 |
eping | +0.125 |
flashing | +0.124 |
Neg logit contributions | |
seek | -0.086 |
One | -0.075 |
One | -0.075 |
moral | -0.067 |
Lily | -0.066 |
Token | doing |
Token ID | 1804 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
seek | +0.100 |
first | +0.085 |
One | +0.085 |
next | +0.084 |
moral | +0.082 |
Neg logit contributions | |
hing | -0.112 |
aw | -0.099 |
ming | -0.099 |
channels | -0.096 |
flashing | -0.095 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
seek | +0.029 |
next | +0.021 |
One | +0.021 |
One | +0.021 |
Lily | +0.020 |
Neg logit contributions | |
hing | -0.054 |
ming | -0.049 |
aw | -0.048 |
flashing | -0.048 |
channels | -0.048 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
seek | +0.049 |
One | +0.040 |
onna | +0.039 |
moment | +0.038 |
One | +0.038 |
Neg logit contributions | |
hing | -0.068 |
aw | -0.065 |
flashing | -0.063 |
ding | -0.063 |
ming | -0.063 |
Token | said |
Token ID | 531 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
hing | +0.146 |
ming | +0.133 |
aw | +0.132 |
flashing | +0.128 |
ong | +0.127 |
Neg logit contributions | |
seek | -0.064 |
One | -0.056 |
One | -0.054 |
Lily | -0.046 |
next | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
hing | +0.144 |
ming | +0.135 |
aw | +0.132 |
flashing | +0.128 |
eping | +0.127 |
Neg logit contributions | |
seek | -0.082 |
One | -0.070 |
One | -0.069 |
moral | -0.062 |
onna | -0.061 |
Token | opening |
Token ID | 4756 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
hing | +0.028 |
ming | +0.025 |
aw | +0.025 |
eping | +0.024 |
flashing | +0.024 |
Neg logit contributions | |
seek | -0.027 |
One | -0.024 |
One | -0.024 |
onna | -0.022 |
moral | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
hing | +0.049 |
ming | +0.046 |
aw | +0.045 |
flashing | +0.044 |
ding | +0.044 |
Neg logit contributions | |
seek | -0.034 |
One | -0.028 |
One | -0.028 |
onna | -0.026 |
moral | -0.025 |
Token | door |
Token ID | 3420 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
hing | +0.025 |
ming | +0.022 |
aw | +0.021 |
eping | +0.020 |
flashing | +0.020 |
Neg logit contributions | |
seek | -0.031 |
One | -0.028 |
One | -0.027 |
onna | -0.026 |
moral | -0.026 |
Token | clearing |
Token ID | 17304 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
hing | +0.031 |
ming | +0.028 |
aw | +0.027 |
eping | +0.026 |
flashing | +0.026 |
Neg logit contributions | |
seek | -0.023 |
One | -0.020 |
One | -0.020 |
moment | -0.018 |
onna | -0.018 |
Token | where |
Token ID | 810 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
hing | +0.021 |
aw | +0.021 |
flashing | +0.020 |
ming | +0.020 |
eping | +0.020 |
Neg logit contributions | |
seek | -0.012 |
One | -0.011 |
One | -0.011 |
onna | -0.010 |
moral | -0.010 |
Token | there |
Token ID | 612 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
seek | +0.030 |
One | +0.026 |
One | +0.025 |
onna | +0.025 |
ider | +0.023 |
Neg logit contributions | |
hing | -0.052 |
aw | -0.050 |
ming | -0.048 |
flashing | -0.048 |
ding | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
seek | +0.087 |
One | +0.076 |
One | +0.075 |
onna | +0.074 |
moral | +0.071 |
Neg logit contributions | |
hing | -0.090 |
aw | -0.082 |
ming | -0.081 |
flashing | -0.076 |
ning | -0.074 |
Token | a |
Token ID | 257 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
hing | +0.033 |
aw | +0.031 |
ming | +0.031 |
flashing | +0.030 |
eping | +0.029 |
Neg logit contributions | |
seek | -0.019 |
One | -0.016 |
One | -0.015 |
onna | -0.015 |
moment | -0.014 |
Token | big |
Token ID | 1263 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
seek | +0.023 |
One | +0.019 |
One | +0.019 |
moral | +0.018 |
moment | +0.018 |
Neg logit contributions | |
hing | -0.032 |
ming | -0.030 |
aw | -0.029 |
eping | -0.028 |
channels | -0.027 |
Token | rock |
Token ID | 3881 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
hing | +0.148 |
ming | +0.137 |
aw | +0.133 |
eping | +0.130 |
flashing | +0.127 |
Neg logit contributions | |
seek | -0.089 |
One | -0.076 |
One | -0.072 |
moment | -0.067 |
onna | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
seek | +0.019 |
One | +0.016 |
One | +0.016 |
moral | +0.014 |
onna | +0.014 |
Neg logit contributions | |
hing | -0.041 |
ming | -0.038 |
aw | -0.037 |
flashing | -0.036 |
eping | -0.036 |
Token | On |
Token ID | 1550 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
seek | +0.023 |
moral | +0.019 |
One | +0.019 |
ifi | +0.018 |
moment | +0.017 |
Neg logit contributions | |
aw | -0.026 |
ding | -0.025 |
ming | -0.025 |
hing | -0.024 |
flashing | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
seek | +0.042 |
ib | +0.039 |
onna | +0.038 |
emo | +0.038 |
ider | +0.038 |
Neg logit contributions | |
hing | -0.037 |
flashing | -0.036 |
aw | -0.035 |
ming | -0.035 |
ning | -0.034 |
Token | rock |
Token ID | 3881 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
hing | +0.076 |
ming | +0.070 |
aw | +0.068 |
eping | +0.066 |
flashing | +0.065 |
Neg logit contributions | |
seek | -0.058 |
One | -0.051 |
One | -0.050 |
moral | -0.046 |
onna | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
seek | +0.010 |
ider | +0.008 |
ro | +0.008 |
ib | +0.008 |
ifi | +0.007 |
Neg logit contributions | |
aw | -0.013 |
hing | -0.012 |
flashing | -0.011 |
eping | -0.011 |
ong | -0.011 |
Token | They |
Token ID | 2990 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
onna | +0.014 |
seek | +0.012 |
ib | +0.012 |
One | +0.012 |
allowance | +0.011 |
Neg logit contributions | |
aw | -0.024 |
hing | -0.022 |
eping | -0.021 |
ming | -0.021 |
ding | -0.021 |
Token | told |
Token ID | 1297 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
seek | +0.002 |
One | +0.001 |
One | +0.001 |
onna | +0.001 |
moment | +0.001 |
Neg logit contributions | |
hing | -0.002 |
ming | -0.002 |
aw | -0.002 |
eping | -0.002 |
flashing | -0.002 |
Token | grandma |
Token ID | 49890 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
seek | +0.032 |
One | +0.028 |
One | +0.028 |
onna | +0.026 |
moral | +0.025 |
Neg logit contributions | |
hing | -0.043 |
ming | -0.039 |
aw | -0.038 |
eping | -0.037 |
flashing | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
seek | +0.006 |
One | +0.005 |
One | +0.005 |
onna | +0.005 |
ro | +0.005 |
Neg logit contributions | |
hing | -0.005 |
ming | -0.004 |
aw | -0.004 |
flashing | -0.004 |
ning | -0.004 |
Token | grand |
Token ID | 4490 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
hing | +0.029 |
aw | +0.025 |
ming | +0.025 |
ong | +0.025 |
eping | +0.024 |
Neg logit contributions | |
seek | -0.014 |
Lily | -0.013 |
One | -0.012 |
D | -0.011 |
moral | -0.011 |
Token | pa |
Token ID | 8957 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
hing | +0.109 |
ming | +0.088 |
aw | +0.085 |
eping | +0.076 |
flashing | +0.075 |
Neg logit contributions | |
seek | -0.319 |
One | -0.294 |
One | -0.292 |
onna | -0.281 |
moral | -0.277 |
Token | what |
Token ID | 644 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
hing | +0.153 |
ming | +0.138 |
aw | +0.136 |
eping | +0.131 |
flashing | +0.130 |
Neg logit contributions | |
seek | -0.130 |
One | -0.116 |
One | -0.113 |
moral | -0.106 |
onna | -0.105 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
hing | +0.005 |
ming | +0.004 |
aw | +0.004 |
flashing | +0.004 |
eping | +0.004 |
Neg logit contributions | |
seek | -0.005 |
One | -0.005 |
One | -0.005 |
onna | -0.004 |
moral | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
hing | +0.069 |
aw | +0.067 |
ming | +0.067 |
ding | +0.063 |
ning | +0.063 |
Neg logit contributions | |
seek | -0.051 |
ifi | -0.044 |
onna | -0.041 |
One | -0.041 |
rog | -0.040 |
Token | Grand |
Token ID | 5675 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
hing | +0.015 |
ming | +0.015 |
aw | +0.014 |
flashing | +0.014 |
ding | +0.014 |
Neg logit contributions | |
seek | -0.009 |
One | -0.008 |
One | -0.007 |
onna | -0.007 |
moment | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
hing | +0.119 |
ming | +0.115 |
ong | +0.110 |
aw | +0.109 |
ding | +0.109 |
Neg logit contributions | |
seek | -0.081 |
One | -0.073 |
ifi | -0.065 |
One | -0.063 |
moral | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
aw | +0.036 |
hing | +0.036 |
flashing | +0.035 |
ding | +0.034 |
ming | +0.033 |
Neg logit contributions | |
seek | -0.026 |
ifi | -0.020 |
allowance | -0.019 |
One | -0.019 |
onna | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
aw | +0.013 |
hing | +0.012 |
ay | +0.012 |
ding | +0.011 |
eping | +0.011 |
Neg logit contributions | |
seek | -0.012 |
ider | -0.010 |
allowance | -0.009 |
ifi | -0.009 |
ro | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
aw | +0.001 |
hing | +0.001 |
ding | +0.001 |
eping | +0.001 |
ming | +0.001 |
Neg logit contributions | |
allowance | -0.001 |
onna | -0.001 |
Nancy | -0.000 |
One | -0.000 |
seek | -0.000 |
Token | Y |
Token ID | 56 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
seek | +0.007 |
One | +0.007 |
onna | +0.006 |
One | +0.006 |
ifi | +0.006 |
Neg logit contributions | |
hing | -0.012 |
ming | -0.010 |
aw | -0.010 |
ding | -0.010 |
flashing | -0.010 |
Token | ay |
Token ID | 323 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
One | +0.047 |
One | +0.045 |
" | +0.043 |
seek | +0.042 |
next | +0.042 |
Neg logit contributions | |
hing | -0.022 |
channels | -0.020 |
flashing | -0.018 |
eping | -0.018 |
ming | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
hing | +0.284 |
channels | +0.262 |
ming | +0.260 |
flashing | +0.253 |
aw | +0.251 |
Neg logit contributions | |
seek | -0.162 |
One | -0.135 |
One | -0.129 |
" | -0.122 |
moment | -0.116 |
Token | Sam |
Token ID | 3409 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
seek | +0.016 |
One | +0.014 |
One | +0.013 |
onna | +0.012 |
moral | +0.012 |
Neg logit contributions | |
hing | -0.030 |
ming | -0.028 |
aw | -0.028 |
eping | -0.027 |
flashing | -0.027 |
Token | ! |
Token ID | 0 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
seek | +0.001 |
One | +0.001 |
One | +0.001 |
onna | +0.001 |
moment | +0.001 |
Neg logit contributions | |
hing | -0.002 |
ming | -0.002 |
aw | -0.002 |
flashing | -0.002 |
eping | -0.002 |
Token | We |
Token ID | 775 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
hing | +0.124 |
aw | +0.114 |
ding | +0.113 |
ming | +0.113 |
flashing | +0.108 |
Neg logit contributions | |
seek | -0.092 |
One | -0.079 |
moral | -0.073 |
ifi | -0.072 |
One | -0.071 |
Token | did |
Token ID | 750 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
hing | +0.004 |
ming | +0.004 |
ning | +0.004 |
aw | +0.004 |
flashing | +0.003 |
Neg logit contributions | |
seek | -0.003 |
One | -0.002 |
One | -0.002 |
moral | -0.002 |
moment | -0.002 |
Token | puff |
Token ID | 33679 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
seek | +0.002 |
One | +0.002 |
One | +0.001 |
onna | +0.001 |
moment | +0.001 |
Neg logit contributions | |
hing | -0.003 |
aw | -0.003 |
ming | -0.003 |
eping | -0.002 |
ding | -0.002 |
Token | ing |
Token ID | 278 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
hing | +0.084 |
channels | +0.072 |
cient | +0.070 |
theatre | +0.070 |
flashing | +0.070 |
Neg logit contributions | |
seek | -0.151 |
One | -0.143 |
ro | -0.143 |
next | -0.141 |
One | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
hing | +0.134 |
aw | +0.121 |
ming | +0.121 |
eping | +0.117 |
ong | +0.115 |
Neg logit contributions | |
seek | -0.086 |
One | -0.075 |
moment | -0.071 |
One | -0.070 |
onna | -0.068 |
Token | blowing |
Token ID | 19280 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
seek | +0.008 |
One | +0.007 |
moment | +0.007 |
One | +0.007 |
onna | +0.007 |
Neg logit contributions | |
hing | -0.010 |
aw | -0.009 |
ong | -0.008 |
ming | -0.008 |
eping | -0.008 |
Token | smoke |
Token ID | 7523 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
hing | +0.050 |
ming | +0.046 |
aw | +0.045 |
eping | +0.044 |
flashing | +0.044 |
Neg logit contributions | |
seek | -0.023 |
One | -0.020 |
One | -0.019 |
moment | -0.018 |
Lily | -0.017 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
hing | +0.350 |
aw | +0.335 |
arre | +0.335 |
cient | +0.334 |
eping | +0.332 |
Neg logit contributions | |
seek | -0.058 |
before | -0.054 |
next | -0.053 |
One | -0.048 |
ro | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
hing | +0.349 |
ming | +0.326 |
aw | +0.322 |
eping | +0.313 |
flashing | +0.311 |
Neg logit contributions | |
seek | -0.122 |
One | -0.096 |
One | -0.092 |
onna | -0.080 |
moment | -0.077 |
Token | The |
Token ID | 383 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
aw | +0.024 |
hing | +0.024 |
ming | +0.023 |
ding | +0.022 |
channels | +0.022 |
Neg logit contributions | |
seek | -0.018 |
ifi | -0.014 |
moral | -0.013 |
ider | -0.013 |
moment | -0.013 |
Token | old |
Token ID | 1468 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
seek | +0.053 |
One | +0.046 |
One | +0.045 |
onna | +0.042 |
moral | +0.041 |
Neg logit contributions | |
hing | -0.071 |
ming | -0.065 |
aw | -0.064 |
eping | -0.062 |
flashing | -0.062 |
Token | man |
Token ID | 582 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
seek | +0.035 |
One | +0.034 |
One | +0.034 |
onna | +0.032 |
ifi | +0.031 |
Neg logit contributions | |
hing | -0.033 |
aw | -0.033 |
ming | -0.033 |
flashing | -0.031 |
eping | -0.031 |
Token | got |
Token ID | 1392 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
hing | +0.023 |
ming | +0.021 |
aw | +0.021 |
flashing | +0.021 |
ong | +0.021 |
Neg logit contributions | |
seek | -0.012 |
One | -0.010 |
One | -0.010 |
moral | -0.009 |
moment | -0.009 |
Token | little |
Token ID | 1310 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
seek | +0.058 |
onna | +0.056 |
One | +0.054 |
One | +0.052 |
ifi | +0.050 |
Neg logit contributions | |
hing | -0.077 |
ding | -0.074 |
opera | -0.073 |
ming | -0.071 |
aw | -0.070 |
Token | girl |
Token ID | 2576 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
hing | +0.011 |
ding | +0.010 |
aw | +0.010 |
opera | +0.010 |
ming | +0.010 |
Neg logit contributions | |
onna | -0.014 |
seek | -0.014 |
One | -0.014 |
One | -0.013 |
orse | -0.013 |
Token | smiled |
Token ID | 13541 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
hing | +0.003 |
ming | +0.003 |
aw | +0.003 |
eping | +0.002 |
ding | +0.002 |
Neg logit contributions | |
seek | -0.002 |
One | -0.002 |
One | -0.002 |
onna | -0.002 |
ifi | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
seek | +0.034 |
One | +0.029 |
One | +0.028 |
onna | +0.025 |
moral | +0.025 |
Neg logit contributions | |
hing | -0.063 |
ming | -0.058 |
aw | -0.057 |
eping | -0.055 |
flashing | -0.055 |
Token | reached |
Token ID | 4251 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
hing | +0.000 |
ming | +0.000 |
aw | +0.000 |
eping | +0.000 |
flashing | +0.000 |
Neg logit contributions | |
seek | -0.000 |
One | -0.000 |
One | -0.000 |
moment | -0.000 |
onna | -0.000 |
Token | out |
Token ID | 503 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
hing | +0.016 |
aw | +0.014 |
ming | +0.014 |
eping | +0.013 |
flashing | +0.013 |
Neg logit contributions | |
seek | -0.021 |
One | -0.019 |
One | -0.019 |
onna | -0.018 |
moment | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
flashing | +0.203 |
hing | +0.201 |
ming | +0.197 |
out | +0.187 |
ding | +0.180 |
Neg logit contributions | |
seek | -0.231 |
emo | -0.205 |
One | -0.196 |
ro | -0.194 |
ifi | -0.194 |
Token | hand |
Token ID | 1021 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
hing | +0.040 |
ming | +0.035 |
aw | +0.035 |
eping | +0.034 |
ding | +0.033 |
Neg logit contributions | |
seek | -0.032 |
One | -0.028 |
One | -0.027 |
moment | -0.026 |
moral | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
hing | +0.144 |
ming | +0.137 |
aw | +0.133 |
flashing | +0.130 |
ning | +0.129 |
Neg logit contributions | |
seek | -0.069 |
One | -0.059 |
One | -0.056 |
moral | -0.054 |
onna | -0.050 |
Token | She |
Token ID | 1375 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
hing | +0.000 |
ming | +0.000 |
aw | +0.000 |
ding | +0.000 |
flashing | +0.000 |
Neg logit contributions | |
seek | -0.000 |
One | -0.000 |
ifi | -0.000 |
moral | -0.000 |
moment | -0.000 |
Token | held |
Token ID | 2714 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
seek | +0.010 |
One | +0.009 |
One | +0.009 |
onna | +0.008 |
moral | +0.008 |
Neg logit contributions | |
hing | -0.016 |
ming | -0.015 |
aw | -0.015 |
eping | -0.014 |
flashing | -0.014 |
Token | now |
Token ID | 783 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
seek | +0.035 |
One | +0.032 |
One | +0.032 |
onna | +0.029 |
moral | +0.029 |
Neg logit contributions | |
hing | -0.035 |
ming | -0.032 |
aw | -0.032 |
eping | -0.030 |
ning | -0.030 |
Token | or |
Token ID | 393 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
seek | +0.069 |
One | +0.060 |
One | +0.059 |
moral | +0.054 |
onna | +0.053 |
Neg logit contributions | |
hing | -0.109 |
ming | -0.101 |
aw | -0.099 |
flashing | -0.095 |
eping | -0.095 |
Token | you |
Token ID | 345 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
seek | +0.041 |
One | +0.034 |
One | +0.033 |
onna | +0.030 |
moral | +0.030 |
Neg logit contributions | |
hing | -0.076 |
ming | -0.070 |
aw | -0.069 |
eping | -0.067 |
flashing | -0.066 |
Token | 're |
Token ID | 821 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
seek | +0.015 |
One | +0.014 |
One | +0.013 |
onna | +0.012 |
moral | +0.012 |
Neg logit contributions | |
hing | -0.016 |
ming | -0.015 |
aw | -0.014 |
eping | -0.014 |
flashing | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
hing | +0.126 |
ming | +0.114 |
aw | +0.112 |
flashing | +0.106 |
eping | +0.104 |
Neg logit contributions | |
seek | -0.113 |
One | -0.098 |
One | -0.096 |
moral | -0.091 |
onna | -0.090 |
Token | big |
Token ID | 1263 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
seek | +0.045 |
One | +0.040 |
One | +0.040 |
moral | +0.037 |
onna | +0.037 |
Neg logit contributions | |
hing | -0.042 |
ming | -0.037 |
aw | -0.037 |
eping | -0.035 |
ong | -0.034 |
Token | trouble |
Token ID | 5876 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
hing | +0.237 |
ming | +0.208 |
aw | +0.205 |
ong | +0.203 |
eping | +0.198 |
Neg logit contributions | |
seek | -0.209 |
One | -0.198 |
One | -0.177 |
moment | -0.175 |
moral | -0.172 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
hing | +0.047 |
ming | +0.044 |
aw | +0.043 |
eping | +0.042 |
flashing | +0.042 |
Neg logit contributions | |
seek | -0.026 |
One | -0.021 |
One | -0.021 |
onna | -0.019 |
moment | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
seek | +0.006 |
One | +0.003 |
onna | +0.003 |
ro | +0.003 |
One | +0.003 |
Neg logit contributions | |
hing | -0.015 |
aw | -0.015 |
ming | -0.014 |
ding | -0.014 |
ong | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
hing | +0.059 |
aw | +0.058 |
ming | +0.054 |
ding | +0.053 |
ong | +0.053 |
Neg logit contributions | |
seek | -0.023 |
One | -0.015 |
ro | -0.014 |
One | -0.014 |
moment | -0.013 |
Token | Jim |
Token ID | 18050 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
hing | +0.024 |
aw | +0.023 |
ming | +0.022 |
ding | +0.021 |
eping | +0.021 |
Neg logit contributions | |
seek | -0.018 |
One | -0.016 |
onna | -0.015 |
One | -0.015 |
D | -0.014 |