TOP ACTIVATIONS
MAX = 0.518

. They heard the s iren and saw the light of
. They hear a s iren and see another fire truck
He shows her the s iren , the light and the
. It was a s iren . It was another cop
. It was a s iren . They saw a big
red light and a s iren . It came to the
, he heard a s iren . It was the zo
They turn on the s iren and the lights . They
the hose , the s iren , the ladder and the
police car had a s iren and a light . It
it heard a loud s iren . It saw a big
. It has a s iren that goes woo - w
It was an emergency s iren . Let 's get to
truck has a loud s iren and a long ladder .
walking , a loud s iren suddenly came on . Everyone
It had a loud s iren and a long hose .
ked . The ambulance s iren w ailed . The driver
to speak when a s iren sounded , making both of
It was an emergency s iren . " Mom
they heard a loud s iren outside . They looked out

MIN ACTIVATIONS
MIN = -0.558

He found some big rad ishes in a garden and ate
Benny happily ate his rad ishes . From that
ch ir ping and gather shells nearby ." S
the biggest and best rad ishes . Every day he took
Why do you like rad ishes ? They 're not very
foods and discovered many new favorites . He learned that it
were shiny rocks and pretty shells . Fin was very happy
where everyone shared their rad ishes . <|endoftext|> Once upon a
saw fish and crabs and shells . They also saw birds
sand , and deep blue seas . One
her finger and the rad ishes . She said , "
always had plenty of rad ishes to eat . The end
hats and went to find shells by the water . They
. The mild minerals loved to have fun together
, a bucket and some shells . They want to create
The girl kept searching for minerals . She went to the
and the sand and the shells . Maybe we will see
for collecting pretty rocks and shells . <|endoftext|> Once upon a
. They collect rocks , shells , leaves , and stickers
ison couldn 't believe her luck and started to think of

INTERVAL 0.249 - 0.518
CONTAINS 1.741%

. <|endoftext|> Once upon a time , there was a little
decided to take a taste of the pie and it was
flash . Then , another boom and another flash . The
. <|endoftext|> Once upon a time , there was a little
play . They do not fight over the banana . <|endoftext|>

INTERVAL -0.020 - 0.249
CONTAINS 59.808%

came . The dog was big and loud . It bark
his room . He ran around until he was tired ,
. He was safe and happy now . <|endoftext|> Once upon
They made life happy and beautiful . <|endoftext|> Anna
said the freezer was too cold for anyone to sleep in

INTERVAL -0.289 - -0.020
CONTAINS 37.963%

and cars . One day , Anna has a new doll
not bad . The eggs are not broken , they are
Two curious little children , called Max and Jenny ,
under a big tree with lots of shade to protect him
Joe hugged his dad tightly , and he was so happy

INTERVAL -0.558 - -0.289
CONTAINS 0.488%

sw am to the oy ster and spoke softly .
time there was an oy ster that lived at the bottom
and slowly walk away ." So , Lily did just that
, " What is your favorite color ?" The child
. They will be angry if we touch it ." But
Token.
Token ID13
Feature activation+4.10e-02

Pos logit contributions
iren+0.011
 crash+0.010
storm+0.010
 aids+0.010
 knock+0.010
Neg logit contributions
ishes-0.009
 minerals-0.008
 favorites-0.008
 seas-0.008
 shells-0.008
Token They
Token ID1119
Feature activation+5.56e-02

Pos logit contributions
iren+0.056
 crash+0.053
storm+0.050
 aids+0.049
 knock+0.048
Neg logit contributions
ishes-0.087
 seas-0.083
 shells-0.080
 seaw-0.080
 minerals-0.079
Token heard
Token ID2982
Feature activation+5.76e-02

Pos logit contributions
 crash+0.086
iren+0.086
storm+0.081
 knock+0.081
 collapsed+0.074
Neg logit contributions
ishes-0.101
 seas-0.095
 favorites-0.095
 minerals-0.093
sters-0.090
Token the
Token ID262
Feature activation+7.85e-02

Pos logit contributions
iren+0.112
storm+0.107
 crash+0.103
aned+0.099
 earthquake+0.098
Neg logit contributions
ishes-0.083
 shells-0.082
 seas-0.082
 minerals-0.081
 dreams-0.080
Token s
Token ID264
Feature activation+3.06e-01

Pos logit contributions
storm+0.107
iren+0.106
 aids+0.100
anne+0.099
aned+0.099
Neg logit contributions
 ones-0.142
 luck-0.139
 dreams-0.138
ishes-0.138
 prett-0.134
Tokeniren
Token ID24080
Feature activation+5.18e-01

Pos logit contributions
storm+0.121
 crash+0.114
 earthquake+0.083
 tornado+0.079
 knock+0.072
Neg logit contributions
ishes-0.906
sters-0.854
 seas-0.836
minded-0.834
 favorites-0.826
Token and
Token ID290
Feature activation+4.17e-02

Pos logit contributions
iren+0.988
storm+0.956
 earthquake+0.930
ggy+0.907
 aids+0.900
Neg logit contributions
ishes-0.678
 dreams-0.671
 luck-0.650
 ones-0.644
 shells-0.613
Token saw
Token ID2497
Feature activation-1.90e-02

Pos logit contributions
iren+0.072
storm+0.067
 crash+0.066
 earthquake+0.062
 aids+0.062
Neg logit contributions
ishes-0.073
 shells-0.069
 minerals-0.069
 seas-0.069
 favorites-0.067
Token the
Token ID262
Feature activation+8.00e-02

Pos logit contributions
ishes+0.030
 shells+0.028
 seas+0.028
 minerals+0.028
 favorites+0.028
Neg logit contributions
iren-0.036
storm-0.034
 crash-0.034
 knock-0.032
 earthquake-0.031
Token light
Token ID1657
Feature activation+1.68e-01

Pos logit contributions
iren+0.119
aned+0.115
anne+0.113
storm+0.112
 aids+0.111
Neg logit contributions
 ones-0.147
ishes-0.138
 favorites-0.137
 prett-0.136
 luck-0.136
Token of
Token ID286
Feature activation+2.94e-01

Pos logit contributions
iren+0.314
aned+0.307
ggy+0.292
unt+0.290
 aids+0.288
Neg logit contributions
 ones-0.239
ishes-0.226
 shells-0.224
 dreams-0.219
 seas-0.208
Token.
Token ID13
Feature activation+4.00e-02

Pos logit contributions
iren+0.088
 crash+0.082
storm+0.079
 aids+0.079
 knock+0.077
Neg logit contributions
ishes-0.057
 minerals-0.053
 seas-0.052
 shells-0.051
 favorites-0.051
Token They
Token ID1119
Feature activation+5.76e-02

Pos logit contributions
iren+0.076
 crash+0.071
storm+0.071
 earthquake+0.068
aned+0.066
Neg logit contributions
ishes-0.061
 favorites-0.060
 minerals-0.059
 seas-0.057
 shells-0.057
Token hear
Token ID3285
Feature activation+1.41e-01

Pos logit contributions
iren+0.102
 crash+0.101
 knock+0.094
storm+0.094
 aids+0.089
Neg logit contributions
ishes-0.097
 seas-0.091
 favorites-0.090
 minerals-0.089
 shells-0.086
Token a
Token ID257
Feature activation-1.24e-01

Pos logit contributions
iren+0.286
storm+0.269
 crash+0.261
aned+0.252
 earthquake+0.248
Neg logit contributions
ishes-0.195
 seas-0.192
 shells-0.191
 minerals-0.190
 favorites-0.185
Token s
Token ID264
Feature activation+3.04e-01

Pos logit contributions
 seaw+0.253
 seas+0.241
 shells+0.241
 minerals+0.239
sters+0.239
Neg logit contributions
iren-0.143
aned-0.141
storm-0.135
 earthquake-0.123
 aids-0.121
Tokeniren
Token ID24080
Feature activation+5.18e-01

Pos logit contributions
storm+0.098
 crash+0.078
 aids+0.054
 tornado+0.053
 earthquake+0.046
Neg logit contributions
ishes-0.913
sters-0.870
 seas-0.858
 shells-0.853
 luck-0.849
Token and
Token ID290
Feature activation+3.89e-02

Pos logit contributions
 aids+1.056
iren+1.014
storm+1.009
 earthquake+1.008
ork+1.007
Neg logit contributions
 ones-0.524
ishes-0.508
sters-0.495
 one-0.493
 dreams-0.487
Token see
Token ID766
Feature activation+2.32e-02

Pos logit contributions
iren+0.064
 crash+0.063
 knock+0.058
storm+0.058
 aids+0.056
Neg logit contributions
ishes-0.072
 favorites-0.067
 seas-0.066
 minerals-0.066
 shells-0.064
Token another
Token ID1194
Feature activation-2.11e-01

Pos logit contributions
iren+0.045
 crash+0.043
storm+0.042
 aids+0.040
 knock+0.040
Neg logit contributions
ishes-0.035
 favorites-0.032
 seas-0.032
 minerals-0.032
 shells-0.032
Token fire
Token ID2046
Feature activation+1.97e-01

Pos logit contributions
 ones+0.369
ishes+0.350
 favorites+0.346
 luck+0.339
 dreams+0.338
Neg logit contributions
iren-0.331
aned-0.315
 aids-0.302
storm-0.295
 crash-0.289
Token truck
Token ID7779
Feature activation+1.17e-01

Pos logit contributions
iren+0.327
 aids+0.318
aned+0.301
 crash+0.298
 earthquake+0.288
Neg logit contributions
ishes-0.321
 ones-0.307
sters-0.298
 islands-0.283
 favorites-0.281
Token He
Token ID679
Feature activation+2.47e-02

Pos logit contributions
iren+0.058
 crash+0.054
storm+0.051
 knock+0.049
 aids+0.048
Neg logit contributions
ishes-0.076
 seas-0.071
 favorites-0.070
 minerals-0.069
 shells-0.069
Token shows
Token ID2523
Feature activation+7.87e-03

Pos logit contributions
iren+0.038
 crash+0.038
 knock+0.037
 aids+0.031
't+0.030
Neg logit contributions
ishes-0.046
 minerals-0.044
 seas-0.044
 seaw-0.043
 fortune-0.042
Token her
Token ID607
Feature activation+4.48e-02

Pos logit contributions
iren+0.015
 crash+0.014
storm+0.014
 knock+0.013
 aids+0.013
Neg logit contributions
ishes-0.012
 favorites-0.011
 seas-0.011
 minerals-0.011
 shells-0.011
Token the
Token ID262
Feature activation+7.26e-02

Pos logit contributions
iren+0.083
 crash+0.080
storm+0.075
 knock+0.073
 aids+0.073
Neg logit contributions
ishes-0.073
 minerals-0.067
 seas-0.067
 favorites-0.067
 seaw-0.065
Token s
Token ID264
Feature activation+3.02e-01

Pos logit contributions
iren+0.140
 crash+0.135
storm+0.128
 knock+0.125
 aids+0.122
Neg logit contributions
ishes-0.114
 favorites-0.104
 minerals-0.103
 seas-0.102
 shells-0.100
Tokeniren
Token ID24080
Feature activation+5.16e-01

Pos logit contributions
iren+0.090
 crash+0.056
storm+0.037
 knock+0.013
 aids+0.012
Neg logit contributions
ishes-0.967
 favorites-0.933
 minerals-0.932
 seas-0.932
 shells-0.923
Token,
Token ID11
Feature activation-1.51e-02

Pos logit contributions
iren+0.954
storm+0.905
 crash+0.896
 earthquake+0.852
 aids+0.835
Neg logit contributions
ishes-0.817
 minerals-0.762
 shells-0.760
 seas-0.758
 favorites-0.758
Token the
Token ID262
Feature activation+7.46e-02

Pos logit contributions
ishes+0.024
 shells+0.023
 minerals+0.022
 favorites+0.022
 seas+0.022
Neg logit contributions
iren-0.028
storm-0.027
 crash-0.026
 earthquake-0.025
 aids-0.025
Token light
Token ID1657
Feature activation+1.63e-01

Pos logit contributions
iren+0.127
storm+0.121
 crash+0.116
aned+0.113
 aids+0.112
Neg logit contributions
ishes-0.124
 shells-0.122
 seas-0.122
 minerals-0.121
 favorites-0.120
Token and
Token ID290
Feature activation+3.99e-02

Pos logit contributions
iren+0.304
aned+0.298
storm+0.297
 earthquake+0.294
 aids+0.288
Neg logit contributions
 ones-0.227
 shells-0.218
ishes-0.212
 dreams-0.208
 luck-0.204
Token the
Token ID262
Feature activation+7.67e-02

Pos logit contributions
iren+0.063
 crash+0.060
storm+0.056
 knock+0.055
 aids+0.053
Neg logit contributions
ishes-0.076
 favorites-0.071
 seas-0.071
 minerals-0.071
 shells-0.069
Token.
Token ID13
Feature activation+3.50e-02

Pos logit contributions
iren+0.716
aned+0.705
 aids+0.698
storm+0.697
unt+0.677
Neg logit contributions
 seaw-0.283
 minerals-0.266
 shells-0.265
 ones-0.258
 dreams-0.247
Token It
Token ID632
Feature activation+7.72e-02

Pos logit contributions
iren+0.069
storm+0.068
 crash+0.066
 brewing+0.064
aned+0.063
Neg logit contributions
 minerals-0.047
ishes-0.045
 favorites-0.045
 seas-0.045
 shells-0.043
Token was
Token ID373
Feature activation+8.26e-02

Pos logit contributions
iren+0.173
 earthquake+0.158
 aids+0.154
storm+0.153
 outage+0.153
Neg logit contributions
 dreams-0.079
 ones-0.076
 seaw-0.076
 luck-0.075
 one-0.074
Token a
Token ID257
Feature activation-1.27e-01

Pos logit contributions
iren+0.195
storm+0.184
aned+0.180
umpy+0.177
t+0.175
Neg logit contributions
 luck-0.087
 minerals-0.082
 seaw-0.081
 something-0.081
 dreams-0.077
Token s
Token ID264
Feature activation+3.04e-01

Pos logit contributions
 seas+0.211
 seaw+0.209
 ones+0.199
 minerals+0.196
 luck+0.195
Neg logit contributions
aned-0.226
iren-0.207
 aids-0.194
loe-0.181
anne-0.179
Tokeniren
Token ID24080
Feature activation+5.16e-01

Pos logit contributions
 crash+0.073
storm+0.073
 aids+0.052
 knock+0.033
 tornado+0.031
Neg logit contributions
ishes-0.919
sters-0.880
 seas-0.878
 seaw-0.868
 minerals-0.866
Token.
Token ID13
Feature activation+3.63e-02

Pos logit contributions
 aids+1.120
iren+1.102
aned+1.053
storm+1.020
unt+1.018
Neg logit contributions
 ones-0.506
ishes-0.494
sters-0.480
 luck-0.478
ish-0.445
Token It
Token ID632
Feature activation+7.75e-02

Pos logit contributions
storm+0.069
iren+0.068
 crash+0.067
aned+0.064
 brewing+0.064
Neg logit contributions
 minerals-0.050
 favorites-0.048
 seas-0.047
ishes-0.047
 shells-0.046
Token was
Token ID373
Feature activation+8.43e-02

Pos logit contributions
iren+0.182
 earthquake+0.175
 aids+0.168
storm+0.163
amp+0.161
Neg logit contributions
 one-0.068
 ones-0.066
 nic-0.065
 dreams-0.062
 seaw-0.061
Token another
Token ID1194
Feature activation-2.14e-01

Pos logit contributions
iren+0.186
storm+0.181
aned+0.176
umpy+0.175
anne+0.173
Neg logit contributions
 luck-0.099
 something-0.096
 minerals-0.092
 one-0.091
 prett-0.090
Token cop
Token ID2243
Feature activation+1.43e-01

Pos logit contributions
 ones+0.342
 favorites+0.333
ishes+0.329
 minerals+0.325
 luck+0.322
Neg logit contributions
iren-0.363
aned-0.334
 crash-0.334
 aids-0.330
 collapse-0.319
Token.
Token ID13
Feature activation+3.26e-02

Pos logit contributions
iren+0.640
storm+0.631
aned+0.631
 aids+0.630
 crash+0.611
Neg logit contributions
 seaw-0.342
 shells-0.333
 minerals-0.325
 ones-0.319
ishes-0.313
Token It
Token ID632
Feature activation+8.05e-02

Pos logit contributions
iren+0.057
 crash+0.054
storm+0.053
 knock+0.049
 earthquake+0.049
Neg logit contributions
ishes-0.055
 minerals-0.054
 favorites-0.053
 seas-0.053
 shells-0.052
Token was
Token ID373
Feature activation+8.89e-02

Pos logit contributions
iren+0.177
 earthquake+0.163
 aids+0.157
storm+0.157
 outage+0.152
Neg logit contributions
 seaw-0.086
 ones-0.085
 dreams-0.084
 seas-0.082
 minerals-0.081
Token a
Token ID257
Feature activation-1.24e-01

Pos logit contributions
iren+0.220
aned+0.207
storm+0.205
umpy+0.200
t+0.197
Neg logit contributions
 luck-0.082
 something-0.080
 minerals-0.080
 dreams-0.079
 ones-0.079
Token s
Token ID264
Feature activation+3.03e-01

Pos logit contributions
 seas+0.203
 seaw+0.199
 ones+0.186
 shells+0.184
 coral+0.184
Neg logit contributions
aned-0.234
iren-0.209
 aids-0.199
loe-0.189
umpy-0.183
Tokeniren
Token ID24080
Feature activation+5.14e-01

Pos logit contributions
storm+0.089
 crash+0.088
 aids+0.073
 tornado+0.050
 knock+0.048
Neg logit contributions
ishes-0.883
sters-0.859
 seas-0.858
 seaw-0.847
 shells-0.841
Token.
Token ID13
Feature activation+3.37e-02

Pos logit contributions
 aids+1.161
iren+1.100
aned+1.071
loe+1.056
 earthquake+1.038
Neg logit contributions
 ones-0.473
sters-0.443
ishes-0.437
 one-0.424
 luck-0.401
Token They
Token ID1119
Feature activation+5.44e-02

Pos logit contributions
iren+0.059
 crash+0.055
storm+0.055
 knock+0.051
 earthquake+0.051
Neg logit contributions
ishes-0.058
 minerals-0.056
 favorites-0.055
 seas-0.055
 shells-0.054
Token saw
Token ID2497
Feature activation-1.72e-02

Pos logit contributions
iren+0.103
storm+0.096
 crash+0.092
 aids+0.092
 earthquake+0.090
Neg logit contributions
ishes-0.086
 shells-0.081
 seas-0.081
 minerals-0.080
 seaw-0.079
Token a
Token ID257
Feature activation-1.22e-01

Pos logit contributions
ishes+0.024
 minerals+0.023
 seas+0.022
 shells+0.022
 favorites+0.022
Neg logit contributions
iren-0.035
storm-0.034
 crash-0.033
 knock-0.031
 aids-0.031
Token big
Token ID1263
Feature activation+1.69e-01

Pos logit contributions
 seas+0.192
 ones+0.185
 shells+0.179
 seaw+0.178
 minerals+0.174
Neg logit contributions
aned-0.221
iren-0.204
 aids-0.203
storm-0.192
loe-0.182
Token red
Token ID2266
Feature activation+5.76e-02

Pos logit contributions
 luck+0.197
 ones+0.194
 seas+0.192
 prett+0.190
 scar+0.189
Neg logit contributions
aned-0.192
iren-0.184
storm-0.179
izz-0.175
amp-0.173
Token light
Token ID1657
Feature activation+1.66e-01

Pos logit contributions
iren+0.099
storm+0.095
 aids+0.093
 brewing+0.093
aned+0.092
Neg logit contributions
 ones-0.084
 seas-0.081
ishes-0.080
 luck-0.079
 shells-0.079
Token and
Token ID290
Feature activation+3.49e-02

Pos logit contributions
iren+0.304
aned+0.295
 aids+0.289
 earthquake+0.282
 crash+0.278
Neg logit contributions
 ones-0.220
 seas-0.217
 shells-0.215
ishes-0.213
 luck-0.206
Token a
Token ID257
Feature activation-1.24e-01

Pos logit contributions
iren+0.077
storm+0.073
 crash+0.071
 aids+0.069
aned+0.069
Neg logit contributions
 seas-0.041
 minerals-0.040
ishes-0.040
 shells-0.040
 seaw-0.038
Token s
Token ID264
Feature activation+3.03e-01

Pos logit contributions
 seas+0.203
 ones+0.201
 luck+0.199
 shells+0.197
 seaw+0.196
Neg logit contributions
iren-0.189
aned-0.188
storm-0.179
 aids-0.168
amp-0.166
Tokeniren
Token ID24080
Feature activation+5.14e-01

Pos logit contributions
 crash+0.145
storm+0.136
 aids+0.125
 knock+0.124
 tornado+0.117
Neg logit contributions
ishes-0.817
sters-0.793
 luck-0.780
 seas-0.774
minded-0.771
Token.
Token ID13
Feature activation+3.26e-02

Pos logit contributions
iren+1.022
 aids+0.999
 earthquake+0.977
unt+0.972
loe+0.954
Neg logit contributions
ishes-0.587
 ones-0.573
 luck-0.547
sters-0.533
 one-0.525
Token It
Token ID632
Feature activation+8.08e-02

Pos logit contributions
iren+0.061
storm+0.059
 crash+0.059
lf+0.055
aned+0.055
Neg logit contributions
ishes-0.047
 minerals-0.046
 favorites-0.043
 dreams-0.043
 seas-0.042
Token came
Token ID1625
Feature activation+1.99e-01

Pos logit contributions
 earthquake+0.189
iren+0.185
 aids+0.183
amp+0.172
arter+0.170
Neg logit contributions
 one-0.073
 nic-0.065
 ones-0.064
 prett-0.062
 most-0.059
Token to
Token ID284
Feature activation+7.11e-02

Pos logit contributions
iren+0.410
storm+0.400
 aids+0.393
lf+0.376
 earthquake+0.371
Neg logit contributions
ishes-0.255
 luck-0.243
 seas-0.232
 minerals-0.232
 shells-0.230
Token the
Token ID262
Feature activation+8.01e-02

Pos logit contributions
iren+0.132
storm+0.119
 crash+0.119
 aids+0.117
aned+0.114
Neg logit contributions
ishes-0.112
 minerals-0.109
 seas-0.109
 shells-0.108
 seaw-0.107
Token,
Token ID11
Feature activation-2.38e-02

Pos logit contributions
ishes+0.220
 favorites+0.208
esty+0.194
 minerals+0.193
 seas+0.189
Neg logit contributions
 crash-0.200
iren-0.193
 knock-0.176
storm-0.172
 earthquake-0.171
Token he
Token ID339
Feature activation-1.09e-01

Pos logit contributions
ishes+0.044
 favorites+0.041
 minerals+0.038
sters+0.038
 seas+0.038
Neg logit contributions
 crash-0.040
iren-0.039
 knock-0.037
storm-0.036
 collapse-0.035
Token heard
Token ID2982
Feature activation+5.32e-02

Pos logit contributions
ishes+0.164
 seas+0.159
 shells+0.158
 seaw+0.157
 favorites+0.150
Neg logit contributions
iren-0.217
storm-0.200
 earthquake-0.197
 crash-0.197
 aids-0.187
Token a
Token ID257
Feature activation-1.27e-01

Pos logit contributions
iren+0.130
storm+0.130
 crash+0.125
aned+0.122
 outage+0.119
Neg logit contributions
 seas-0.048
 shells-0.047
 minerals-0.047
 seaw-0.045
 dreams-0.044
Token s
Token ID264
Feature activation+3.01e-01

Pos logit contributions
 seaw+0.265
 minerals+0.249
 shells+0.249
sters+0.248
 seas+0.244
Neg logit contributions
iren-0.154
storm-0.148
aned-0.138
 aids-0.135
 earthquake-0.130
Tokeniren
Token ID24080
Feature activation+5.13e-01

Pos logit contributions
storm+0.105
 crash+0.086
 aids+0.068
 tornado+0.060
 earthquake+0.055
Neg logit contributions
ishes-0.880
sters-0.856
 seaw-0.843
 seas-0.841
 shells-0.837
Token.
Token ID13
Feature activation+3.07e-02

Pos logit contributions
 aids+1.037
storm+1.001
unt+0.986
loe+0.982
anne+0.971
Neg logit contributions
ishes-0.519
 ones-0.519
 dreams-0.503
sters-0.497
 luck-0.491
Token It
Token ID632
Feature activation+7.72e-02

Pos logit contributions
iren+0.060
storm+0.059
 crash+0.056
 brewing+0.056
aned+0.056
Neg logit contributions
 minerals-0.042
ishes-0.039
 seaw-0.038
 seas-0.038
 dreams-0.038
Token was
Token ID373
Feature activation+8.60e-02

Pos logit contributions
iren+0.169
 earthquake+0.166
 aids+0.160
storm+0.157
maker+0.150
Neg logit contributions
 ones-0.076
 seaw-0.074
 one-0.073
 dreams-0.072
ishes-0.070
Token the
Token ID262
Feature activation+7.26e-02

Pos logit contributions
iren+0.181
storm+0.176
umpy+0.171
anne+0.170
aned+0.169
Neg logit contributions
 luck-0.106
 something-0.103
 shells-0.100
 minerals-0.098
 seaw-0.097
Token zo
Token ID40565
Feature activation+1.06e-01

Pos logit contributions
iren+0.124
 crash+0.112
storm+0.109
 aids+0.107
aned+0.106
Neg logit contributions
ishes-0.126
 seas-0.123
 shells-0.121
 minerals-0.121
 favorites-0.120
Token They
Token ID1119
Feature activation+5.18e-02

Pos logit contributions
iren+0.063
 crash+0.060
storm+0.059
 aids+0.055
 knock+0.055
Neg logit contributions
ishes-0.062
 minerals-0.058
 favorites-0.058
 shells-0.057
 seas-0.057
Token turn
Token ID1210
Feature activation+9.30e-02

Pos logit contributions
iren+0.082
 crash+0.082
 knock+0.076
storm+0.074
 collapse+0.069
Neg logit contributions
ishes-0.096
 seas-0.091
 favorites-0.091
 minerals-0.089
 shells-0.087
Token on
Token ID319
Feature activation+9.14e-02

Pos logit contributions
storm+0.183
iren+0.176
 aids+0.167
ggy+0.166
lf+0.164
Neg logit contributions
ishes-0.144
 shells-0.135
 minerals-0.134
 seas-0.132
 luck-0.130
Token the
Token ID262
Feature activation+7.52e-02

Pos logit contributions
iren+0.160
 crash+0.149
storm+0.147
 aids+0.138
 knock+0.137
Neg logit contributions
ishes-0.159
 seas-0.150
 minerals-0.150
 shells-0.148
 favorites-0.148
Token s
Token ID264
Feature activation+3.00e-01

Pos logit contributions
iren+0.120
storm+0.116
 aids+0.112
aned+0.111
anne+0.108
Neg logit contributions
 minerals-0.132
ishes-0.132
 shells-0.129
 ones-0.128
 seas-0.127
Tokeniren
Token ID24080
Feature activation+5.13e-01

Pos logit contributions
 crash+0.078
iren+0.077
storm+0.073
 knock+0.040
 aids+0.039
Neg logit contributions
ishes-0.941
 seas-0.895
 minerals-0.892
 favorites-0.892
 shells-0.886
Token and
Token ID290
Feature activation+3.82e-02

Pos logit contributions
iren+1.011
storm+0.961
 crash+0.944
 aids+0.932
 earthquake+0.923
Neg logit contributions
ishes-0.732
 seas-0.673
 shells-0.671
 minerals-0.662
 ones-0.659
Token the
Token ID262
Feature activation+7.67e-02

Pos logit contributions
 crash+0.057
iren+0.056
 knock+0.052
storm+0.049
 collapse+0.047
Neg logit contributions
ishes-0.076
 favorites-0.073
 seas-0.072
 minerals-0.071
sters-0.069
Token lights
Token ID7588
Feature activation+1.09e-01

Pos logit contributions
iren+0.123
storm+0.117
aned+0.114
 aids+0.111
 crash+0.108
Neg logit contributions
ishes-0.136
 minerals-0.134
 shells-0.133
 ones-0.131
 seas-0.130
Token.
Token ID13
Feature activation+3.89e-02

Pos logit contributions
iren+0.227
storm+0.214
unt+0.213
 aids+0.212
 earthquake+0.209
Neg logit contributions
 shells-0.137
ishes-0.134
 luck-0.128
 seas-0.128
 dreams-0.127
Token They
Token ID1119
Feature activation+5.47e-02

Pos logit contributions
iren+0.073
 crash+0.069
storm+0.068
 aids+0.064
 earthquake+0.064
Neg logit contributions
ishes-0.060
 favorites-0.058
 minerals-0.058
 shells-0.056
 seas-0.056
Token the
Token ID262
Feature activation+7.99e-02

Pos logit contributions
iren+0.214
 crash+0.205
 aids+0.194
 knock+0.194
storm+0.184
Neg logit contributions
ishes-0.181
 favorites-0.171
 seas-0.168
 minerals-0.162
 seaw-0.161
Token hose
Token ID31489
Feature activation+1.56e-01

Pos logit contributions
iren+0.142
storm+0.131
 crash+0.129
 aids+0.126
aned+0.124
Neg logit contributions
ishes-0.133
 favorites-0.129
 minerals-0.128
 shells-0.126
 ones-0.126
Token,
Token ID11
Feature activation-1.69e-02

Pos logit contributions
iren+0.319
storm+0.297
 crash+0.296
 earthquake+0.285
 aids+0.277
Neg logit contributions
ishes-0.222
 shells-0.211
 minerals-0.209
 favorites-0.201
 seas-0.201
Token the
Token ID262
Feature activation+7.99e-02

Pos logit contributions
ishes+0.025
 shells+0.024
 minerals+0.024
 seas+0.023
 favorites+0.023
Neg logit contributions
iren-0.034
storm-0.033
 crash-0.031
 earthquake-0.030
 aids-0.030
Token s
Token ID264
Feature activation+3.00e-01

Pos logit contributions
iren+0.139
storm+0.128
 crash+0.128
 aids+0.121
aned+0.119
Neg logit contributions
ishes-0.138
 minerals-0.130
 favorites-0.130
 shells-0.130
 seas-0.129
Tokeniren
Token ID24080
Feature activation+5.12e-01

Pos logit contributions
 crash+0.086
storm+0.075
 aids+0.048
iren+0.047
 knock+0.047
Neg logit contributions
ishes-0.938
 seas-0.879
sters-0.879
 favorites-0.876
 shells-0.873
Token,
Token ID11
Feature activation-1.64e-02

Pos logit contributions
iren+1.091
 earthquake+1.054
storm+1.050
 tornado+1.013
 aids+0.988
Neg logit contributions
ishes-0.620
 ones-0.592
 shells-0.591
sters-0.571
 luck-0.562
Token the
Token ID262
Feature activation+8.04e-02

Pos logit contributions
ishes+0.025
 shells+0.023
 minerals+0.023
 seas+0.023
 seaw+0.022
Neg logit contributions
iren-0.032
storm-0.031
 crash-0.030
 earthquake-0.029
 aids-0.029
Token ladder
Token ID18002
Feature activation+2.04e-01

Pos logit contributions
iren+0.142
storm+0.131
 crash+0.130
 aids+0.124
aned+0.122
Neg logit contributions
ishes-0.136
 minerals-0.129
 shells-0.129
 favorites-0.128
 seas-0.127
Token and
Token ID290
Feature activation+3.87e-02

Pos logit contributions
iren+0.440
storm+0.418
 earthquake+0.412
 aids+0.404
 crash+0.402
Neg logit contributions
ishes-0.254
 shells-0.242
 ones-0.237
 minerals-0.230
 seas-0.228
Token the
Token ID262
Feature activation+8.11e-02

Pos logit contributions
iren+0.074
storm+0.070
 aids+0.066
 crash+0.066
aned+0.065
Neg logit contributions
ishes-0.061
 shells-0.060
 minerals-0.058
 seas-0.057
 ones-0.056
Token police
Token ID1644
Feature activation+9.75e-02

Pos logit contributions
iren+0.139
storm+0.133
 aids+0.127
aned+0.127
 crash+0.126
Neg logit contributions
 seas-0.125
ishes-0.124
 minerals-0.123
 shells-0.122
 ones-0.121
Token car
Token ID1097
Feature activation+4.02e-02

Pos logit contributions
iren+0.164
storm+0.162
 aids+0.158
 earthquake+0.157
 brewing+0.145
Neg logit contributions
ishes-0.157
 seas-0.150
 shells-0.150
sters-0.147
 ones-0.147
Token had
Token ID550
Feature activation+1.39e-01

Pos logit contributions
iren+0.072
 earthquake+0.072
 aids+0.070
storm+0.070
loe+0.069
Neg logit contributions
 ones-0.053
 shells-0.052
ishes-0.052
sters-0.051
 seas-0.051
Token a
Token ID257
Feature activation-1.28e-01

Pos logit contributions
iren+0.265
storm+0.264
 earthquake+0.239
 crash+0.235
 aids+0.233
Neg logit contributions
 shells-0.210
ishes-0.207
 seas-0.207
 luck-0.206
 minerals-0.199
Token s
Token ID264
Feature activation+3.00e-01

Pos logit contributions
 seas+0.205
 luck+0.198
 ones+0.195
 shells+0.194
 favorites+0.193
Neg logit contributions
iren-0.219
aned-0.208
storm-0.205
 aids-0.198
 brewing-0.195
Tokeniren
Token ID24080
Feature activation+5.11e-01

Pos logit contributions
storm+0.088
 crash+0.079
 knock+0.045
 tornado+0.043
 aids+0.041
Neg logit contributions
ishes-0.926
 seas-0.882
sters-0.875
 luck-0.868
 shells-0.866
Token and
Token ID290
Feature activation+3.45e-02

Pos logit contributions
iren+1.071
storm+1.058
 earthquake+1.044
 aids+1.042
unt+1.030
Neg logit contributions
ishes-0.553
 ones-0.532
 luck-0.510
sters-0.495
 shells-0.472
Token a
Token ID257
Feature activation-1.28e-01

Pos logit contributions
iren+0.079
storm+0.075
 crash+0.074
 aids+0.072
 earthquake+0.071
Neg logit contributions
ishes-0.039
 seas-0.037
 minerals-0.037
 shells-0.036
 favorites-0.035
Token light
Token ID1657
Feature activation+1.63e-01

Pos logit contributions
 seas+0.206
 shells+0.201
 ones+0.200
 luck+0.195
 seaw+0.195
Neg logit contributions
iren-0.213
aned-0.206
storm-0.203
 aids-0.191
 brewing-0.190
Token.
Token ID13
Feature activation+3.67e-02

Pos logit contributions
iren+0.328
aned+0.316
 earthquake+0.310
 crash+0.304
 aids+0.303
Neg logit contributions
 shells-0.202
 ones-0.202
 seas-0.200
ishes-0.195
 luck-0.186
Token It
Token ID632
Feature activation+7.75e-02

Pos logit contributions
storm+0.070
iren+0.069
 crash+0.066
lf+0.064
aned+0.064
Neg logit contributions
 favorites-0.051
 minerals-0.050
ishes-0.050
 seas-0.049
 dreams-0.047
Token it
Token ID340
Feature activation+3.69e-02

Pos logit contributions
ishes+0.333
 favorites+0.331
esty+0.306
 nic+0.298
 prett+0.297
Neg logit contributions
 crash-0.193
 knock-0.162
iren-0.160
 earthquake-0.157
 collapse-0.153
Token heard
Token ID2982
Feature activation+5.14e-02

Pos logit contributions
iren+0.071
 crash+0.065
storm+0.064
 earthquake+0.062
 aids+0.061
Neg logit contributions
ishes-0.056
 seas-0.055
 seaw-0.055
 shells-0.054
 minerals-0.053
Token a
Token ID257
Feature activation-1.27e-01

Pos logit contributions
iren+0.134
storm+0.134
 crash+0.127
 outage+0.125
aned+0.124
Neg logit contributions
 seas-0.039
 shells-0.038
 dreams-0.037
 seaw-0.035
 minerals-0.034
Token loud
Token ID7812
Feature activation+3.30e-01

Pos logit contributions
 seaw+0.273
 minerals+0.257
 shells+0.256
 seas+0.256
 luck+0.254
Neg logit contributions
iren-0.148
storm-0.138
aned-0.132
 aids-0.126
 brewing-0.119
Token s
Token ID264
Feature activation+2.98e-01

Pos logit contributions
 cancelled+0.434
case+0.432
iren+0.424
storm+0.407
aned+0.406
Neg logit contributions
 seaw-0.574
 dreams-0.534
 ones-0.516
 one-0.513
 minerals-0.513
Tokeniren
Token ID24080
Feature activation+5.11e-01

Pos logit contributions
storm+0.117
 crash+0.098
 aids+0.077
 tornado+0.075
 earthquake+0.060
Neg logit contributions
ishes-0.858
sters-0.848
 seaw-0.838
 seas-0.833
 shells-0.829
Token.
Token ID13
Feature activation+3.06e-02

Pos logit contributions
 aids+1.116
loe+1.097
unt+1.074
anne+1.053
storm+1.048
Neg logit contributions
 ones-0.437
sters-0.432
 one-0.428
ishes-0.417
 dreams-0.410
Token It
Token ID632
Feature activation+7.81e-02

Pos logit contributions
iren+0.057
storm+0.054
 crash+0.054
aned+0.051
 brewing+0.050
Neg logit contributions
 minerals-0.045
ishes-0.045
 seas-0.044
 seaw-0.043
 shells-0.043
Token saw
Token ID2497
Feature activation-2.40e-02

Pos logit contributions
iren+0.173
 earthquake+0.163
 aids+0.160
storm+0.157
 crash+0.149
Neg logit contributions
 seaw-0.088
 shells-0.081
 seas-0.080
 ones-0.079
 one-0.077
Token a
Token ID257
Feature activation-1.25e-01

Pos logit contributions
ishes+0.037
 shells+0.036
 seas+0.036
 minerals+0.035
 seaw+0.034
Neg logit contributions
iren-0.046
storm-0.044
 crash-0.043
 knock-0.040
 aids-0.040
Token big
Token ID1263
Feature activation+1.65e-01

Pos logit contributions
 seas+0.198
 seaw+0.189
 ones+0.183
 shells+0.182
 minerals+0.180
Neg logit contributions
aned-0.227
iren-0.210
 aids-0.206
storm-0.198
anne-0.189
Token.
Token ID13
Feature activation+3.41e-02

Pos logit contributions
iren+0.327
unt+0.312
 aids+0.312
storm+0.309
aned+0.301
Neg logit contributions
ishes-0.167
 shells-0.161
 ones-0.156
sters-0.152
 minerals-0.151
Token It
Token ID632
Feature activation+7.60e-02

Pos logit contributions
iren+0.063
 crash+0.059
storm+0.055
 aids+0.054
 knock+0.054
Neg logit contributions
ishes-0.057
 favorites-0.052
 seas-0.052
 minerals-0.051
 shells-0.050
Token has
Token ID468
Feature activation+5.57e-02

Pos logit contributions
iren+0.145
storm+0.137
 crash+0.132
 earthquake+0.131
 aids+0.129
Neg logit contributions
ishes-0.117
 minerals-0.110
 favorites-0.108
 shells-0.108
 seas-0.106
Token a
Token ID257
Feature activation-1.30e-01

Pos logit contributions
iren+0.132
storm+0.128
 crash+0.123
 earthquake+0.118
 aids+0.118
Neg logit contributions
ishes-0.057
 seas-0.057
 shells-0.057
 minerals-0.056
 favorites-0.054
Token s
Token ID264
Feature activation+2.99e-01

Pos logit contributions
 seas+0.207
 shells+0.199
 ones+0.198
 favorites+0.197
 minerals+0.196
Neg logit contributions
iren-0.222
aned-0.212
storm-0.202
 aids-0.197
 brewing-0.194
Tokeniren
Token ID24080
Feature activation+5.10e-01

Pos logit contributions
storm+0.107
 crash+0.083
 tornado+0.067
 aids+0.063
 knock+0.049
Neg logit contributions
ishes-0.898
 seas-0.862
 shells-0.851
sters-0.850
 minerals-0.844
Token that
Token ID326
Feature activation+9.09e-02

Pos logit contributions
iren+1.009
storm+0.984
 aids+0.957
 earthquake+0.949
 crash+0.941
Neg logit contributions
ishes-0.645
 ones-0.624
sters-0.600
 dreams-0.581
 luck-0.581
Token goes
Token ID2925
Feature activation+4.44e-02

Pos logit contributions
iren+0.188
storm+0.182
 crash+0.175
aned+0.170
 earthquake+0.170
Neg logit contributions
ishes-0.121
 shells-0.113
 minerals-0.112
 favorites-0.110
 dreams-0.109
Token woo
Token ID36440
Feature activation+1.67e-01

Pos logit contributions
 aids+0.093
anne+0.088
storm+0.086
lf+0.086
ggy+0.084
Neg logit contributions
ishes-0.055
 ones-0.054
 seas-0.054
 one-0.053
 minerals-0.051
Token-
Token ID12
Feature activation+1.27e-01

Pos logit contributions
iren+0.285
 crash+0.274
storm+0.266
 aids+0.259
 knock+0.253
Neg logit contributions
ishes-0.283
 seas-0.264
 minerals-0.262
 luck-0.261
sters-0.258
Tokenw
Token ID86
Feature activation-4.51e-02

Pos logit contributions
iren+0.196
 crash+0.195
storm+0.188
 aids+0.182
 earthquake+0.180
Neg logit contributions
ishes-0.233
 seas-0.217
 favorites-0.212
 minerals-0.212
 shells-0.211
TokenIt
Token ID1026
Feature activation+6.19e-02

Pos logit contributions
iren+0.161
 crash+0.158
 earthquake+0.150
storm+0.147
 aids+0.145
Neg logit contributions
ishes-0.119
 seas-0.117
 minerals-0.113
 shells-0.112
 seaw-0.112
Token was
Token ID373
Feature activation+8.69e-02

Pos logit contributions
iren+0.148
 crash+0.138
storm+0.136
 aids+0.131
 earthquake+0.130
Neg logit contributions
ishes-0.068
 minerals-0.059
 favorites-0.057
 dreams-0.055
 seas-0.055
Token an
Token ID281
Feature activation-1.68e-01

Pos logit contributions
iren+0.224
 crash+0.205
storm+0.204
aned+0.202
 aids+0.194
Neg logit contributions
 minerals-0.076
 seas-0.075
 luck-0.075
ishes-0.072
 seaw-0.069
Token emergency
Token ID6334
Feature activation+3.66e-01

Pos logit contributions
 luck+0.339
 dreams+0.334
 minerals+0.331
 seaw+0.331
ish+0.329
Neg logit contributions
iren-0.198
 crash-0.183
storm-0.171
oe-0.167
 aids-0.163
Token s
Token ID264
Feature activation+3.00e-01

Pos logit contributions
iren+0.640
 crash+0.588
 aids+0.583
aned+0.569
storm+0.557
Neg logit contributions
ishes-0.590
 ones-0.565
 favorites-0.542
 luck-0.541
 minerals-0.539
Tokeniren
Token ID24080
Feature activation+5.09e-01

Pos logit contributions
 crash+0.175
 knock+0.148
 aids+0.142
storm+0.138
 ripping+0.128
Neg logit contributions
ishes-0.811
 seas-0.780
sters-0.772
 minerals-0.755
 seaw-0.755
Token.
Token ID13
Feature activation+2.46e-02

Pos logit contributions
iren+1.020
 crash+0.948
 aids+0.930
storm+0.913
 knock+0.898
Neg logit contributions
ishes-0.710
 ones-0.629
 minerals-0.626
 seas-0.619
 luck-0.618
Token Let
Token ID3914
Feature activation-1.35e-02

Pos logit contributions
iren+0.045
 crash+0.043
storm+0.042
 aids+0.039
aned+0.039
Neg logit contributions
ishes-0.038
 minerals-0.036
 favorites-0.036
 seas-0.034
 shells-0.033
Token's
Token ID338
Feature activation-1.34e-01

Pos logit contributions
ishes+0.013
 ones+0.011
 seas+0.011
 dreams+0.011
 luck+0.011
Neg logit contributions
iren-0.034
 crash-0.031
 outage-0.030
storm-0.030
 aids-0.030
Token get
Token ID651
Feature activation+9.10e-02

Pos logit contributions
ishes+0.229
 favorites+0.214
 minerals+0.214
 seas+0.212
 shells+0.211
Neg logit contributions
iren-0.233
 crash-0.215
storm-0.212
 aids-0.201
 earthquake-0.195
Token to
Token ID284
Feature activation+6.94e-02

Pos logit contributions
iren+0.178
storm+0.170
 crash+0.167
 aids+0.161
 earthquake+0.155
Neg logit contributions
ishes-0.136
 seas-0.125
 minerals-0.125
 shells-0.125
 favorites-0.122
Token truck
Token ID7779
Feature activation+1.06e-01

Pos logit contributions
iren+0.348
 aids+0.336
 crash+0.329
 earthquake+0.327
ggy+0.326
Neg logit contributions
ishes-0.277
 ones-0.240
ish-0.239
sters-0.237
 minerals-0.236
Token has
Token ID468
Feature activation+5.26e-02

Pos logit contributions
iren+0.223
storm+0.219
 earthquake+0.215
 aids+0.213
ggy+0.211
Neg logit contributions
ishes-0.120
 minerals-0.110
 dreams-0.108
 ones-0.107
sters-0.105
Token a
Token ID257
Feature activation-1.33e-01

Pos logit contributions
iren+0.121
storm+0.118
 crash+0.111
 earthquake+0.109
aned+0.109
Neg logit contributions
 seas-0.058
 shells-0.058
 minerals-0.056
ishes-0.055
 ones-0.055
Token loud
Token ID7812
Feature activation+3.28e-01

Pos logit contributions
 seas+0.218
 minerals+0.210
 favorites+0.207
 shells+0.205
 seaw+0.204
Neg logit contributions
iren-0.227
aned-0.212
 aids-0.198
storm-0.196
 brewing-0.190
Token s
Token ID264
Feature activation+2.96e-01

Pos logit contributions
izz+0.437
umpy+0.432
iren+0.429
amp+0.404
 cancelled+0.393
Neg logit contributions
 ones-0.583
 dreams-0.571
 seaw-0.553
 one-0.553
 luck-0.540
Tokeniren
Token ID24080
Feature activation+5.09e-01

Pos logit contributions
storm+0.098
 crash+0.098
 tornado+0.069
 aids+0.067
 knock+0.061
Neg logit contributions
ishes-0.879
 seas-0.848
 seaw-0.833
sters-0.830
 minerals-0.830
Token and
Token ID290
Feature activation+3.18e-02

Pos logit contributions
iren+1.025
storm+0.990
 aids+0.988
 tornado+0.973
 earthquake+0.971
Neg logit contributions
ishes-0.583
 ones-0.572
sters-0.560
 luck-0.516
 shells-0.510
Token a
Token ID257
Feature activation-1.32e-01

Pos logit contributions
iren+0.065
 crash+0.063
storm+0.059
 knock+0.058
 aids+0.057
Neg logit contributions
ishes-0.047
 favorites-0.042
 seas-0.042
 minerals-0.041
 shells-0.040
Token long
Token ID890
Feature activation+7.41e-02

Pos logit contributions
 seas+0.247
 seaw+0.242
 shells+0.241
 ones+0.239
 minerals+0.238
Neg logit contributions
iren-0.186
aned-0.175
storm-0.166
 aids-0.157
 brewing-0.155
Token ladder
Token ID18002
Feature activation+1.97e-01

Pos logit contributions
iren+0.131
umpy+0.118
storm+0.118
 brewing+0.117
maker+0.116
Neg logit contributions
 ones-0.108
 seas-0.101
 shells-0.100
 one-0.098
 seaw-0.097
Token.
Token ID13
Feature activation+3.19e-02

Pos logit contributions
unt+0.418
 aids+0.414
iren+0.408
storm+0.406
 earthquake+0.406
Neg logit contributions
ishes-0.206
 ones-0.205
 shells-0.198
sters-0.184
 seas-0.180
Token walking
Token ID6155
Feature activation+8.56e-02

Pos logit contributions
 luck+0.008
ishes+0.007
 seas+0.007
 best+0.007
sters+0.007
Neg logit contributions
iren-0.010
storm-0.010
 aids-0.010
 outage-0.009
 earthquake-0.009
Token,
Token ID11
Feature activation-2.19e-02

Pos logit contributions
iren+0.128
 crash+0.124
storm+0.112
 knock+0.109
 brewing+0.105
Neg logit contributions
ishes-0.169
 favorites-0.157
 seaw-0.153
sters-0.153
 minerals-0.152
Token a
Token ID257
Feature activation-1.25e-01

Pos logit contributions
ishes+0.038
 favorites+0.035
 minerals+0.034
 seas+0.034
 shells+0.034
Neg logit contributions
iren-0.038
 crash-0.036
storm-0.035
 knock-0.033
 aids-0.033
Token loud
Token ID7812
Feature activation+3.31e-01

Pos logit contributions
 seas+0.194
 seaw+0.176
 shells+0.175
 minerals+0.169
 ones+0.168
Neg logit contributions
aned-0.236
iren-0.232
 aids-0.212
 crash-0.205
 collapse-0.204
Token s
Token ID264
Feature activation+2.98e-01

Pos logit contributions
aned+0.580
iren+0.539
izz+0.519
 collapse+0.511
umpy+0.510
Neg logit contributions
 one-0.494
 ones-0.480
 seas-0.478
 dreams-0.472
 seaw-0.459
Tokeniren
Token ID24080
Feature activation+5.06e-01

Pos logit contributions
 crash+0.132
storm+0.104
 aids+0.101
 knock+0.086
 earthquake+0.081
Neg logit contributions
ishes-0.846
 seas-0.836
sters-0.818
 shells-0.809
 ones-0.800
Token suddenly
Token ID6451
Feature activation-3.55e-02

Pos logit contributions
iren+0.890
 aids+0.888
 collapse+0.817
 crash+0.815
 earthquake+0.814
Neg logit contributions
ishes-0.746
 ones-0.729
 seas-0.706
 shells-0.701
sters-0.699
Token came
Token ID1625
Feature activation+1.97e-01

Pos logit contributions
 seas+0.057
 shells+0.055
ishes+0.054
 seaw+0.054
 ones+0.053
Neg logit contributions
iren-0.061
 crash-0.056
 aids-0.055
 earthquake-0.055
storm-0.054
Token on
Token ID319
Feature activation+9.57e-02

Pos logit contributions
iren+0.356
storm+0.341
 aids+0.330
 crash+0.329
 earthquake+0.320
Neg logit contributions
ishes-0.313
 seas-0.295
 luck-0.293
 minerals-0.291
 shells-0.290
Token.
Token ID13
Feature activation+2.53e-02

Pos logit contributions
iren+0.191
 crash+0.179
storm+0.178
 aids+0.170
aned+0.169
Neg logit contributions
 seas-0.134
 minerals-0.132
ishes-0.132
 ones-0.128
 shells-0.127
Token Everyone
Token ID11075
Feature activation+1.28e-01

Pos logit contributions
iren+0.050
storm+0.048
 crash+0.047
 earthquake+0.046
 knock+0.044
Neg logit contributions
 favorites-0.036
 minerals-0.035
ishes-0.035
 seas-0.035
 shells-0.033
Token It
Token ID632
Feature activation+7.14e-02

Pos logit contributions
iren+0.036
 crash+0.034
storm+0.033
 knock+0.031
 earthquake+0.031
Neg logit contributions
ishes-0.036
 minerals-0.035
 seas-0.034
 favorites-0.034
 shells-0.034
Token had
Token ID550
Feature activation+1.35e-01

Pos logit contributions
iren+0.154
 earthquake+0.151
 aids+0.149
storm+0.142
 tornado+0.135
Neg logit contributions
 minerals-0.080
 seas-0.080
 ones-0.078
 one-0.078
 nic-0.076
Token a
Token ID257
Feature activation-1.32e-01

Pos logit contributions
iren+0.319
storm+0.311
 crash+0.290
 earthquake+0.287
 aids+0.287
Neg logit contributions
 seas-0.146
 shells-0.144
 minerals-0.139
 seaw-0.136
ishes-0.134
Token loud
Token ID7812
Feature activation+3.26e-01

Pos logit contributions
 seas+0.211
 luck+0.201
 minerals+0.200
 favorites+0.199
 seaw+0.199
Neg logit contributions
iren-0.225
aned-0.212
storm-0.210
 aids-0.203
maker-0.196
Token s
Token ID264
Feature activation+2.95e-01

Pos logit contributions
izz+0.428
storm+0.412
umpy+0.408
iren+0.407
amp+0.396
Neg logit contributions
 ones-0.572
 seaw-0.559
 luck-0.555
 dreams-0.554
 one-0.550
Tokeniren
Token ID24080
Feature activation+5.06e-01

Pos logit contributions
storm+0.106
 crash+0.090
 aids+0.069
 knock+0.062
 tornado+0.060
Neg logit contributions
ishes-0.866
 seas-0.842
sters-0.833
 seaw-0.829
 shells-0.825
Token and
Token ID290
Feature activation+2.71e-02

Pos logit contributions
iren+0.993
 aids+0.986
storm+0.983
unt+0.951
 earthquake+0.946
Neg logit contributions
ishes-0.604
 ones-0.586
sters-0.574
 luck-0.569
 seas-0.556
Token a
Token ID257
Feature activation-1.31e-01

Pos logit contributions
iren+0.060
storm+0.057
 crash+0.057
 aids+0.054
 earthquake+0.053
Neg logit contributions
ishes-0.032
 seas-0.031
 minerals-0.031
 shells-0.030
 favorites-0.030
Token long
Token ID890
Feature activation+7.56e-02

Pos logit contributions
 seas+0.228
 shells+0.221
 seaw+0.221
 ones+0.221
 minerals+0.216
Neg logit contributions
iren-0.196
aned-0.189
storm-0.186
 aids-0.176
 earthquake-0.170
Token hose
Token ID31489
Feature activation+1.49e-01

Pos logit contributions
iren+0.137
storm+0.129
 brewing+0.127
 aids+0.124
umpy+0.124
Neg logit contributions
 ones-0.105
 seas-0.102
 shells-0.098
 one-0.096
 seaw-0.094
Token.
Token ID13
Feature activation+2.41e-02

Pos logit contributions
iren+0.317
 aids+0.311
unt+0.310
 earthquake+0.293
loe+0.290
Neg logit contributions
 shells-0.162
ishes-0.160
sters-0.155
 ones-0.153
 seas-0.152
Tokenked
Token ID9091
Feature activation-1.01e-01

Pos logit contributions
ishes+0.142
 favorites+0.131
 seas+0.129
 shells+0.127
 minerals+0.125
Neg logit contributions
iren-0.210
 crash-0.200
storm-0.197
 earthquake-0.189
 knock-0.188
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
ishes+0.136
 ones+0.133
 shells+0.131
 luck+0.130
 minerals+0.128
Neg logit contributions
iren-0.213
storm-0.203
 outage-0.188
 earthquake-0.186
 crash-0.183
Token The
Token ID383
Feature activation+7.14e-02

Pos logit contributions
iren+0.041
storm+0.039
 crash+0.037
 brewing+0.036
 earthquake+0.036
Neg logit contributions
 favorites-0.032
 minerals-0.031
ishes-0.031
 dreams-0.031
 seas-0.030
Token ambulance
Token ID22536
Feature activation+2.80e-01

Pos logit contributions
aned+0.139
storm+0.139
anne+0.138
iren+0.137
 brewing+0.134
Neg logit contributions
 ones-0.095
 shells-0.088
 luck-0.087
 seas-0.087
 dreams-0.084
Token s
Token ID264
Feature activation+2.95e-01

Pos logit contributions
 earthquake+0.520
iren+0.501
arter+0.482
 aids+0.479
 tornado+0.477
Neg logit contributions
 ones-0.382
 shells-0.367
 seas-0.365
sters-0.357
ishes-0.354
Tokeniren
Token ID24080
Feature activation+5.06e-01

Pos logit contributions
 crash+0.283
storm+0.275
 knock+0.261
 tornado+0.254
 earthquake+0.253
Neg logit contributions
ishes-0.696
sters-0.666
 seas-0.641
 ones-0.629
 shells-0.621
Token w
Token ID266
Feature activation-2.97e-02

Pos logit contributions
 earthquake+1.009
iren+0.958
 tornado+0.943
 outage+0.939
storm+0.929
Neg logit contributions
 ones-0.628
 one-0.604
ishes-0.588
sters-0.585
 shells-0.573
Tokenailed
Token ID6255
Feature activation+2.47e-01

Pos logit contributions
ishes+0.046
sters+0.042
 luck+0.040
 seas+0.040
 shells+0.038
Neg logit contributions
 crash-0.055
storm-0.055
 knock-0.054
 outage-0.052
maker-0.050
Token.
Token ID13
Feature activation+2.35e-02

Pos logit contributions
iren+0.539
storm+0.516
 crash+0.495
 earthquake+0.479
 knock+0.475
Neg logit contributions
ishes-0.310
 luck-0.299
 ones-0.292
 minerals-0.287
 shells-0.286
Token The
Token ID383
Feature activation+7.21e-02

Pos logit contributions
iren+0.044
storm+0.043
 brewing+0.041
 earthquake+0.041
 crash+0.040
Neg logit contributions
 favorites-0.033
 dreams-0.032
 minerals-0.032
ishes-0.031
 ones-0.031
Token driver
Token ID4639
Feature activation+1.77e-01

Pos logit contributions
aned+0.131
anne+0.131
storm+0.128
iren+0.126
onna+0.124
Neg logit contributions
 ones-0.106
 seas-0.095
 luck-0.094
 shells-0.094
 dreams-0.093
Token to
Token ID284
Feature activation+6.45e-02

Pos logit contributions
iren+0.397
 crash+0.386
storm+0.358
 knock+0.347
 aids+0.341
Neg logit contributions
ishes-0.547
 favorites-0.506
 seas-0.497
 minerals-0.488
sters-0.484
Token speak
Token ID2740
Feature activation+5.23e-02

Pos logit contributions
iren+0.122
storm+0.111
 crash+0.110
 aids+0.104
aned+0.102
Neg logit contributions
ishes-0.098
 minerals-0.096
 shells-0.095
 seaw-0.095
 luck-0.094
Token when
Token ID618
Feature activation-1.47e-01

Pos logit contributions
iren+0.093
 crash+0.087
storm+0.085
 knock+0.080
 earthquake+0.079
Neg logit contributions
ishes-0.089
 minerals-0.083
 seas-0.083
 favorites-0.083
 shells-0.082
Token a
Token ID257
Feature activation-1.28e-01

Pos logit contributions
 minerals+0.173
 seas+0.173
ishes+0.173
 shells+0.168
 favorites+0.160
Neg logit contributions
iren-0.329
storm-0.304
 crash-0.303
 aids-0.293
aned-0.287
Token s
Token ID264
Feature activation+2.95e-01

Pos logit contributions
 seas+0.211
 seaw+0.202
 minerals+0.202
 luck+0.200
 shells+0.200
Neg logit contributions
iren-0.221
aned-0.218
storm-0.202
 crash-0.198
 aids-0.192
Tokeniren
Token ID24080
Feature activation+5.05e-01

Pos logit contributions
 crash+0.119
storm+0.110
 knock+0.081
 tornado+0.075
 ripping+0.070
Neg logit contributions
ishes-0.855
sters-0.832
 seas-0.819
 seaw-0.805
 shells-0.802
Token sounded
Token ID14846
Feature activation+5.27e-02

Pos logit contributions
iren+0.913
 aids+0.859
 earthquake+0.825
 crash+0.823
 outage+0.807
Neg logit contributions
ishes-0.717
 ones-0.689
sters-0.661
 seas-0.657
 minerals-0.641
Token,
Token ID11
Feature activation-2.76e-02

Pos logit contributions
iren+0.105
 crash+0.097
storm+0.096
lf+0.091
 aids+0.090
Neg logit contributions
ishes-0.076
 luck-0.074
 seas-0.074
 minerals-0.074
 shells-0.074
Token making
Token ID1642
Feature activation+1.73e-01

Pos logit contributions
ishes+0.044
 seas+0.041
 favorites+0.040
 minerals+0.040
 shells+0.040
Neg logit contributions
iren-0.052
 crash-0.049
storm-0.048
 knock-0.046
 aids-0.045
Token both
Token ID1111
Feature activation-9.00e-02

Pos logit contributions
iren+0.360
storm+0.341
 crash+0.334
 knock+0.314
 earthquake+0.310
Neg logit contributions
ishes-0.237
 minerals-0.223
 seas-0.222
 favorites-0.219
 shells-0.219
Token of
Token ID286
Feature activation+2.85e-01

Pos logit contributions
ishes+0.163
 dreams+0.160
 shells+0.158
 experiences+0.155
 ones+0.154
Neg logit contributions
iren-0.132
storm-0.131
aned-0.119
 crash-0.114
lf-0.113
Token It
Token ID632
Feature activation+7.35e-02

Pos logit contributions
iren+0.030
 crash+0.028
storm+0.027
 knock+0.025
 earthquake+0.025
Neg logit contributions
ishes-0.032
 favorites-0.030
 minerals-0.030
 seas-0.030
 shells-0.029
Token was
Token ID373
Feature activation+8.19e-02

Pos logit contributions
iren+0.166
 earthquake+0.149
 aids+0.149
maker+0.143
onna+0.142
Neg logit contributions
 one-0.069
 dreams-0.068
 ones-0.067
 seaw-0.065
 nic-0.063
Token an
Token ID281
Feature activation-1.71e-01

Pos logit contributions
iren+0.209
aned+0.201
storm+0.193
umpy+0.189
lf+0.187
Neg logit contributions
 something-0.068
 one-0.064
 ones-0.062
 seaw-0.060
 luck-0.059
Token emergency
Token ID6334
Feature activation+3.61e-01

Pos logit contributions
 seaw+0.293
 minerals+0.290
ishes+0.289
ish+0.289
 luck+0.289
Neg logit contributions
iren-0.249
 crash-0.230
storm-0.228
t-0.222
't-0.220
Token s
Token ID264
Feature activation+2.94e-01

Pos logit contributions
iren+0.689
 aids+0.662
aned+0.637
 crash+0.623
umpy+0.597
Neg logit contributions
 ones-0.493
ishes-0.474
 luck-0.458
 minerals-0.449
 seas-0.445
Tokeniren
Token ID24080
Feature activation+5.04e-01

Pos logit contributions
 crash+0.198
 aids+0.171
storm+0.167
 knock+0.164
 tornado+0.142
Neg logit contributions
ishes-0.749
 seas-0.735
sters-0.732
 seaw-0.705
 ones-0.704
Token.
Token ID13
Feature activation+2.00e-02

Pos logit contributions
iren+1.023
 aids+0.985
 crash+0.943
storm+0.927
 earthquake+0.911
Neg logit contributions
ishes-0.620
 ones-0.576
sters-0.566
 luck-0.559
 minerals-0.547
Token
Token ID198
Feature activation+5.85e-03

Pos logit contributions
iren+0.035
 crash+0.033
storm+0.031
 aids+0.030
 knock+0.030
Neg logit contributions
ishes-0.035
 seas-0.033
 favorites-0.033
 minerals-0.033
 shells-0.032
Token
Token ID198
Feature activation+6.21e-03

Pos logit contributions
storm+0.012
iren+0.012
 crash+0.012
 earthquake+0.012
 knock+0.011
Neg logit contributions
 favorites-0.007
ishes-0.007
 seas-0.007
 minerals-0.007
 shells-0.007
Token"
Token ID1
Feature activation+1.78e-02

Pos logit contributions
iren+0.012
 crash+0.011
storm+0.011
 knock+0.010
 earthquake+0.010
Neg logit contributions
ishes-0.010
 favorites-0.009
 seas-0.009
 minerals-0.009
 shells-0.009
TokenMom
Token ID29252
Feature activation+9.40e-02

Pos logit contributions
iren+0.034
 crash+0.032
 earthquake+0.030
storm+0.030
aned+0.030
Neg logit contributions
ishes-0.025
 favorites-0.024
 seas-0.024
 seaw-0.024
 ones-0.024
Token they
Token ID484
Feature activation-2.18e-02

Pos logit contributions
ishes+0.076
 minerals+0.070
 favorites+0.069
 seaw+0.069
 seas+0.068
Neg logit contributions
 crash-0.049
iren-0.049
 knock-0.047
storm-0.045
 collapse-0.043
Token heard
Token ID2982
Feature activation+3.90e-02

Pos logit contributions
ishes+0.033
 seas+0.031
 shells+0.030
 favorites+0.030
 minerals+0.030
Neg logit contributions
iren-0.044
 crash-0.041
storm-0.040
 aids-0.039
 earthquake-0.038
Token a
Token ID257
Feature activation-1.43e-01

Pos logit contributions
iren+0.095
storm+0.092
 crash+0.091
aned+0.087
 earthquake+0.084
Neg logit contributions
 shells-0.037
 seas-0.037
ishes-0.036
 minerals-0.036
 favorites-0.035
Token loud
Token ID7812
Feature activation+3.18e-01

Pos logit contributions
 seaw+0.288
 minerals+0.272
 luck+0.272
 shells+0.272
 seas+0.269
Neg logit contributions
iren-0.174
aned-0.169
storm-0.166
 aids-0.147
 brewing-0.142
Token s
Token ID264
Feature activation+2.88e-01

Pos logit contributions
 cancelled+0.431
aned+0.423
case+0.415
umpy+0.413
 collapsed+0.412
Neg logit contributions
 dreams-0.499
 seaw-0.494
 one-0.487
 ones-0.482
 minerals-0.451
Tokeniren
Token ID24080
Feature activation+5.04e-01

Pos logit contributions
storm+0.118
 crash+0.103
 aids+0.071
 tornado+0.068
 earthquake+0.065
Neg logit contributions
ishes-0.834
sters-0.805
 seas-0.791
minded-0.784
 shells-0.783
Token outside
Token ID2354
Feature activation+1.42e-01

Pos logit contributions
 aids+1.116
loe+1.076
onna+1.071
unt+1.058
storm+1.056
Neg logit contributions
 ones-0.409
ishes-0.392
 one-0.391
sters-0.388
 luck-0.362
Token.
Token ID13
Feature activation+1.62e-02

Pos logit contributions
aned+0.386
storm+0.376
iren+0.373
drop+0.355
unt+0.352
Neg logit contributions
 ones-0.075
 dreams-0.068
 something-0.066
 one-0.065
 if-0.061
Token They
Token ID1119
Feature activation+3.49e-02

Pos logit contributions
iren+0.031
storm+0.030
 crash+0.030
aned+0.029
lf+0.028
Neg logit contributions
 minerals-0.023
ishes-0.023
 favorites-0.023
 seas-0.022
 shells-0.022
Token looked
Token ID3114
Feature activation-1.92e-02

Pos logit contributions
iren+0.067
storm+0.063
 crash+0.061
 aids+0.060
 earthquake+0.058
Neg logit contributions
ishes-0.055
 shells-0.051
 seas-0.051
 minerals-0.050
 seaw-0.050
Token out
Token ID503
Feature activation-2.35e-02

Pos logit contributions
ishes+0.037
 favorites+0.035
 seas+0.035
 minerals+0.035
 shells+0.034
Neg logit contributions
iren-0.029
 crash-0.028
storm-0.026
 knock-0.025
 aids-0.025
Token He
Token ID679
Feature activation-7.10e-02

Pos logit contributions
ishes+0.130
 seas+0.122
 favorites+0.121
 minerals+0.120
 shells+0.119
Neg logit contributions
iren-0.122
 crash-0.116
storm-0.111
 aids-0.106
 knock-0.105
Token found
Token ID1043
Feature activation-1.50e-01

Pos logit contributions
ishes+0.122
 seas+0.114
 favorites+0.114
 minerals+0.114
 shells+0.111
Neg logit contributions
iren-0.123
 crash-0.117
storm-0.112
 knock-0.108
 aids-0.106
Token some
Token ID617
Feature activation-3.01e-01

Pos logit contributions
ishes+0.200
 favorites+0.187
sters+0.182
 experiences+0.180
esty+0.177
Neg logit contributions
iren-0.309
 crash-0.295
 aids-0.271
 knock-0.271
storm-0.268
Token big
Token ID1263
Feature activation+8.87e-02

Pos logit contributions
ishes+0.463
 favorites+0.431
 seas+0.425
 minerals+0.418
 shells+0.410
Neg logit contributions
iren-0.574
 crash-0.545
storm-0.520
 knock-0.505
 aids-0.498
Token rad
Token ID2511
Feature activation-1.60e-01

Pos logit contributions
iren+0.170
 crash+0.169
 knock+0.154
 earthquake+0.151
storm+0.148
Neg logit contributions
ishes-0.116
esty-0.114
 favorites-0.113
 seas-0.109
sters-0.107
Tokenishes
Token ID5614
Feature activation-5.07e-01

Pos logit contributions
 Majesty+0.156
 dreams+0.150
 Anything+0.141
 experiences+0.140
 amaz+0.138
Neg logit contributions
iren-0.332
 crash-0.305
oe-0.301
maker-0.297
 burned-0.286
Token in
Token ID287
Feature activation+1.32e-02

Pos logit contributions
ishes+0.901
 favorites+0.860
 seas+0.848
 minerals+0.835
 shells+0.819
Neg logit contributions
iren-0.842
 crash-0.797
storm-0.766
 knock-0.723
 aids-0.711
Token a
Token ID257
Feature activation-1.98e-01

Pos logit contributions
iren+0.022
 crash+0.021
storm+0.019
 knock+0.019
 aids+0.018
Neg logit contributions
ishes-0.024
 favorites-0.023
 seas-0.023
 minerals-0.022
 shells-0.022
Token garden
Token ID11376
Feature activation-1.50e-01

Pos logit contributions
ishes+0.323
 seas+0.304
 minerals+0.301
 favorites+0.300
 shells+0.297
Neg logit contributions
iren-0.365
 crash-0.344
storm-0.335
 aids-0.317
 knock-0.316
Token and
Token ID290
Feature activation-3.34e-02

Pos logit contributions
ishes+0.261
 favorites+0.244
 seas+0.242
 minerals+0.241
 shells+0.236
Neg logit contributions
iren-0.260
 crash-0.246
storm-0.238
 knock-0.226
 aids-0.224
Token ate
Token ID15063
Feature activation+1.37e-02

Pos logit contributions
ishes+0.059
 favorites+0.056
 seas+0.054
 luck+0.053
 minerals+0.053
Neg logit contributions
iren-0.053
 crash-0.052
 knock-0.050
storm-0.050
 aids-0.047
Token Benny
Token ID44275
Feature activation-1.55e-01

Pos logit contributions
ishes+0.095
 favorites+0.089
 seas+0.088
 minerals+0.088
 shells+0.086
Neg logit contributions
iren-0.093
 crash-0.089
storm-0.085
 knock-0.081
 aids-0.080
Token happily
Token ID18177
Feature activation-6.99e-02

Pos logit contributions
ishes+0.277
 favorites+0.259
 seas+0.259
 minerals+0.258
 shells+0.254
Neg logit contributions
iren-0.260
 crash-0.243
storm-0.237
 aids-0.223
 knock-0.222
Token ate
Token ID15063
Feature activation+6.95e-03

Pos logit contributions
ishes+0.130
 favorites+0.124
 seas+0.122
 minerals+0.122
 shells+0.118
Neg logit contributions
iren-0.111
 crash-0.106
storm-0.101
 knock-0.097
 aids-0.093
Token his
Token ID465
Feature activation-7.75e-02

Pos logit contributions
iren+0.010
 crash+0.010
storm+0.009
 earthquake+0.008
 knock+0.008
Neg logit contributions
ishes-0.014
 favorites-0.013
sters-0.013
esty-0.012
 seas-0.012
Token rad
Token ID2511
Feature activation-1.57e-01

Pos logit contributions
ishes+0.130
 favorites+0.116
esty+0.112
sters+0.112
 minerals+0.111
Neg logit contributions
iren-0.132
 crash-0.132
 knock-0.123
storm-0.123
 earthquake-0.122
Tokenishes
Token ID5614
Feature activation-5.02e-01

Pos logit contributions
 islands+0.167
 Anything+0.160
 seaw+0.159
 props+0.157
 galaxies+0.155
Neg logit contributions
 crash-0.276
iren-0.271
 hurt-0.267
oe-0.263
 burned-0.256
Token.
Token ID13
Feature activation-5.10e-02

Pos logit contributions
ishes+0.917
 favorites+0.885
 seas+0.847
 minerals+0.841
 shells+0.815
Neg logit contributions
iren-0.792
 crash-0.762
storm-0.733
 knock-0.679
 brewing-0.674
Token
Token ID198
Feature activation-6.35e-02

Pos logit contributions
ishes+0.096
 seas+0.091
 shells+0.090
 seaw+0.088
 luck+0.088
Neg logit contributions
iren-0.081
 crash-0.077
storm-0.074
 aids-0.069
 knock-0.068
Token
Token ID198
Feature activation-6.02e-02

Pos logit contributions
ishes+0.122
 minerals+0.118
 seas+0.118
 favorites+0.118
 shells+0.116
Neg logit contributions
iren-0.094
 crash-0.088
storm-0.087
 earthquake-0.082
 knock-0.080
TokenFrom
Token ID4863
Feature activation+3.98e-02

Pos logit contributions
ishes+0.105
 favorites+0.097
 seas+0.097
 minerals+0.096
 shells+0.095
Neg logit contributions
iren-0.106
 crash-0.100
storm-0.097
 knock-0.092
 aids-0.091
Token that
Token ID326
Feature activation+2.47e-02

Pos logit contributions
iren+0.059
 crash+0.055
storm+0.054
 knock+0.051
 earthquake+0.051
Neg logit contributions
ishes-0.080
 favorites-0.076
 seas-0.072
 minerals-0.072
 seaw-0.071
Token ch
Token ID442
Feature activation-1.22e-01

Pos logit contributions
ishes+0.298
 favorites+0.274
 seas+0.274
 shells+0.271
 minerals+0.269
Neg logit contributions
iren-0.329
 crash-0.307
storm-0.297
 aids-0.286
 knock-0.285
Tokenir
Token ID343
Feature activation+1.07e-01

Pos logit contributions
ishes+0.278
 seas+0.261
 favorites+0.261
 shells+0.258
 minerals+0.258
Neg logit contributions
iren-0.148
 crash-0.138
storm-0.133
 knock-0.124
 aids-0.120
Tokenping
Token ID13886
Feature activation+1.37e-01

Pos logit contributions
iren+0.137
 crash+0.127
storm+0.122
 knock+0.121
 aids+0.112
Neg logit contributions
ishes-0.234
 shells-0.215
 seas-0.215
 favorites-0.213
 minerals-0.213
Token and
Token ID290
Feature activation-7.89e-02

Pos logit contributions
iren+0.265
 crash+0.244
storm+0.239
 knock+0.236
 outage+0.228
Neg logit contributions
ishes-0.211
 seas-0.195
 shells-0.194
 minerals-0.192
 ones-0.191
Token gather
Token ID6431
Feature activation-1.29e-01

Pos logit contributions
ishes+0.142
 minerals+0.133
 seas+0.133
 favorites+0.132
 shells+0.131
Neg logit contributions
iren-0.132
 crash-0.122
storm-0.119
 aids-0.112
 knock-0.111
Token shells
Token ID19679
Feature activation-5.00e-01

Pos logit contributions
ishes+0.219
 seas+0.204
 favorites+0.204
 minerals+0.203
 shells+0.200
Neg logit contributions
iren-0.229
 crash-0.217
storm-0.211
 knock-0.200
 aids-0.198
Token nearby
Token ID6716
Feature activation+3.56e-02

Pos logit contributions
ishes+0.930
 favorites+0.905
 minerals+0.868
 seas+0.862
 seaw+0.846
Neg logit contributions
iren-0.758
 crash-0.707
storm-0.692
 brewing-0.628
 aids-0.624
Token."
Token ID526
Feature activation-8.30e-02

Pos logit contributions
iren+0.064
 crash+0.061
storm+0.059
 knock+0.056
 aids+0.056
Neg logit contributions
ishes-0.058
 favorites-0.054
 seas-0.054
 minerals-0.054
 shells-0.053
Token
Token ID198
Feature activation-7.15e-02

Pos logit contributions
ishes+0.131
 favorites+0.124
 minerals+0.122
 seas+0.121
 shells+0.120
Neg logit contributions
iren-0.154
 crash-0.147
storm-0.143
 knock-0.135
 earthquake-0.135
Token
Token ID198
Feature activation-6.30e-02

Pos logit contributions
ishes+0.081
 favorites+0.079
 minerals+0.078
 seas+0.078
 shells+0.077
Neg logit contributions
storm-0.151
 crash-0.151
iren-0.149
 earthquake-0.145
 knock-0.139
TokenS
Token ID50
Feature activation-5.50e-03

Pos logit contributions
ishes+0.098
 minerals+0.094
 favorites+0.094
 seas+0.094
 shells+0.093
Neg logit contributions
iren-0.111
 crash-0.109
storm-0.105
 earthquake-0.100
 knock-0.097
Token the
Token ID262
Feature activation-6.21e-03

Pos logit contributions
iren+0.020
 crash+0.019
storm+0.018
 knock+0.017
 aids+0.017
Neg logit contributions
ishes-0.022
 favorites-0.021
 seas-0.020
 minerals-0.020
 shells-0.020
Token biggest
Token ID4094
Feature activation-3.73e-01

Pos logit contributions
ishes+0.010
 favorites+0.010
 minerals+0.009
 seas+0.009
 shells+0.009
Neg logit contributions
iren-0.011
 crash-0.011
storm-0.010
 knock-0.010
 aids-0.010
Token and
Token ID290
Feature activation-4.33e-02

Pos logit contributions
ishes+0.618
 seas+0.586
 minerals+0.584
 favorites+0.581
 shells+0.575
Neg logit contributions
iren-0.669
 crash-0.626
storm-0.613
 aids-0.579
 knock-0.575
Token best
Token ID1266
Feature activation-3.51e-01

Pos logit contributions
ishes+0.085
 favorites+0.079
sters+0.075
 seas+0.072
ish+0.071
Neg logit contributions
 crash-0.065
iren-0.064
 knock-0.062
 knocking-0.056
 annoying-0.056
Token rad
Token ID2511
Feature activation-1.51e-01

Pos logit contributions
ishes+0.603
 favorites+0.565
 seas+0.565
 minerals+0.564
 shells+0.555
Neg logit contributions
iren-0.616
 crash-0.580
storm-0.564
 knock-0.532
 aids-0.531
Tokenishes
Token ID5614
Feature activation-5.00e-01

Pos logit contributions
 seaw+0.116
 coral+0.112
 dreams+0.112
 seas+0.107
 amaz+0.095
Neg logit contributions
iren-0.360
maker-0.357
 crash-0.329
storm-0.325
makers-0.322
Token.
Token ID13
Feature activation-3.77e-02

Pos logit contributions
ishes+0.879
 favorites+0.825
 seas+0.820
 minerals+0.816
 shells+0.802
Neg logit contributions
iren-0.847
 crash-0.801
storm-0.774
 knock-0.731
 aids-0.726
Token Every
Token ID3887
Feature activation-6.79e-02

Pos logit contributions
ishes+0.070
 seas+0.065
 shells+0.064
 luck+0.064
 seaw+0.063
Neg logit contributions
iren-0.062
 crash-0.058
storm-0.055
 aids-0.054
 knock-0.053
Token day
Token ID1110
Feature activation+3.23e-02

Pos logit contributions
ishes+0.125
 seas+0.124
 minerals+0.122
 favorites+0.122
 shells+0.119
Neg logit contributions
iren-0.109
 crash-0.100
storm-0.094
 knock-0.090
aned-0.089
Token he
Token ID339
Feature activation-1.79e-01

Pos logit contributions
iren+0.064
 crash+0.061
storm+0.059
 knock+0.057
 aids+0.056
Neg logit contributions
ishes-0.048
 favorites-0.044
 seas-0.044
 minerals-0.044
 shells-0.043
Token took
Token ID1718
Feature activation+4.87e-03

Pos logit contributions
ishes+0.247
 seas+0.229
 favorites+0.228
 minerals+0.226
 shells+0.221
Neg logit contributions
iren-0.368
 crash-0.354
storm-0.345
 knock-0.334
 aids-0.327
TokenWhy
Token ID5195
Feature activation-2.66e-02

Pos logit contributions
ishes+0.026
 favorites+0.025
 seas+0.025
 minerals+0.024
 shells+0.024
Neg logit contributions
iren-0.024
storm-0.022
 crash-0.022
 aids-0.020
 knock-0.019
Token do
Token ID466
Feature activation-3.04e-02

Pos logit contributions
ishes+0.039
 favorites+0.036
 seas+0.036
 minerals+0.035
 shells+0.035
Neg logit contributions
iren-0.054
 crash-0.051
storm-0.050
 knock-0.048
 aids-0.047
Token you
Token ID345
Feature activation-1.65e-01

Pos logit contributions
ishes+0.038
 seas+0.036
 minerals+0.036
 favorites+0.035
 shells+0.034
Neg logit contributions
iren-0.066
 crash-0.063
storm-0.062
 knock-0.059
 aids-0.059
Token like
Token ID588
Feature activation-1.78e-01

Pos logit contributions
ishes+0.204
 minerals+0.200
 seaw+0.199
 favorites+0.198
 shells+0.194
Neg logit contributions
iren-0.357
storm-0.316
 crash-0.308
 aids-0.301
 brewing-0.299
Token rad
Token ID2511
Feature activation-1.53e-01

Pos logit contributions
 minerals+0.264
 shells+0.260
ishes+0.255
 seas+0.254
 ones+0.250
Neg logit contributions
iren-0.356
storm-0.332
 collapse-0.320
aned-0.320
 crash-0.319
Tokenishes
Token ID5614
Feature activation-4.99e-01

Pos logit contributions
 seaw+0.126
 seas+0.125
 Something+0.121
 Anything+0.121
 coral+0.117
Neg logit contributions
iren-0.334
 crash-0.311
 hitting-0.309
 hurting-0.301
 earthquake-0.299
Token?
Token ID30
Feature activation-1.07e-01

Pos logit contributions
ishes+0.788
 minerals+0.729
 seas+0.722
 favorites+0.721
 shells+0.712
Neg logit contributions
iren-0.949
 crash-0.896
storm-0.870
 knock-0.834
 aids-0.832
Token They
Token ID1119
Feature activation-2.91e-02

Pos logit contributions
ishes+0.191
 seas+0.185
 shells+0.178
 favorites+0.177
 seaw+0.174
Neg logit contributions
iren-0.181
 crash-0.170
storm-0.162
 knock-0.157
 aids-0.155
Token're
Token ID821
Feature activation-3.11e-01

Pos logit contributions
ishes+0.046
 seas+0.045
 favorites+0.044
 minerals+0.042
 shells+0.042
Neg logit contributions
 crash-0.052
iren-0.051
storm-0.048
 knock-0.048
 earthquake-0.046
Token not
Token ID407
Feature activation+1.54e-01

Pos logit contributions
ishes+0.473
 minerals+0.467
 shells+0.439
 favorites+0.434
 luck+0.432
Neg logit contributions
iren-0.641
storm-0.586
 crash-0.564
 outage-0.539
 aids-0.535
Token very
Token ID845
Feature activation-3.01e-03

Pos logit contributions
iren+0.287
storm+0.263
 crash+0.260
 aids+0.244
 knock+0.241
Neg logit contributions
ishes-0.261
 minerals-0.246
 shells-0.238
 favorites-0.238
 seas-0.237
Token foods
Token ID9013
Feature activation-4.12e-01

Pos logit contributions
ishes+0.239
 favorites+0.218
 minerals+0.216
 seas+0.214
 shells+0.209
Neg logit contributions
iren-0.285
 crash-0.274
storm-0.267
 knock-0.253
 aids-0.252
Token and
Token ID290
Feature activation-7.67e-02

Pos logit contributions
ishes+0.710
 favorites+0.663
 seas+0.660
 minerals+0.657
 shells+0.645
Neg logit contributions
iren-0.712
 crash-0.671
storm-0.651
 knock-0.615
 aids-0.612
Token discovered
Token ID5071
Feature activation-2.55e-01

Pos logit contributions
ishes+0.129
 favorites+0.120
 seas+0.120
sters+0.116
esty+0.114
Neg logit contributions
 crash-0.127
iren-0.122
 knock-0.121
storm-0.116
 aids-0.114
Token many
Token ID867
Feature activation-2.14e-01

Pos logit contributions
ishes+0.404
 favorites+0.375
 minerals+0.361
 seas+0.360
 seaw+0.352
Neg logit contributions
iren-0.470
 crash-0.443
storm-0.424
 aids-0.421
 knock-0.414
Token new
Token ID649
Feature activation-1.32e-01

Pos logit contributions
ishes+0.300
 favorites+0.273
 seas+0.267
 minerals+0.263
sters+0.259
Neg logit contributions
iren-0.429
 crash-0.408
storm-0.389
 knock-0.385
 aids-0.383
Token favorites
Token ID18852
Feature activation-4.96e-01

Pos logit contributions
ishes+0.150
esty+0.130
 favorites+0.129
 seas+0.128
 seaw+0.125
Neg logit contributions
iren-0.291
 crash-0.280
storm-0.267
 aids-0.267
 knock-0.265
Token.
Token ID13
Feature activation-7.38e-02

Pos logit contributions
ishes+0.776
 minerals+0.737
 shells+0.730
 seas+0.724
 favorites+0.715
Neg logit contributions
iren-0.967
 crash-0.914
storm-0.894
 knock-0.840
 aids-0.835
Token He
Token ID679
Feature activation-6.82e-02

Pos logit contributions
ishes+0.137
 seas+0.128
 shells+0.125
 seaw+0.125
 luck+0.125
Neg logit contributions
iren-0.120
 crash-0.112
storm-0.107
 aids-0.105
 knock-0.102
Token learned
Token ID4499
Feature activation-1.36e-01

Pos logit contributions
ishes+0.120
 favorites+0.113
 seas+0.112
 minerals+0.112
 shells+0.110
Neg logit contributions
iren-0.116
 crash-0.109
storm-0.106
 knock-0.100
 aids-0.100
Token that
Token ID326
Feature activation+1.40e-02

Pos logit contributions
ishes+0.248
 favorites+0.231
 seas+0.220
 minerals+0.218
 seaw+0.215
Neg logit contributions
iren-0.227
 crash-0.212
 aids-0.200
storm-0.197
 knock-0.194
Token it
Token ID340
Feature activation-3.69e-02

Pos logit contributions
iren+0.025
 crash+0.025
storm+0.024
 knock+0.023
 earthquake+0.023
Neg logit contributions
ishes-0.023
 favorites-0.021
 seas-0.020
sters-0.019
 shells-0.019
Token were
Token ID547
Feature activation-1.24e-01

Pos logit contributions
iren+0.045
 crash+0.041
storm+0.041
lf+0.040
 brewing+0.039
Neg logit contributions
ishes-0.034
 favorites-0.032
 minerals-0.031
 seas-0.030
 shells-0.030
Token shiny
Token ID22441
Feature activation-1.15e-01

Pos logit contributions
ishes+0.177
 shells+0.175
 seas+0.175
 luck+0.172
 favorites+0.171
Neg logit contributions
iren-0.257
storm-0.236
 crash-0.233
 outage-0.216
 knock-0.216
Token rocks
Token ID12586
Feature activation-3.53e-01

Pos logit contributions
ishes+0.229
 favorites+0.221
esty+0.216
 Majesty+0.209
sters+0.207
Neg logit contributions
iren-0.147
 crash-0.146
storm-0.139
 earthquake-0.135
 knock-0.128
Token and
Token ID290
Feature activation-6.92e-02

Pos logit contributions
ishes+0.570
 seas+0.541
 minerals+0.535
 shells+0.528
 favorites+0.524
Neg logit contributions
iren-0.649
 crash-0.608
storm-0.582
 aids-0.578
 knock-0.569
Token pretty
Token ID2495
Feature activation-1.01e-01

Pos logit contributions
ishes+0.119
 favorites+0.113
sters+0.106
 seas+0.105
 luck+0.105
Neg logit contributions
 crash-0.118
iren-0.112
 knock-0.109
storm-0.103
 knocking-0.100
Token shells
Token ID19679
Feature activation-4.94e-01

Pos logit contributions
ishes+0.147
esty+0.141
 favorites+0.139
 nic+0.128
sters+0.128
Neg logit contributions
 crash-0.179
iren-0.177
storm-0.168
 knock-0.161
 earthquake-0.157
Token.
Token ID13
Feature activation-6.50e-02

Pos logit contributions
ishes+0.830
 favorites+0.773
 seas+0.773
 minerals+0.770
 shells+0.757
Neg logit contributions
iren-0.880
 crash-0.833
storm-0.805
 knock-0.766
 aids-0.762
Token Fin
Token ID4463
Feature activation-1.54e-01

Pos logit contributions
ishes+0.125
 seas+0.117
 favorites+0.115
 minerals+0.115
 shells+0.114
Neg logit contributions
iren-0.102
 crash-0.096
storm-0.091
 aids-0.087
 knock-0.087
Token was
Token ID373
Feature activation-9.47e-05

Pos logit contributions
ishes+0.275
 seas+0.265
 favorites+0.261
 minerals+0.257
 shells+0.254
Neg logit contributions
iren-0.242
 crash-0.235
storm-0.221
 knock-0.217
 aids-0.205
Token very
Token ID845
Feature activation-1.55e-02

Pos logit contributions
ishes+0.000
 favorites+0.000
 seas+0.000
 shells+0.000
 minerals+0.000
Neg logit contributions
iren-0.000
storm-0.000
 crash-0.000
 aids-0.000
 earthquake-0.000
Token happy
Token ID3772
Feature activation-1.78e-02

Pos logit contributions
ishes+0.025
 favorites+0.024
 minerals+0.024
 seas+0.024
 shells+0.024
Neg logit contributions
iren-0.028
 crash-0.027
storm-0.027
 aids-0.025
 earthquake-0.024
Token where
Token ID810
Feature activation-9.11e-02

Pos logit contributions
 minerals+0.057
ishes+0.056
 seas+0.056
 ones+0.055
 luck+0.055
Neg logit contributions
iren-0.075
aned-0.069
 crash-0.069
 knock-0.066
 aids-0.065
Token everyone
Token ID2506
Feature activation+7.52e-03

Pos logit contributions
ishes+0.123
 minerals+0.117
 seas+0.115
 shells+0.114
 favorites+0.112
Neg logit contributions
iren-0.193
 crash-0.181
storm-0.179
 knock-0.170
 aids-0.169
Token shared
Token ID4888
Feature activation-1.10e-01

Pos logit contributions
iren+0.015
 crash+0.014
storm+0.013
 aids+0.013
 earthquake+0.013
Neg logit contributions
ishes-0.011
 minerals-0.011
 shells-0.010
 favorites-0.010
 seas-0.010
Token their
Token ID511
Feature activation+1.05e-02

Pos logit contributions
ishes+0.190
 favorites+0.176
 seas+0.174
 minerals+0.174
 shells+0.170
Neg logit contributions
iren-0.186
 crash-0.179
storm-0.169
 aids-0.166
 knock-0.162
Token rad
Token ID2511
Feature activation-1.48e-01

Pos logit contributions
iren+0.022
 crash+0.021
storm+0.020
 knock+0.020
 aids+0.020
Neg logit contributions
ishes-0.014
 favorites-0.013
 seas-0.013
 minerals-0.013
 shells-0.013
Tokenishes
Token ID5614
Feature activation-4.93e-01

Pos logit contributions
 seas+0.106
 seaw+0.100
 yes+0.085
 Anything+0.084
 nic+0.077
Neg logit contributions
iren-0.336
 crash-0.321
umpy-0.310
 earthquake-0.304
 harm-0.301
Token.
Token ID13
Feature activation-3.55e-02

Pos logit contributions
ishes+0.922
 favorites+0.885
 seas+0.870
 minerals+0.847
 seaw+0.837
Neg logit contributions
iren-0.751
 crash-0.709
storm-0.677
 aids-0.659
 earthquake-0.634
Token<|endoftext|>
Token ID50256
Feature activation+1.11e-01

Pos logit contributions
ishes+0.064
 seas+0.059
 favorites+0.058
 shells+0.058
 minerals+0.058
Neg logit contributions
iren-0.060
 crash-0.057
storm-0.055
 aids-0.052
 knock-0.052
TokenOnce
Token ID7454
Feature activation-2.40e-02

Pos logit contributions
iren+0.225
 crash+0.216
storm+0.212
 knock+0.204
 earthquake+0.202
Neg logit contributions
ishes-0.153
 seas-0.146
 favorites-0.145
 minerals-0.144
 shells-0.140
Token upon
Token ID2402
Feature activation-2.41e-01

Pos logit contributions
ishes+0.018
 seas+0.016
 favorites+0.016
 minerals+0.015
 shells+0.014
Neg logit contributions
iren-0.066
 crash-0.063
storm-0.063
 aids-0.060
 knock-0.060
Token a
Token ID257
Feature activation-1.86e-01

Pos logit contributions
ishes+0.487
sters+0.409
 favorites+0.406
ish+0.404
esty+0.393
Neg logit contributions
 crash-0.398
iren-0.381
't-0.366
ggy-0.363
 knock-0.361
Token saw
Token ID2497
Feature activation-1.13e-01

Pos logit contributions
iren+0.037
 crash+0.034
 knock+0.032
storm+0.031
 aids+0.029
Neg logit contributions
ishes-0.043
 favorites-0.041
 minerals-0.039
 seas-0.039
 luck-0.038
Token fish
Token ID5916
Feature activation-3.15e-01

Pos logit contributions
ishes+0.144
 seas+0.137
 shells+0.137
 minerals+0.136
 favorites+0.133
Neg logit contributions
iren-0.245
 crash-0.234
storm-0.231
 knock-0.217
 earthquake-0.214
Token and
Token ID290
Feature activation-6.71e-02

Pos logit contributions
ishes+0.501
 seas+0.466
 minerals+0.464
 shells+0.463
 seaw+0.455
Neg logit contributions
iren-0.598
 crash-0.557
storm-0.547
 aids-0.519
 knock-0.517
Token crabs
Token ID49172
Feature activation-3.74e-01

Pos logit contributions
ishes+0.097
 favorites+0.091
 seas+0.089
 minerals+0.087
 shells+0.084
Neg logit contributions
iren-0.132
 crash-0.131
storm-0.124
 knock-0.122
 aids-0.120
Token and
Token ID290
Feature activation-5.75e-02

Pos logit contributions
ishes+0.609
 seas+0.567
 minerals+0.564
 favorites+0.562
 shells+0.562
Neg logit contributions
iren-0.691
 crash-0.648
storm-0.631
 aids-0.601
 knock-0.600
Token shells
Token ID19679
Feature activation-4.92e-01

Pos logit contributions
ishes+0.076
 favorites+0.072
esty+0.066
 seas+0.065
sters+0.064
Neg logit contributions
 crash-0.120
iren-0.113
 knock-0.111
storm-0.109
 aids-0.107
Token.
Token ID13
Feature activation-6.15e-02

Pos logit contributions
ishes+0.854
 favorites+0.807
 minerals+0.795
 seas+0.794
 shells+0.772
Neg logit contributions
iren-0.843
 crash-0.798
storm-0.770
 knock-0.724
 aids-0.720
Token They
Token ID1119
Feature activation-1.62e-02

Pos logit contributions
ishes+0.123
 seas+0.116
 favorites+0.115
 luck+0.113
 minerals+0.113
Neg logit contributions
iren-0.090
 crash-0.085
storm-0.080
 aids-0.077
 knock-0.077
Token also
Token ID635
Feature activation-4.72e-02

Pos logit contributions
ishes+0.028
 favorites+0.027
 seas+0.026
 minerals+0.026
 shells+0.025
Neg logit contributions
iren-0.027
 crash-0.027
storm-0.025
 knock-0.025
 aids-0.024
Token saw
Token ID2497
Feature activation-9.39e-02

Pos logit contributions
ishes+0.082
 favorites+0.076
 seas+0.076
 minerals+0.075
 shells+0.072
Neg logit contributions
iren-0.080
 crash-0.078
storm-0.073
 knock-0.072
 aids-0.070
Token birds
Token ID10087
Feature activation-1.14e-01

Pos logit contributions
ishes+0.141
 favorites+0.132
 seas+0.124
 minerals+0.124
esty+0.123
Neg logit contributions
iren-0.179
 crash-0.175
storm-0.163
 aids-0.163
 knock-0.160
Token sand
Token ID6450
Feature activation-2.69e-01

Pos logit contributions
ishes+0.142
 favorites+0.130
 minerals+0.128
sters+0.123
 seas+0.123
Neg logit contributions
iren-0.167
 crash-0.163
storm-0.157
 aids-0.150
 knock-0.147
Token,
Token ID11
Feature activation-1.21e-01

Pos logit contributions
ishes+0.474
 favorites+0.448
 minerals+0.442
 seas+0.433
 seaw+0.423
Neg logit contributions
iren-0.446
 crash-0.425
storm-0.413
 knock-0.383
 aids-0.378
Token and
Token ID290
Feature activation-6.04e-02

Pos logit contributions
ishes+0.198
 favorites+0.184
 minerals+0.182
 seas+0.182
 shells+0.177
Neg logit contributions
iren-0.219
 crash-0.209
storm-0.201
 knock-0.193
 aids-0.191
Token deep
Token ID2769
Feature activation+4.55e-02

Pos logit contributions
ishes+0.100
 favorites+0.093
 seas+0.091
 minerals+0.091
 shells+0.087
Neg logit contributions
iren-0.107
 crash-0.105
storm-0.099
 knock-0.097
 aids-0.095
Token blue
Token ID4171
Feature activation-6.56e-02

Pos logit contributions
iren+0.082
 crash+0.078
storm+0.075
 knock+0.072
 aids+0.071
Neg logit contributions
ishes-0.076
 seas-0.070
 favorites-0.070
 minerals-0.070
 shells-0.069
Token seas
Token ID21547
Feature activation-4.91e-01

Pos logit contributions
ishes+0.094
 favorites+0.087
 minerals+0.085
 seas+0.083
esty+0.080
Neg logit contributions
iren-0.132
 crash-0.126
storm-0.122
 aids-0.116
 knock-0.115
Token.
Token ID13
Feature activation-6.56e-02

Pos logit contributions
 seas+0.902
ishes+0.897
 shells+0.880
 seaw+0.865
 minerals+0.857
Neg logit contributions
iren-0.763
 crash-0.710
storm-0.678
 knock-0.665
 earthquake-0.664
Token
Token ID220
Feature activation-1.52e-01

Pos logit contributions
ishes+0.125
 seas+0.117
 favorites+0.115
 minerals+0.115
 shells+0.114
Neg logit contributions
iren-0.103
 crash-0.097
storm-0.093
 aids-0.088
 knock-0.087
Token
Token ID198
Feature activation-6.50e-02

Pos logit contributions
ishes+0.248
 favorites+0.231
 seas+0.230
 minerals+0.230
 shells+0.226
Neg logit contributions
iren-0.277
 crash-0.263
storm-0.256
 knock-0.243
 aids-0.241
Token
Token ID198
Feature activation-6.12e-02

Pos logit contributions
ishes+0.102
 favorites+0.096
 seas+0.096
 minerals+0.095
 shells+0.093
Neg logit contributions
iren-0.121
 crash-0.117
storm-0.114
 earthquake-0.107
 knock-0.107
TokenOne
Token ID3198
Feature activation-1.78e-01

Pos logit contributions
ishes+0.093
 favorites+0.089
 seas+0.088
 minerals+0.088
 shells+0.086
Neg logit contributions
iren-0.116
 crash-0.111
storm-0.108
 knock-0.102
 earthquake-0.102
Token her
Token ID607
Feature activation-2.91e-02

Pos logit contributions
iren+0.385
storm+0.344
 crash+0.343
aned+0.317
 aids+0.316
Neg logit contributions
ishes-0.339
 minerals-0.331
 shells-0.331
 seas-0.325
 favorites-0.319
Token finger
Token ID7660
Feature activation-1.10e-01

Pos logit contributions
ishes+0.045
 favorites+0.043
 seas+0.043
 minerals+0.043
 shells+0.043
Neg logit contributions
iren-0.057
 crash-0.053
storm-0.052
 aids-0.048
 knock-0.048
Token and
Token ID290
Feature activation-3.66e-02

Pos logit contributions
ishes+0.170
 favorites+0.157
 minerals+0.155
 seas+0.155
 shells+0.155
Neg logit contributions
iren-0.213
 crash-0.199
storm-0.194
 knock-0.185
 aids-0.184
Token the
Token ID262
Feature activation+2.67e-03

Pos logit contributions
ishes+0.064
 favorites+0.061
 seas+0.060
 minerals+0.060
 shells+0.058
Neg logit contributions
iren-0.061
 crash-0.059
storm-0.056
 knock-0.054
 aids-0.054
Token rad
Token ID2511
Feature activation-1.46e-01

Pos logit contributions
iren+0.005
 crash+0.004
storm+0.004
 aids+0.004
 knock+0.004
Neg logit contributions
ishes-0.004
 seas-0.004
 shells-0.004
 minerals-0.004
 favorites-0.004
Tokenishes
Token ID5614
Feature activation-4.90e-01

Pos logit contributions
 seas+0.177
 seaw+0.166
 islands+0.162
 experiences+0.156
 Anything+0.147
Neg logit contributions
iren-0.279
 crash-0.268
 burned-0.262
 hurt-0.260
 burnt-0.255
Token.
Token ID13
Feature activation-2.95e-02

Pos logit contributions
ishes+0.735
 shells+0.692
 seas+0.674
 minerals+0.673
 seaw+0.660
Neg logit contributions
iren-0.977
 crash-0.898
storm-0.878
 aids-0.852
 earthquake-0.845
Token She
Token ID1375
Feature activation+1.25e-02

Pos logit contributions
ishes+0.063
 seas+0.060
 minerals+0.058
 shells+0.058
 favorites+0.057
Neg logit contributions
iren-0.041
 crash-0.038
storm-0.036
 aids-0.035
 knock-0.034
Token said
Token ID531
Feature activation-6.11e-02

Pos logit contributions
iren+0.022
 crash+0.021
storm+0.021
 knock+0.019
 aids+0.019
Neg logit contributions
ishes-0.021
 favorites-0.019
 seas-0.019
 minerals-0.019
 shells-0.019
Token,
Token ID11
Feature activation-8.21e-02

Pos logit contributions
ishes+0.095
 seas+0.088
 minerals+0.088
 favorites+0.088
 shells+0.086
Neg logit contributions
iren-0.118
 crash-0.112
storm-0.109
 knock-0.103
 aids-0.103
Token "
Token ID366
Feature activation+2.56e-02

Pos logit contributions
ishes+0.128
 minerals+0.124
 favorites+0.121
 shells+0.120
sters+0.118
Neg logit contributions
iren-0.151
storm-0.138
 crash-0.138
 earthquake-0.133
 collapse-0.132
Token always
Token ID1464
Feature activation+1.34e-03

Pos logit contributions
ishes+0.064
 favorites+0.061
 seas+0.059
 minerals+0.058
sters+0.057
Neg logit contributions
iren-0.058
 crash-0.057
storm-0.053
 knock-0.052
 earthquake-0.050
Token had
Token ID550
Feature activation+7.81e-02

Pos logit contributions
iren+0.002
 crash+0.002
storm+0.002
 knock+0.002
 earthquake+0.002
Neg logit contributions
ishes-0.002
 favorites-0.002
 seas-0.002
 minerals-0.002
 shells-0.002
Token plenty
Token ID6088
Feature activation-4.05e-01

Pos logit contributions
iren+0.144
 crash+0.142
 aids+0.131
storm+0.129
 ripping+0.127
Neg logit contributions
ishes-0.115
sters-0.106
 favorites-0.106
 minerals-0.100
 seas-0.100
Token of
Token ID286
Feature activation+2.20e-01

Pos logit contributions
ishes+1.103
 favorites+1.056
 seas+1.042
 minerals+1.030
sters+1.022
Neg logit contributions
iren-0.311
 crash-0.260
storm-0.229
 knock-0.200
 earthquake-0.198
Token rad
Token ID2511
Feature activation-1.47e-01

Pos logit contributions
iren+0.463
 crash+0.442
storm+0.430
 knock+0.412
 aids+0.410
Neg logit contributions
ishes-0.304
 favorites-0.279
 seas-0.278
 minerals-0.277
 shells-0.271
Tokenishes
Token ID5614
Feature activation-4.90e-01

Pos logit contributions
 Something+0.120
 Anything+0.117
 amaz+0.111
 yes+0.109
 dreams+0.103
Neg logit contributions
iren-0.314
 crash-0.285
maker-0.274
 brewing-0.273
oe-0.269
Token to
Token ID284
Feature activation+7.79e-04

Pos logit contributions
ishes+0.889
 favorites+0.862
 seas+0.839
 minerals+0.825
 shells+0.808
Neg logit contributions
iren-0.775
 crash-0.727
storm-0.715
 brewing-0.650
 knock-0.649
Token eat
Token ID4483
Feature activation-9.18e-04

Pos logit contributions
iren+0.001
 crash+0.001
storm+0.001
 knock+0.001
 aids+0.001
Neg logit contributions
ishes-0.001
 favorites-0.001
 seas-0.001
 minerals-0.001
 shells-0.001
Token.
Token ID13
Feature activation-3.37e-02

Pos logit contributions
ishes+0.002
 favorites+0.002
 seas+0.002
 minerals+0.001
esty+0.001
Neg logit contributions
iren-0.001
 crash-0.001
storm-0.001
 knock-0.001
 aids-0.001
Token The
Token ID383
Feature activation+1.53e-02

Pos logit contributions
ishes+0.062
 seas+0.058
 shells+0.057
 favorites+0.057
 minerals+0.057
Neg logit contributions
iren-0.055
 crash-0.052
storm-0.050
 aids-0.048
 knock-0.047
Token end
Token ID886
Feature activation-5.67e-02

Pos logit contributions
 earthquake+0.020
 crash+0.019
 knock+0.019
iren+0.019
storm+0.018
Neg logit contributions
ishes-0.031
 favorites-0.029
sters-0.029
 seas-0.028
 combinations-0.028
Token hats
Token ID23910
Feature activation-2.61e-01

Pos logit contributions
ishes+0.162
 favorites+0.151
 seas+0.151
 minerals+0.150
 shells+0.147
Neg logit contributions
iren-0.181
 crash-0.172
storm-0.166
 knock-0.158
 aids-0.157
Token and
Token ID290
Feature activation-5.68e-02

Pos logit contributions
ishes+0.393
 seas+0.360
 favorites+0.358
 shells+0.352
 minerals+0.347
Neg logit contributions
iren-0.512
 crash-0.481
storm-0.458
 knock-0.456
 aids-0.456
Token went
Token ID1816
Feature activation-3.08e-02

Pos logit contributions
ishes+0.098
 favorites+0.093
 seas+0.091
 minerals+0.090
sters+0.087
Neg logit contributions
iren-0.095
 crash-0.094
storm-0.087
 knock-0.087
 aids-0.084
Token to
Token ID284
Feature activation-1.87e-02

Pos logit contributions
ishes+0.044
 seas+0.043
 shells+0.041
 favorites+0.040
 minerals+0.039
Neg logit contributions
iren-0.060
storm-0.059
 aids-0.058
 crash-0.058
 earthquake-0.057
Token find
Token ID1064
Feature activation-1.79e-01

Pos logit contributions
ishes+0.032
 seas+0.030
 favorites+0.030
 minerals+0.030
 shells+0.030
Neg logit contributions
iren-0.033
 crash-0.030
storm-0.030
 aids-0.028
 knock-0.028
Token shells
Token ID19679
Feature activation-4.88e-01

Pos logit contributions
ishes+0.268
sters+0.252
 favorites+0.251
 minerals+0.240
esty+0.236
Neg logit contributions
iren-0.331
 crash-0.308
 aids-0.301
 knock-0.291
 earthquake-0.288
Token by
Token ID416
Feature activation-1.19e-02

Pos logit contributions
ishes+0.867
 favorites+0.829
 minerals+0.807
 seas+0.803
 seaw+0.787
Neg logit contributions
iren-0.793
 crash-0.747
storm-0.733
 knock-0.671
 aids-0.667
Token the
Token ID262
Feature activation+5.66e-03

Pos logit contributions
ishes+0.020
 favorites+0.018
 seas+0.018
 minerals+0.018
 shells+0.018
Neg logit contributions
iren-0.022
 crash-0.020
storm-0.020
 knock-0.019
 aids-0.019
Token water
Token ID1660
Feature activation-6.59e-02

Pos logit contributions
iren+0.011
 crash+0.010
storm+0.010
 knock+0.009
 aids+0.009
Neg logit contributions
ishes-0.009
 favorites-0.008
 minerals-0.008
 seas-0.008
 shells-0.008
Token.
Token ID13
Feature activation-4.43e-02

Pos logit contributions
ishes+0.104
 seas+0.096
 minerals+0.096
 shells+0.095
 favorites+0.094
Neg logit contributions
iren-0.126
 crash-0.120
storm-0.114
 knock-0.112
 aids-0.111
Token They
Token ID1119
Feature activation-9.81e-03

Pos logit contributions
ishes+0.073
 favorites+0.069
 minerals+0.069
 seas+0.068
 shells+0.067
Neg logit contributions
iren-0.080
 crash-0.076
storm-0.073
 knock-0.069
 earthquake-0.069
Token.
Token ID13
Feature activation-6.40e-02

Pos logit contributions
ishes+0.410
 seas+0.376
 favorites+0.374
 minerals+0.374
 shells+0.373
Neg logit contributions
iren-0.526
 crash-0.494
storm-0.471
 knock-0.466
 aids-0.464
Token
Token ID198
Feature activation-6.87e-02

Pos logit contributions
ishes+0.120
 seas+0.112
 minerals+0.109
 shells+0.109
 favorites+0.108
Neg logit contributions
iren-0.105
 crash-0.099
storm-0.094
 aids-0.091
 knock-0.090
Token
Token ID198
Feature activation-6.20e-02

Pos logit contributions
ishes+0.103
 favorites+0.100
 seas+0.099
 minerals+0.099
 shells+0.097
Neg logit contributions
iren-0.128
 crash-0.124
storm-0.124
 earthquake-0.115
 knock-0.113
TokenThe
Token ID464
Feature activation-1.62e-02

Pos logit contributions
ishes+0.094
 favorites+0.087
 seas+0.086
 minerals+0.086
 shells+0.085
Neg logit contributions
iren-0.122
 crash-0.116
storm-0.112
 knock-0.107
 aids-0.107
Token mild
Token ID11607
Feature activation-9.83e-03

Pos logit contributions
ishes+0.027
 seas+0.025
 favorites+0.025
 minerals+0.025
 shells+0.025
Neg logit contributions
iren-0.029
 crash-0.028
storm-0.027
 knock-0.025
 aids-0.025
Token minerals
Token ID21622
Feature activation-4.86e-01

Pos logit contributions
ishes+0.015
 minerals+0.015
 shells+0.015
 ones+0.015
 seas+0.015
Neg logit contributions
iren-0.019
 crash-0.017
storm-0.017
aned-0.017
 collapse-0.016
Token loved
Token ID6151
Feature activation-6.65e-02

Pos logit contributions
ishes+0.714
 shells+0.675
 seas+0.667
 minerals+0.663
 seaw+0.646
Neg logit contributions
iren-0.969
 crash-0.898
storm-0.882
 aids-0.848
 earthquake-0.840
Token to
Token ID284
Feature activation-6.51e-03

Pos logit contributions
 minerals+0.104
ishes+0.103
 seas+0.102
 shells+0.102
 seaw+0.098
Neg logit contributions
iren-0.132
 crash-0.118
storm-0.117
aned-0.114
 collapse-0.110
Token have
Token ID423
Feature activation+5.96e-02

Pos logit contributions
 shells+0.009
 minerals+0.009
ishes+0.009
 seaw+0.009
 seas+0.009
Neg logit contributions
iren-0.013
storm-0.012
 crash-0.012
 brewing-0.011
aned-0.011
Token fun
Token ID1257
Feature activation-1.09e-01

Pos logit contributions
iren+0.110
 crash+0.108
storm+0.099
 aids+0.099
 knock+0.098
Neg logit contributions
ishes-0.093
 favorites-0.084
sters-0.082
 seas-0.081
esty-0.080
Token together
Token ID1978
Feature activation-2.31e-01

Pos logit contributions
ishes+0.196
 favorites+0.182
 seas+0.181
 minerals+0.180
 shells+0.176
Neg logit contributions
iren-0.181
 crash-0.172
storm-0.164
 knock-0.157
 aids-0.156
Token,
Token ID11
Feature activation-1.34e-01

Pos logit contributions
ishes+0.007
 seas+0.007
 minerals+0.007
 favorites+0.007
 shells+0.007
Neg logit contributions
iren-0.008
 crash-0.008
storm-0.008
 knock-0.007
 aids-0.007
Token a
Token ID257
Feature activation-2.30e-01

Pos logit contributions
ishes+0.195
 minerals+0.184
 shells+0.182
 seas+0.182
 favorites+0.179
Neg logit contributions
iren-0.272
 crash-0.251
storm-0.247
 aids-0.233
 knock-0.232
Token bucket
Token ID19236
Feature activation-2.41e-01

Pos logit contributions
 seas+0.374
ishes+0.369
 minerals+0.366
 shells+0.366
 seaw+0.365
Neg logit contributions
iren-0.419
 crash-0.373
storm-0.371
aned-0.367
 aids-0.360
Token and
Token ID290
Feature activation-5.61e-02

Pos logit contributions
 shells+0.377
ishes+0.373
 seas+0.364
 seaw+0.363
 minerals+0.356
Neg logit contributions
iren-0.430
 aids-0.414
 crash-0.399
 knock-0.386
aned-0.384
Token some
Token ID617
Feature activation-3.07e-01

Pos logit contributions
ishes+0.086
 favorites+0.080
 seas+0.077
 minerals+0.077
sters+0.074
Neg logit contributions
iren-0.107
 crash-0.104
storm-0.099
 knock-0.097
 aids-0.095
Token shells
Token ID19679
Feature activation-4.86e-01

Pos logit contributions
ishes+0.441
 shells+0.426
 minerals+0.424
 seas+0.422
 seaw+0.414
Neg logit contributions
iren-0.625
 crash-0.590
storm-0.588
 aids-0.549
 knock-0.546
Token.
Token ID13
Feature activation-5.89e-02

Pos logit contributions
ishes+0.811
 seas+0.756
 minerals+0.753
 shells+0.752
 favorites+0.744
Neg logit contributions
iren-0.879
 crash-0.830
storm-0.804
 aids-0.773
 knock-0.769
Token They
Token ID1119
Feature activation-1.38e-02

Pos logit contributions
ishes+0.115
 seas+0.108
 favorites+0.106
 minerals+0.106
 shells+0.105
Neg logit contributions
iren-0.090
 crash-0.085
storm-0.080
 aids-0.077
 knock-0.077
Token want
Token ID765
Feature activation-1.68e-01

Pos logit contributions
ishes+0.023
 seas+0.021
 favorites+0.021
 minerals+0.021
sters+0.020
Neg logit contributions
iren-0.024
 crash-0.024
storm-0.023
 knock-0.023
 aids-0.021
Token to
Token ID284
Feature activation-6.51e-03

Pos logit contributions
ishes+0.301
 seas+0.285
 minerals+0.284
 favorites+0.282
 shells+0.281
Neg logit contributions
iren-0.284
 crash-0.267
storm-0.260
 aids-0.243
 knock-0.243
Token create
Token ID2251
Feature activation-1.00e-01

Pos logit contributions
ishes+0.011
 favorites+0.010
 minerals+0.010
 seas+0.010
 shells+0.010
Neg logit contributions
iren-0.012
 crash-0.011
storm-0.011
 aids-0.010
 knock-0.010
TokenThe
Token ID464
Feature activation-2.71e-02

Pos logit contributions
ishes+0.115
 favorites+0.113
 minerals+0.111
 seas+0.111
 shells+0.109
Neg logit contributions
iren-0.155
 crash-0.151
storm-0.147
 earthquake-0.140
 knock-0.136
Token girl
Token ID2576
Feature activation-2.19e-01

Pos logit contributions
ishes+0.045
 favorites+0.042
 seas+0.041
 minerals+0.041
 shells+0.040
Neg logit contributions
iren-0.049
 crash-0.047
storm-0.045
 knock-0.043
 aids-0.043
Token kept
Token ID4030
Feature activation-1.02e-01

Pos logit contributions
ishes+0.339
 favorites+0.325
 shells+0.313
 seas+0.313
 dreams+0.308
Neg logit contributions
iren-0.432
 crash-0.396
storm-0.388
 earthquake-0.378
 outage-0.363
Token searching
Token ID10342
Feature activation-1.26e-01

Pos logit contributions
ishes+0.158
 shells+0.153
 seas+0.148
 minerals+0.148
 luck+0.146
Neg logit contributions
storm-0.202
iren-0.194
 outage-0.186
umpy-0.180
 earthquake-0.177
Token for
Token ID329
Feature activation-1.04e-01

Pos logit contributions
ishes+0.205
 favorites+0.191
 seas+0.190
 minerals+0.188
 shells+0.184
Neg logit contributions
iren-0.231
 crash-0.220
storm-0.210
 knock-0.203
 aids-0.200
Token minerals
Token ID21622
Feature activation-4.85e-01

Pos logit contributions
ishes+0.182
 favorites+0.165
sters+0.163
ish+0.162
esty+0.160
Neg logit contributions
 crash-0.164
iren-0.161
 knock-0.157
 knocking-0.149
 ripping-0.148
Token.
Token ID13
Feature activation-6.21e-02

Pos logit contributions
ishes+0.915
 favorites+0.886
 Majesty+0.840
 seas+0.840
 seaw+0.832
Neg logit contributions
iren-0.717
 crash-0.668
storm-0.660
 brewing-0.602
 earthquake-0.591
Token She
Token ID1375
Feature activation-6.73e-03

Pos logit contributions
ishes+0.124
 seas+0.118
 seaw+0.116
 shells+0.115
 minerals+0.114
Neg logit contributions
iren-0.091
 crash-0.086
storm-0.081
 aids-0.078
 knock-0.078
Token went
Token ID1816
Feature activation-1.69e-02

Pos logit contributions
ishes+0.012
 favorites+0.011
 minerals+0.011
 seas+0.011
sters+0.010
Neg logit contributions
iren-0.011
 crash-0.010
 knock-0.010
storm-0.010
lf-0.009
Token to
Token ID284
Feature activation-2.75e-03

Pos logit contributions
ishes+0.032
 favorites+0.030
 minerals+0.029
 seas+0.029
 seaw+0.029
Neg logit contributions
iren-0.027
 crash-0.026
storm-0.024
 knock-0.023
 brewing-0.022
Token the
Token ID262
Feature activation+5.29e-03

Pos logit contributions
ishes+0.006
sters+0.005
 favorites+0.005
 seas+0.005
esty+0.005
Neg logit contributions
 crash-0.004
iren-0.004
 knock-0.004
 knocking-0.003
 earthquake-0.003
Token and
Token ID290
Feature activation-7.14e-02

Pos logit contributions
ishes+0.182
 seas+0.170
 shells+0.168
 minerals+0.166
 seaw+0.164
Neg logit contributions
iren-0.208
 crash-0.194
storm-0.186
 aids-0.186
 knock-0.184
Token the
Token ID262
Feature activation-1.53e-02

Pos logit contributions
ishes+0.124
 favorites+0.117
 seas+0.115
 minerals+0.114
 shells+0.111
Neg logit contributions
iren-0.121
 crash-0.117
storm-0.112
 knock-0.108
 aids-0.105
Token sand
Token ID6450
Feature activation-2.48e-01

Pos logit contributions
ishes+0.024
 seas+0.023
 minerals+0.023
 favorites+0.023
 shells+0.023
Neg logit contributions
iren-0.028
 crash-0.027
storm-0.026
 aids-0.025
 knock-0.025
Token and
Token ID290
Feature activation-5.35e-02

Pos logit contributions
ishes+0.375
 seas+0.356
 shells+0.353
 minerals+0.343
 seaw+0.338
Neg logit contributions
iren-0.496
 crash-0.463
storm-0.446
 aids-0.439
 knock-0.433
Token the
Token ID262
Feature activation-6.90e-03

Pos logit contributions
ishes+0.086
 favorites+0.080
 seas+0.078
 minerals+0.078
 shells+0.075
Neg logit contributions
iren-0.098
 crash-0.095
storm-0.091
 knock-0.088
 aids-0.086
Token shells
Token ID19679
Feature activation-4.84e-01

Pos logit contributions
ishes+0.010
 favorites+0.009
 minerals+0.009
 seas+0.009
 shells+0.009
Neg logit contributions
iren-0.014
 crash-0.013
storm-0.013
 knock-0.013
 aids-0.012
Token.
Token ID13
Feature activation-5.71e-02

Pos logit contributions
ishes+0.742
 shells+0.714
 seas+0.706
 minerals+0.686
 seaw+0.682
Neg logit contributions
iren-0.947
 crash-0.873
storm-0.849
 aids-0.849
 earthquake-0.827
Token Maybe
Token ID6674
Feature activation-2.80e-01

Pos logit contributions
ishes+0.108
 seas+0.101
 favorites+0.100
 minerals+0.099
 shells+0.098
Neg logit contributions
iren-0.091
 crash-0.086
storm-0.082
 aids-0.078
 knock-0.078
Token we
Token ID356
Feature activation-1.36e-01

Pos logit contributions
ishes+0.569
 favorites+0.533
esty+0.515
sters+0.494
 Majesty+0.489
Neg logit contributions
 crash-0.385
 knock-0.381
iren-0.381
storm-0.354
 earthquake-0.349
Token will
Token ID481
Feature activation-2.58e-01

Pos logit contributions
ishes+0.170
 seas+0.160
 favorites+0.157
 minerals+0.155
 shells+0.151
Neg logit contributions
iren-0.293
 crash-0.289
storm-0.279
 knock-0.271
 earthquake-0.262
Token see
Token ID766
Feature activation-4.95e-02

Pos logit contributions
ishes+0.437
 favorites+0.403
 seas+0.402
 minerals+0.397
 shells+0.387
Neg logit contributions
iren-0.458
 crash-0.446
storm-0.423
 knock-0.413
 aids-0.399
Token for
Token ID329
Feature activation-1.18e-01

Pos logit contributions
ishes+0.369
 minerals+0.349
 favorites+0.345
 seas+0.343
 shells+0.339
Neg logit contributions
iren-0.450
 crash-0.424
storm-0.413
 knock-0.393
 aids-0.390
Token collecting
Token ID13157
Feature activation-1.75e-01

Pos logit contributions
ishes+0.209
 favorites+0.195
 seas+0.194
 minerals+0.193
 shells+0.190
Neg logit contributions
iren-0.200
 crash-0.190
storm-0.182
 knock-0.174
 aids-0.172
Token pretty
Token ID2495
Feature activation-9.56e-02

Pos logit contributions
ishes+0.223
 favorites+0.212
esty+0.198
sters+0.195
lets+0.186
Neg logit contributions
iren-0.355
 crash-0.336
 aids-0.318
 knock-0.315
 earthquake-0.306
Token rocks
Token ID12586
Feature activation-3.27e-01

Pos logit contributions
esty+0.111
ishes+0.106
 favorites+0.099
 nic+0.097
sters+0.096
Neg logit contributions
iren-0.193
 crash-0.183
 aids-0.172
storm-0.172
 knock-0.171
Token and
Token ID290
Feature activation-5.38e-02

Pos logit contributions
ishes+0.582
 favorites+0.554
 seas+0.542
 minerals+0.539
 shells+0.530
Neg logit contributions
iren-0.539
 crash-0.505
storm-0.494
 knock-0.455
 aids-0.451
Token shells
Token ID19679
Feature activation-4.84e-01

Pos logit contributions
ishes+0.079
 favorites+0.073
esty+0.072
sters+0.069
ish+0.068
Neg logit contributions
 crash-0.103
 knock-0.096
iren-0.094
 knocking-0.092
 earthquake-0.089
Token.
Token ID13
Feature activation-6.05e-02

Pos logit contributions
ishes+0.889
 favorites+0.852
 minerals+0.823
 seas+0.821
 seaw+0.808
Neg logit contributions
iren-0.753
 crash-0.698
storm-0.690
 aids-0.613
 knock-0.610
Token<|endoftext|>
Token ID50256
Feature activation+9.84e-02

Pos logit contributions
ishes+0.111
 seas+0.104
 shells+0.102
 minerals+0.101
 favorites+0.101
Neg logit contributions
iren-0.099
 crash-0.094
storm-0.091
 aids-0.086
 knock-0.085
TokenOnce
Token ID7454
Feature activation-3.40e-02

Pos logit contributions
iren+0.194
 crash+0.186
storm+0.183
 knock+0.175
 aids+0.174
Neg logit contributions
ishes-0.142
 seas-0.135
 favorites-0.134
 minerals-0.133
 shells-0.129
Token upon
Token ID2402
Feature activation-2.54e-01

Pos logit contributions
ishes+0.026
 seas+0.024
 favorites+0.023
 minerals+0.023
 shells+0.022
Neg logit contributions
iren-0.092
 crash-0.088
storm-0.087
 aids-0.084
 knock-0.083
Token a
Token ID257
Feature activation-1.95e-01

Pos logit contributions
ishes+0.533
ish+0.446
sters+0.445
 favorites+0.440
esty+0.429
Neg logit contributions
 crash-0.400
iren-0.382
ggy-0.374
't-0.370
 knock-0.358
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
ishes+0.569
 favorites+0.531
 seas+0.530
 minerals+0.528
 shells+0.519
Neg logit contributions
iren-0.597
 crash-0.565
storm-0.547
 knock-0.519
 aids-0.516
Token They
Token ID1119
Feature activation-3.86e-02

Pos logit contributions
ishes+0.200
 seas+0.187
 shells+0.183
 minerals+0.182
 favorites+0.181
Neg logit contributions
iren-0.182
 crash-0.173
storm-0.167
 aids-0.159
 knock-0.157
Token collect
Token ID2824
Feature activation-2.81e-01

Pos logit contributions
ishes+0.065
 seas+0.061
 favorites+0.061
 minerals+0.060
 shells+0.058
Neg logit contributions
iren-0.067
 crash-0.065
storm-0.062
 knock-0.061
 aids-0.058
Token rocks
Token ID12586
Feature activation-3.29e-01

Pos logit contributions
ishes+0.299
 favorites+0.289
esty+0.283
 Majesty+0.280
sters+0.277
Neg logit contributions
iren-0.607
 crash-0.595
 knock-0.558
 aids-0.539
 earthquake-0.528
Token,
Token ID11
Feature activation-1.04e-01

Pos logit contributions
ishes+0.545
 seas+0.507
 minerals+0.506
 favorites+0.506
 shells+0.497
Neg logit contributions
iren-0.597
 crash-0.566
storm-0.548
 knock-0.521
 aids-0.520
Token shells
Token ID19679
Feature activation-4.84e-01

Pos logit contributions
ishes+0.113
 favorites+0.109
 luck+0.107
 Majesty+0.107
esty+0.102
Neg logit contributions
 crash-0.229
iren-0.228
 knock-0.217
storm-0.208
 knocking-0.203
Token,
Token ID11
Feature activation-9.49e-02

Pos logit contributions
ishes+0.786
 favorites+0.738
 seas+0.729
 minerals+0.726
 shells+0.709
Neg logit contributions
iren-0.881
 crash-0.837
storm-0.806
 knock-0.766
 aids-0.757
Token leaves
Token ID5667
Feature activation-1.55e-01

Pos logit contributions
 favorites+0.142
ishes+0.140
 Majesty+0.139
esty+0.137
 luck+0.136
Neg logit contributions
 crash-0.168
iren-0.161
 knock-0.157
storm-0.144
 knocking-0.144
Token,
Token ID11
Feature activation-8.91e-02

Pos logit contributions
ishes+0.241
 minerals+0.223
 seas+0.223
 favorites+0.222
 shells+0.220
Neg logit contributions
iren-0.296
 crash-0.281
storm-0.273
 aids-0.261
 knock-0.260
Token and
Token ID290
Feature activation-3.02e-02

Pos logit contributions
 favorites+0.164
ishes+0.160
esty+0.156
 Majesty+0.155
 luck+0.153
Neg logit contributions
 crash-0.130
iren-0.122
 knock-0.120
storm-0.109
 knocking-0.108
Token stickers
Token ID28568
Feature activation-2.41e-01

Pos logit contributions
ishes+0.042
 favorites+0.039
esty+0.038
ish+0.037
 Majesty+0.035
Neg logit contributions
 crash-0.062
 knock-0.060
 knocking-0.055
iren-0.053
 drip-0.053
Tokenison
Token ID1653
Feature activation-1.39e-01

Pos logit contributions
iren+0.026
 crash+0.024
storm+0.022
 knock+0.022
 aids+0.021
Neg logit contributions
ishes-0.033
 favorites-0.031
 seas-0.030
 minerals-0.030
 shells-0.030
Token couldn
Token ID3521
Feature activation-8.49e-02

Pos logit contributions
ishes+0.231
 favorites+0.215
 seas+0.215
 minerals+0.214
 shells+0.210
Neg logit contributions
iren-0.250
 crash-0.237
storm-0.229
 knock-0.218
 aids-0.217
Token't
Token ID470
Feature activation+2.63e-01

Pos logit contributions
 dreams+0.194
 minerals+0.185
 luck+0.184
 ones+0.183
 one+0.183
Neg logit contributions
iren-0.080
storm-0.066
 aids-0.062
 ripping-0.059
aned-0.058
Token believe
Token ID1975
Feature activation-2.17e-01

Pos logit contributions
iren+0.550
 crash+0.499
storm+0.498
 aids+0.480
 brewing+0.464
Neg logit contributions
ishes-0.353
 minerals-0.336
 shells-0.333
 favorites-0.331
 seas-0.330
Token her
Token ID607
Feature activation-8.02e-02

Pos logit contributions
ishes+0.346
 seas+0.321
 favorites+0.321
 minerals+0.320
 shells+0.315
Neg logit contributions
iren-0.408
 crash-0.387
storm-0.376
 knock-0.356
 aids-0.355
Token luck
Token ID8458
Feature activation-4.83e-01

Pos logit contributions
ishes+0.119
 seas+0.110
 favorites+0.109
 seaw+0.107
 minerals+0.106
Neg logit contributions
iren-0.153
 crash-0.149
 earthquake-0.141
storm-0.140
 aids-0.139
Token and
Token ID290
Feature activation-7.12e-02

Pos logit contributions
ishes+0.834
 favorites+0.778
 seas+0.776
 minerals+0.774
 shells+0.760
Neg logit contributions
iren-0.842
 crash-0.796
storm-0.770
 knock-0.729
 aids-0.725
Token started
Token ID2067
Feature activation-4.32e-02

Pos logit contributions
ishes+0.127
 favorites+0.119
 seas+0.116
 minerals+0.115
 seaw+0.111
Neg logit contributions
iren-0.117
 crash-0.116
 knock-0.109
storm-0.106
 aids-0.104
Token to
Token ID284
Feature activation-2.48e-02

Pos logit contributions
 shells+0.069
ishes+0.068
 minerals+0.067
 luck+0.065
 seas+0.065
Neg logit contributions
iren-0.080
storm-0.076
 crash-0.070
 earthquake-0.068
 outage-0.067
Token think
Token ID892
Feature activation-2.41e-01

Pos logit contributions
ishes+0.043
 favorites+0.041
 seas+0.041
 minerals+0.040
 shells+0.040
Neg logit contributions
iren-0.043
 crash-0.040
storm-0.039
 knock-0.037
 aids-0.037
Token of
Token ID286
Feature activation+2.02e-01

Pos logit contributions
 shells+0.430
 seas+0.429
 minerals+0.423
ishes+0.413
 luck+0.410
Neg logit contributions
iren-0.388
storm-0.370
 crash-0.363
aned-0.320
 collapse-0.315
Token.
Token ID13
Feature activation+1.94e-02

Pos logit contributions
iren+0.418
storm+0.391
 crash+0.386
 knock+0.381
 tornado+0.362
Neg logit contributions
ishes-0.232
 luck-0.231
 dreams-0.225
 ones-0.224
 minerals-0.221
Token<|endoftext|>
Token ID50256
Feature activation+1.73e-01

Pos logit contributions
iren+0.034
 crash+0.032
storm+0.031
 knock+0.030
 aids+0.029
Neg logit contributions
ishes-0.033
 seas-0.031
 favorites-0.031
 minerals-0.031
 shells-0.030
TokenOnce
Token ID7454
Feature activation+3.57e-02

Pos logit contributions
iren+0.347
 crash+0.331
storm+0.326
 earthquake+0.314
 knock+0.312
Neg logit contributions
ishes-0.239
 seas-0.231
 favorites-0.228
 minerals-0.227
 shells-0.221
Token upon
Token ID2402
Feature activation-1.82e-01

Pos logit contributions
iren+0.092
 crash+0.088
storm+0.087
 aids+0.084
 knock+0.084
Neg logit contributions
ishes-0.032
 favorites-0.028
 seas-0.028
 minerals-0.027
 shells-0.027
Token a
Token ID257
Feature activation-1.28e-01

Pos logit contributions
ishes+0.315
 favorites+0.269
 minerals+0.262
sters+0.262
ish+0.256
Neg logit contributions
 crash-0.339
iren-0.334
storm-0.312
 knock-0.312
't-0.310
Token time
Token ID640
Feature activation+2.58e-01

Pos logit contributions
ishes+0.304
 favorites+0.296
 seas+0.294
 minerals+0.290
 shells+0.286
Neg logit contributions
iren-0.138
 crash-0.123
storm-0.114
 aids-0.104
 knock-0.104
Token,
Token ID11
Feature activation-2.45e-02

Pos logit contributions
iren+0.453
 crash+0.439
storm+0.417
 knock+0.400
 earthquake+0.393
Neg logit contributions
ishes-0.446
 favorites-0.407
 minerals-0.403
 seas-0.402
 shells-0.397
Token there
Token ID612
Feature activation-5.07e-02

Pos logit contributions
ishes+0.037
 favorites+0.034
 seas+0.034
 minerals+0.034
 shells+0.033
Neg logit contributions
iren-0.048
 crash-0.046
storm-0.045
 knock-0.043
 earthquake-0.042
Token was
Token ID373
Feature activation+8.56e-02

Pos logit contributions
 favorites+0.069
ishes+0.069
 seas+0.069
 minerals+0.067
 dreams+0.066
Neg logit contributions
iren-0.106
 crash-0.095
storm-0.093
 aids-0.091
 earthquake-0.090
Token a
Token ID257
Feature activation-1.26e-01

Pos logit contributions
iren+0.140
 crash+0.138
storm+0.135
 earthquake+0.132
't+0.131
Neg logit contributions
ishes-0.155
sters-0.141
esty-0.133
 Majesty-0.129
 minerals-0.128
Token little
Token ID1310
Feature activation+7.35e-02

Pos logit contributions
ishes+0.202
 seas+0.197
 minerals+0.194
 favorites+0.191
 shells+0.190
Neg logit contributions
iren-0.232
 crash-0.212
storm-0.208
 aids-0.204
aned-0.200
Token decided
Token ID3066
Feature activation-1.89e-01

Pos logit contributions
ishes+0.023
 seas+0.022
 shells+0.022
 seaw+0.022
 favorites+0.021
Neg logit contributions
iren-0.028
 crash-0.025
storm-0.025
 earthquake-0.024
 aids-0.024
Token to
Token ID284
Feature activation+4.06e-02

Pos logit contributions
ishes+0.345
 favorites+0.323
 seas+0.322
 minerals+0.321
 shells+0.315
Neg logit contributions
iren-0.314
 crash-0.297
storm-0.286
 knock-0.271
 aids-0.269
Token take
Token ID1011
Feature activation-4.23e-02

Pos logit contributions
iren+0.076
 crash+0.070
storm+0.069
 aids+0.066
 knock+0.064
Neg logit contributions
ishes-0.065
 minerals-0.061
 favorites-0.060
 shells-0.060
 seas-0.060
Token a
Token ID257
Feature activation-1.53e-01

Pos logit contributions
ishes+0.067
 favorites+0.062
sters+0.060
 minerals+0.060
 seas+0.057
Neg logit contributions
iren-0.080
 crash-0.077
 knock-0.070
 aids-0.069
 earthquake-0.068
Token taste
Token ID6938
Feature activation+1.89e-02

Pos logit contributions
 seas+0.297
ishes+0.293
 shells+0.287
 seaw+0.287
 minerals+0.286
Neg logit contributions
iren-0.225
storm-0.198
 aids-0.194
 crash-0.193
aned-0.187
Token of
Token ID286
Feature activation+2.61e-01

Pos logit contributions
iren+0.028
 crash+0.027
storm+0.026
 knock+0.024
 aids+0.024
Neg logit contributions
ishes-0.036
 seas-0.036
 shells-0.036
 seaw-0.035
 minerals-0.035
Token the
Token ID262
Feature activation+4.67e-02

Pos logit contributions
iren+0.458
 crash+0.434
storm+0.418
 knock+0.399
 aids+0.396
Neg logit contributions
ishes-0.449
 favorites-0.419
 seas-0.417
 minerals-0.416
 shells-0.407
Token pie
Token ID2508
Feature activation+1.20e-01

Pos logit contributions
iren+0.072
 crash+0.067
storm+0.065
 aids+0.061
 knock+0.060
Neg logit contributions
ishes-0.090
 favorites-0.085
 seas-0.085
 minerals-0.085
 shells-0.084
Token and
Token ID290
Feature activation+8.42e-05

Pos logit contributions
iren+0.198
 crash+0.190
storm+0.185
 knock+0.173
 earthquake+0.169
Neg logit contributions
ishes-0.216
 favorites-0.208
 seas-0.201
 minerals-0.199
 shells-0.196
Token it
Token ID340
Feature activation+1.33e-02

Pos logit contributions
 crash+0.000
iren+0.000
 knock+0.000
storm+0.000
 aids+0.000
Neg logit contributions
ishes-0.000
 favorites-0.000
 seas-0.000
 minerals-0.000
esty-0.000
Token was
Token ID373
Feature activation+5.89e-02

Pos logit contributions
iren+0.025
 crash+0.023
storm+0.022
 earthquake+0.021
 aids+0.021
Neg logit contributions
ishes-0.022
 minerals-0.020
 shells-0.020
 seas-0.020
 seaw-0.020
Token flash
Token ID7644
Feature activation+3.11e-01

Pos logit contributions
 seas+0.005
 ones+0.005
 dreams+0.005
 shells+0.004
 seaw+0.004
Neg logit contributions
aned-0.004
iren-0.004
ggies-0.004
 aids-0.004
ggy-0.004
Token.
Token ID13
Feature activation+1.98e-02

Pos logit contributions
iren+0.635
aned+0.584
 aids+0.579
 crash+0.566
unt+0.561
Neg logit contributions
 seas-0.394
 ones-0.393
 shells-0.378
 luck-0.373
 seaw-0.362
Token Then
Token ID3244
Feature activation-1.93e-01

Pos logit contributions
iren+0.035
 crash+0.034
storm+0.032
 knock+0.031
aned+0.030
Neg logit contributions
ishes-0.032
 minerals-0.032
 seas-0.032
 favorites-0.032
 shells-0.031
Token,
Token ID11
Feature activation-3.05e-02

Pos logit contributions
ishes+0.425
 favorites+0.401
ish+0.375
esty+0.373
 seaw+0.368
Neg logit contributions
 crash-0.245
 knock-0.225
iren-0.220
 collapse-0.203
 collapsed-0.201
Token another
Token ID1194
Feature activation-2.22e-01

Pos logit contributions
ishes+0.061
 favorites+0.057
ish+0.054
esty+0.054
sters+0.052
Neg logit contributions
 crash-0.046
iren-0.043
 knock-0.043
 tornado-0.039
storm-0.039
Token boom
Token ID14166
Feature activation+2.81e-01

Pos logit contributions
 dreams+0.320
 ones+0.316
 seas+0.305
 favorites+0.305
 minerals+0.303
Neg logit contributions
iren-0.427
aned-0.419
 aids-0.378
 brewing-0.376
 crash-0.373
Token and
Token ID290
Feature activation+2.52e-02

Pos logit contributions
iren+0.521
 aids+0.507
unt+0.461
 earthquake+0.459
 crash+0.458
Neg logit contributions
 seaw-0.401
 shells-0.392
 seas-0.392
 ones-0.391
ishes-0.386
Token another
Token ID1194
Feature activation-2.21e-01

Pos logit contributions
iren+0.050
 crash+0.047
storm+0.046
 aids+0.044
 earthquake+0.044
Neg logit contributions
ishes-0.037
 seas-0.035
 minerals-0.035
 shells-0.035
 seaw-0.034
Token flash
Token ID7644
Feature activation+3.13e-01

Pos logit contributions
 ones+0.329
 dreams+0.327
 seas+0.316
 shells+0.316
 favorites+0.313
Neg logit contributions
iren-0.411
aned-0.395
 aids-0.358
storm-0.356
 brewing-0.356
Token.
Token ID13
Feature activation+2.26e-02

Pos logit contributions
iren+0.570
 aids+0.513
unt+0.499
 crash+0.495
aned+0.488
Neg logit contributions
 seas-0.494
 shells-0.479
 ones-0.478
 seaw-0.458
 luck-0.458
Token The
Token ID383
Feature activation+7.52e-02

Pos logit contributions
iren+0.038
 crash+0.035
storm+0.034
 knock+0.032
 aids+0.032
Neg logit contributions
ishes-0.041
 favorites-0.039
 minerals-0.038
 seas-0.038
 shells-0.038
Token.
Token ID13
Feature activation+1.61e-02

Pos logit contributions
ishes+0.159
 seas+0.153
 favorites+0.151
 shells+0.147
 minerals+0.145
Neg logit contributions
 crash-0.113
iren-0.112
storm-0.107
 earthquake-0.101
 knock-0.099
Token<|endoftext|>
Token ID50256
Feature activation+1.70e-01

Pos logit contributions
iren+0.023
 crash+0.022
storm+0.020
't+0.020
 aids+0.019
Neg logit contributions
ishes-0.033
 seas-0.032
 shells-0.032
 seaw-0.031
 favorites-0.031
TokenOnce
Token ID7454
Feature activation+3.38e-02

Pos logit contributions
iren+0.293
 crash+0.277
storm+0.266
 knock+0.251
 aids+0.249
Neg logit contributions
ishes-0.297
 favorites-0.273
 minerals-0.271
 seas-0.270
 shells-0.268
Token upon
Token ID2402
Feature activation-1.86e-01

Pos logit contributions
iren+0.087
 crash+0.083
storm+0.082
 aids+0.079
 knock+0.079
Neg logit contributions
ishes-0.030
 seas-0.027
 favorites-0.027
 minerals-0.027
 shells-0.026
Token a
Token ID257
Feature activation-1.30e-01

Pos logit contributions
ishes+0.385
sters+0.326
 favorites+0.322
ish+0.320
esty+0.316
Neg logit contributions
 crash-0.293
't-0.281
ggy-0.278
iren-0.270
 knock-0.268
Token time
Token ID640
Feature activation+2.55e-01

Pos logit contributions
ishes+0.326
 favorites+0.312
 seas+0.311
 minerals+0.310
 shells+0.307
Neg logit contributions
iren-0.125
 crash-0.112
storm-0.105
 knock-0.094
 aids-0.093
Token,
Token ID11
Feature activation-2.45e-02

Pos logit contributions
iren+0.424
 crash+0.419
storm+0.393
 knock+0.381
 earthquake+0.371
Neg logit contributions
ishes-0.459
 favorites-0.415
 minerals-0.410
 seas-0.406
 shells-0.403
Token there
Token ID612
Feature activation-5.27e-02

Pos logit contributions
ishes+0.039
 favorites+0.035
 seas+0.035
 minerals+0.035
 shells+0.034
Neg logit contributions
iren-0.046
 crash-0.045
storm-0.043
 knock-0.042
 earthquake-0.041
Token was
Token ID373
Feature activation+8.28e-02

Pos logit contributions
ishes+0.081
 seas+0.080
 favorites+0.080
 minerals+0.078
 shells+0.077
Neg logit contributions
iren-0.103
 crash-0.092
storm-0.091
 aids-0.087
 earthquake-0.086
Token a
Token ID257
Feature activation-1.28e-01

Pos logit contributions
 crash+0.129
iren+0.128
storm+0.125
 earthquake+0.123
ggy+0.121
Neg logit contributions
ishes-0.156
sters-0.141
esty-0.130
 Majesty-0.129
ish-0.128
Token little
Token ID1310
Feature activation+6.85e-02

Pos logit contributions
ishes+0.213
 seas+0.205
 minerals+0.202
 favorites+0.201
 shells+0.198
Neg logit contributions
iren-0.231
 crash-0.213
storm-0.208
 aids-0.201
aned-0.194
Token play
Token ID711
Feature activation+9.76e-03

Pos logit contributions
iren+0.049
 crash+0.048
storm+0.045
 knock+0.044
 aids+0.042
Neg logit contributions
ishes-0.063
 favorites-0.060
 seas-0.059
 minerals-0.058
sters-0.057
Token.
Token ID13
Feature activation+3.39e-02

Pos logit contributions
iren+0.014
 crash+0.014
storm+0.013
 knock+0.012
 aids+0.012
Neg logit contributions
ishes-0.019
 seas-0.018
 minerals-0.018
 favorites-0.018
 seaw-0.018
Token They
Token ID1119
Feature activation+5.26e-02

Pos logit contributions
iren+0.062
 crash+0.058
storm+0.057
 knock+0.053
 aids+0.053
Neg logit contributions
ishes-0.056
 favorites-0.054
 minerals-0.053
 seas-0.052
 shells-0.052
Token do
Token ID466
Feature activation+5.64e-02

Pos logit contributions
iren+0.093
 crash+0.093
storm+0.087
 knock+0.086
 aids+0.082
Neg logit contributions
ishes-0.087
 seas-0.082
 favorites-0.080
 minerals-0.079
 shells-0.078
Token not
Token ID407
Feature activation+2.21e-01

Pos logit contributions
iren+0.046
 crash+0.044
 knock+0.039
 aids+0.037
storm+0.036
Neg logit contributions
ishes-0.148
 favorites-0.140
 minerals-0.140
 seas-0.139
 seaw-0.137
Token fight
Token ID1907
Feature activation+2.64e-01

Pos logit contributions
iren+0.492
aned+0.433
storm+0.429
lf+0.417
 aids+0.415
Neg logit contributions
ishes-0.285
 minerals-0.280
 shells-0.271
 seaw-0.270
 favorites-0.263
Token over
Token ID625
Feature activation+2.55e-01

Pos logit contributions
iren+0.609
storm+0.593
 outage+0.552
aned+0.530
anne+0.529
Neg logit contributions
 ones-0.337
 luck-0.325
 one-0.308
 if-0.299
 something-0.292
Token the
Token ID262
Feature activation+6.91e-02

Pos logit contributions
iren+0.419
 crash+0.399
storm+0.380
 knock+0.366
 aids+0.362
Neg logit contributions
ishes-0.456
 seas-0.428
 favorites-0.428
 minerals-0.425
 shells-0.416
Token banana
Token ID25996
Feature activation+2.17e-02

Pos logit contributions
iren+0.138
 crash+0.134
storm+0.129
 knock+0.124
 earthquake+0.122
Neg logit contributions
ishes-0.101
 favorites-0.093
 seas-0.092
 minerals-0.092
 shells-0.090
Token.
Token ID13
Feature activation+3.54e-02

Pos logit contributions
iren+0.042
 crash+0.038
storm+0.037
 aids+0.036
 knock+0.035
Neg logit contributions
ishes-0.034
 minerals-0.031
 favorites-0.031
 shells-0.031
 seas-0.031
Token<|endoftext|>
Token ID50256
Feature activation+1.76e-01

Pos logit contributions
iren+0.065
 crash+0.061
storm+0.060
 knock+0.057
 earthquake+0.056
Neg logit contributions
ishes-0.057
 favorites-0.056
 minerals-0.055
 seas-0.053
 shells-0.053
Token came
Token ID1625
Feature activation+1.54e-01

Pos logit contributions
iren+0.076
 aids+0.074
 outage+0.073
 earthquake+0.071
aned+0.071
Neg logit contributions
 seaw-0.063
ishes-0.060
sters-0.059
 shells-0.058
 ones-0.057
Token.
Token ID13
Feature activation-9.53e-03

Pos logit contributions
iren+0.269
 crash+0.254
storm+0.249
 aids+0.235
 knock+0.233
Neg logit contributions
ishes-0.268
 minerals-0.249
 favorites-0.248
 seas-0.248
 shells-0.245
Token The
Token ID383
Feature activation+4.14e-02

Pos logit contributions
 minerals+0.011
 dreams+0.011
 seaw+0.011
ishes+0.010
 favorites+0.010
Neg logit contributions
storm-0.020
 brewing-0.019
iren-0.019
lf-0.019
aned-0.019
Token dog
Token ID3290
Feature activation+4.60e-02

Pos logit contributions
iren+0.065
 crash+0.061
storm+0.059
 knock+0.055
 aids+0.055
Neg logit contributions
ishes-0.079
 seas-0.074
 favorites-0.074
 minerals-0.074
 shells-0.073
Token was
Token ID373
Feature activation+4.65e-02

Pos logit contributions
iren+0.108
 outage+0.105
 earthquake+0.102
 aids+0.099
storm+0.095
Neg logit contributions
ishes-0.049
sters-0.048
 seaw-0.048
 ones-0.044
 shells-0.043
Token big
Token ID1263
Feature activation+1.28e-01

Pos logit contributions
storm+0.093
iren+0.088
 outage+0.084
anne+0.081
 earthquake+0.080
Neg logit contributions
 luck-0.066
 prett-0.064
 one-0.063
 best-0.060
 carrots-0.060
Token and
Token ID290
Feature activation-2.58e-03

Pos logit contributions
iren+0.210
 crash+0.202
storm+0.189
 knock+0.181
 earthquake+0.178
Neg logit contributions
ishes-0.233
 favorites-0.222
 seas-0.219
 minerals-0.218
 shells-0.214
Token loud
Token ID7812
Feature activation+2.94e-01

Pos logit contributions
 minerals+0.004
 seaw+0.004
 seas+0.004
 prett+0.004
ishes+0.004
Neg logit contributions
iren-0.005
storm-0.004
 aids-0.004
aned-0.004
 outage-0.004
Token.
Token ID13
Feature activation-4.64e-03

Pos logit contributions
iren+0.637
storm+0.600
 crash+0.586
 outage+0.579
 aids+0.572
Neg logit contributions
ishes-0.345
 ones-0.336
 dreams-0.321
 minerals-0.315
 luck-0.308
Token It
Token ID632
Feature activation+4.34e-02

Pos logit contributions
 minerals+0.005
 dreams+0.005
 seaw+0.005
 favorites+0.005
 So+0.005
Neg logit contributions
storm-0.010
 brewing-0.010
iren-0.010
lf-0.010
aned-0.010
Token bark
Token ID21405
Feature activation+1.20e-01

Pos logit contributions
iren+0.098
 earthquake+0.090
 outage+0.088
 aids+0.087
loe+0.084
Neg logit contributions
 seaw-0.055
 minerals-0.049
 ones-0.049
 shells-0.049
ishes-0.049
Token his
Token ID465
Feature activation-1.92e-02

Pos logit contributions
iren+0.125
storm+0.117
 crash+0.117
 aids+0.109
 knock+0.107
Neg logit contributions
ishes-0.121
 seas-0.118
 minerals-0.117
 shells-0.115
 favorites-0.115
Token room
Token ID2119
Feature activation+1.61e-01

Pos logit contributions
ishes+0.037
 minerals+0.033
 seas+0.033
 favorites+0.033
sters+0.033
Neg logit contributions
iren-0.030
 crash-0.029
storm-0.027
 knock-0.027
 earthquake-0.026
Token.
Token ID13
Feature activation+1.12e-02

Pos logit contributions
iren+0.296
 crash+0.283
storm+0.275
 knock+0.262
 aids+0.260
Neg logit contributions
ishes-0.261
 minerals-0.237
 favorites-0.235
 seas-0.234
 shells-0.230
Token He
Token ID679
Feature activation+3.10e-03

Pos logit contributions
iren+0.021
 crash+0.020
storm+0.020
 aids+0.018
 knock+0.018
Neg logit contributions
 favorites-0.017
ishes-0.016
 minerals-0.016
 seas-0.016
 shells-0.016
Token ran
Token ID4966
Feature activation+1.45e-01

Pos logit contributions
iren+0.006
 crash+0.006
storm+0.006
 aids+0.005
 earthquake+0.005
Neg logit contributions
 seas-0.004
ishes-0.004
 shells-0.004
 favorites-0.004
 minerals-0.004
Token around
Token ID1088
Feature activation+1.39e-01

Pos logit contributions
iren+0.261
storm+0.248
 aids+0.235
 crash+0.231
 collapse+0.229
Neg logit contributions
 seas-0.233
 minerals-0.228
 shells-0.226
 ones-0.222
 favorites-0.219
Token until
Token ID1566
Feature activation-1.65e-01

Pos logit contributions
iren+0.253
 crash+0.235
storm+0.232
 aids+0.218
 knock+0.215
Neg logit contributions
ishes-0.228
 seas-0.219
 minerals-0.218
 favorites-0.216
 shells-0.215
Token he
Token ID339
Feature activation-1.26e-01

Pos logit contributions
ishes+0.203
 seas+0.187
 favorites+0.185
 minerals+0.185
 shells+0.182
Neg logit contributions
iren-0.369
 crash-0.352
storm-0.343
 aids-0.329
 knock-0.329
Token was
Token ID373
Feature activation+7.02e-02

Pos logit contributions
 seas+0.162
 shells+0.155
 favorites+0.152
 seaw+0.149
ishes+0.143
Neg logit contributions
iren-0.282
 crash-0.254
storm-0.253
 earthquake-0.252
 aids-0.248
Token tired
Token ID10032
Feature activation-4.43e-02

Pos logit contributions
iren+0.137
storm+0.133
 aids+0.121
 crash+0.119
unt+0.115
Neg logit contributions
 seas-0.106
 shells-0.104
 luck-0.104
 favorites-0.102
 minerals-0.098
Token,
Token ID11
Feature activation-3.79e-02

Pos logit contributions
ishes+0.062
 minerals+0.061
 seas+0.060
 shells+0.059
 seaw+0.058
Neg logit contributions
iren-0.088
 crash-0.081
storm-0.081
 aids-0.079
 knock-0.076
Token.
Token ID13
Feature activation-4.99e-02

Pos logit contributions
ishes+0.341
 seas+0.321
 minerals+0.318
 shells+0.315
 favorites+0.313
Neg logit contributions
iren-0.418
 crash-0.392
storm-0.380
 knock-0.367
 aids-0.364
Token He
Token ID679
Feature activation-5.28e-02

Pos logit contributions
ishes+0.090
 seas+0.084
 shells+0.083
 favorites+0.082
 minerals+0.082
Neg logit contributions
iren-0.084
 crash-0.079
storm-0.075
 aids-0.073
 knock-0.072
Token was
Token ID373
Feature activation+1.72e-02

Pos logit contributions
ishes+0.092
 favorites+0.086
 seas+0.086
 minerals+0.085
 shells+0.085
Neg logit contributions
iren-0.092
 crash-0.086
storm-0.084
 earthquake-0.079
 aids-0.079
Token safe
Token ID3338
Feature activation+1.88e-02

Pos logit contributions
iren+0.037
storm+0.036
 crash+0.033
 earthquake+0.032
 tornado+0.031
Neg logit contributions
 luck-0.022
ishes-0.021
 shells-0.021
 favorites-0.021
 prett-0.021
Token and
Token ID290
Feature activation-3.07e-02

Pos logit contributions
iren+0.032
 crash+0.031
storm+0.030
 knock+0.028
 aids+0.028
Neg logit contributions
ishes-0.033
 favorites-0.031
 seas-0.030
 minerals-0.030
 shells-0.030
Token happy
Token ID3772
Feature activation-8.89e-03

Pos logit contributions
ishes+0.056
 favorites+0.053
 seas+0.051
 minerals+0.051
 shells+0.049
Neg logit contributions
iren-0.050
 crash-0.049
storm-0.046
 knock-0.045
 aids-0.044
Token now
Token ID783
Feature activation+3.32e-02

Pos logit contributions
ishes+0.015
 favorites+0.014
 seas+0.014
 minerals+0.014
 shells+0.013
Neg logit contributions
iren-0.016
 crash-0.015
storm-0.015
 knock-0.014
 aids-0.014
Token.
Token ID13
Feature activation-3.54e-02

Pos logit contributions
iren+0.069
 crash+0.064
storm+0.063
 aids+0.060
 knock+0.060
Neg logit contributions
ishes-0.046
 minerals-0.044
 seas-0.043
 favorites-0.042
 shells-0.042
Token<|endoftext|>
Token ID50256
Feature activation+1.17e-01

Pos logit contributions
ishes+0.066
 seas+0.062
 shells+0.061
 favorites+0.060
 minerals+0.060
Neg logit contributions
iren-0.058
 crash-0.054
storm-0.051
 aids-0.050
 knock-0.049
TokenOnce
Token ID7454
Feature activation-2.00e-02

Pos logit contributions
iren+0.259
 crash+0.250
storm+0.246
 knock+0.238
 earthquake+0.236
Neg logit contributions
ishes-0.139
 seas-0.131
 favorites-0.129
 minerals-0.129
 shells-0.125
Token upon
Token ID2402
Feature activation-2.39e-01

Pos logit contributions
ishes+0.015
 seas+0.014
 favorites+0.014
 minerals+0.013
 shells+0.013
Neg logit contributions
iren-0.054
 crash-0.052
storm-0.051
 aids-0.050
 knock-0.049
Token
Token ID198
Feature activation-7.18e-03

Pos logit contributions
iren+0.023
 crash+0.022
storm+0.021
 knock+0.020
 aids+0.020
Neg logit contributions
ishes-0.023
 favorites-0.022
 minerals-0.021
 seas-0.021
 shells-0.021
Token
Token ID198
Feature activation-6.39e-03

Pos logit contributions
 favorites+0.009
ishes+0.009
 minerals+0.009
 shells+0.009
 seas+0.009
Neg logit contributions
storm-0.014
iren-0.014
 crash-0.014
 earthquake-0.013
 aids-0.013
TokenThey
Token ID2990
Feature activation-3.33e-02

Pos logit contributions
ishes+0.010
 favorites+0.009
 seas+0.009
 minerals+0.009
 shells+0.009
Neg logit contributions
iren-0.012
 crash-0.011
storm-0.011
 earthquake-0.011
 aids-0.010
Token made
Token ID925
Feature activation+2.14e-02

Pos logit contributions
ishes+0.052
 seas+0.049
 favorites+0.049
 shells+0.049
 minerals+0.048
Neg logit contributions
iren-0.064
 crash-0.059
storm-0.058
 aids-0.055
 earthquake-0.055
Token life
Token ID1204
Feature activation-1.07e-01

Pos logit contributions
iren+0.040
 crash+0.039
 knock+0.036
 aids+0.036
storm+0.036
Neg logit contributions
ishes-0.034
 minerals-0.031
 favorites-0.031
 seas-0.030
 seaw-0.030
Token happy
Token ID3772
Feature activation+3.72e-02

Pos logit contributions
ishes+0.174
 favorites+0.162
 minerals+0.160
 seas+0.158
 seaw+0.155
Neg logit contributions
iren-0.200
 crash-0.192
storm-0.182
 knock-0.177
 aids-0.175
Token and
Token ID290
Feature activation+1.68e-02

Pos logit contributions
iren+0.065
 crash+0.062
storm+0.059
 knock+0.057
 aids+0.056
Neg logit contributions
ishes-0.065
 favorites-0.060
 seas-0.060
 minerals-0.060
 shells-0.059
Token beautiful
Token ID4950
Feature activation-1.31e-02

Pos logit contributions
iren+0.029
 crash+0.027
storm+0.026
 aids+0.025
 knock+0.025
Neg logit contributions
ishes-0.030
 favorites-0.028
 minerals-0.028
 seas-0.028
 shells-0.027
Token.
Token ID13
Feature activation+1.77e-02

Pos logit contributions
ishes+0.022
 favorites+0.021
 minerals+0.021
 seas+0.021
 seaw+0.020
Neg logit contributions
iren-0.023
 crash-0.022
storm-0.021
 knock-0.020
 aids-0.020
Token<|endoftext|>
Token ID50256
Feature activation+1.59e-01

Pos logit contributions
iren+0.032
 crash+0.030
storm+0.029
 knock+0.028
 aids+0.027
Neg logit contributions
ishes-0.030
 favorites-0.028
 minerals-0.028
 seas-0.028
 shells-0.027
TokenAnna
Token ID31160
Feature activation+1.39e-01

Pos logit contributions
iren+0.364
 crash+0.348
storm+0.339
 knock+0.326
 aids+0.325
Neg logit contributions
ishes-0.189
 favorites-0.171
 seas-0.170
 minerals-0.169
 shells-0.165
Token said
Token ID531
Feature activation-9.27e-03

Pos logit contributions
iren+0.481
 crash+0.456
storm+0.442
 knock+0.419
 aids+0.411
Neg logit contributions
ishes-0.514
 minerals-0.481
 favorites-0.481
 seas-0.480
 shells-0.471
Token the
Token ID262
Feature activation+6.46e-02

Pos logit contributions
ishes+0.014
 favorites+0.013
 seas+0.013
 minerals+0.013
 shells+0.013
Neg logit contributions
iren-0.018
 crash-0.017
storm-0.017
 knock-0.016
 aids-0.016
Token freezer
Token ID30967
Feature activation+1.52e-04

Pos logit contributions
iren+0.117
 crash+0.109
storm+0.107
 aids+0.103
 knock+0.100
Neg logit contributions
ishes-0.105
 minerals-0.102
 seas-0.101
 favorites-0.101
 shells-0.099
Token was
Token ID373
Feature activation+7.36e-02

Pos logit contributions
iren+0.000
 crash+0.000
storm+0.000
 aids+0.000
 earthquake+0.000
Neg logit contributions
ishes-0.000
 luck-0.000
 minerals-0.000
 shells-0.000
 seas-0.000
Token too
Token ID1165
Feature activation-1.50e-03

Pos logit contributions
iren+0.159
storm+0.138
 aids+0.137
 crash+0.135
unt+0.129
Neg logit contributions
 luck-0.109
 prett-0.099
 seas-0.099
 minerals-0.097
 shells-0.096
Token cold
Token ID4692
Feature activation+1.37e-01

Pos logit contributions
ishes+0.003
 seas+0.003
 minerals+0.003
 luck+0.002
 seaw+0.002
Neg logit contributions
iren-0.003
 crash-0.002
 aids-0.002
storm-0.002
 earthquake-0.002
Token for
Token ID329
Feature activation-3.29e-02

Pos logit contributions
iren+0.277
 aids+0.267
 crash+0.257
 knock+0.254
lf+0.248
Neg logit contributions
ishes-0.185
 luck-0.178
 ones-0.176
 minerals-0.176
 seas-0.171
Token anyone
Token ID2687
Feature activation-4.12e-03

Pos logit contributions
 minerals+0.034
 seas+0.034
 shells+0.033
ishes+0.033
 luck+0.033
Neg logit contributions
iren-0.079
storm-0.074
 outage-0.073
umpy-0.072
 crash-0.071
Token to
Token ID284
Feature activation+5.94e-02

Pos logit contributions
ishes+0.007
 shells+0.006
 minerals+0.006
 favorites+0.006
 seas+0.006
Neg logit contributions
iren-0.008
 crash-0.007
storm-0.007
 aids-0.007
 earthquake-0.007
Token sleep
Token ID3993
Feature activation+7.70e-02

Pos logit contributions
iren+0.114
 aids+0.100
storm+0.099
 crash+0.098
aned+0.095
Neg logit contributions
 seaw-0.091
 shells-0.089
 minerals-0.089
ishes-0.089
 seas-0.089
Token in
Token ID287
Feature activation+8.15e-02

Pos logit contributions
iren+0.166
 crash+0.155
storm+0.148
 knock+0.146
 aids+0.145
Neg logit contributions
 seas-0.098
ishes-0.096
 minerals-0.093
 shells-0.092
 luck-0.092
Token and
Token ID290
Feature activation+6.55e-03

Pos logit contributions
iren+0.023
 crash+0.022
storm+0.022
 knock+0.020
 aids+0.020
Neg logit contributions
ishes-0.025
 seas-0.024
 minerals-0.024
 favorites-0.023
 seaw-0.023
Token cars
Token ID5006
Feature activation+1.22e-02

Pos logit contributions
 crash+0.011
iren+0.011
 knock+0.010
storm+0.010
 earthquake+0.010
Neg logit contributions
ishes-0.012
 favorites-0.011
 seas-0.011
 minerals-0.010
sters-0.010
Token.
Token ID13
Feature activation+7.36e-03

Pos logit contributions
iren+0.024
 crash+0.023
storm+0.023
 aids+0.022
 earthquake+0.022
Neg logit contributions
ishes-0.018
 favorites-0.017
 seas-0.016
 shells-0.016
 minerals-0.016
Token One
Token ID1881
Feature activation-1.15e-01

Pos logit contributions
iren+0.012
 crash+0.012
storm+0.011
 knock+0.011
 aids+0.011
Neg logit contributions
ishes-0.013
 seas-0.012
sters-0.012
 minerals-0.012
 luck-0.012
Token day
Token ID1110
Feature activation+6.78e-02

Pos logit contributions
 ones+0.138
 dreams+0.135
 one+0.129
 favorites+0.127
 seas+0.121
Neg logit contributions
aned-0.257
iren-0.255
 crash-0.237
storm-0.236
 brewing-0.231
Token,
Token ID11
Feature activation-4.32e-02

Pos logit contributions
 crash+0.092
iren+0.091
't+0.084
 knock+0.083
storm+0.081
Neg logit contributions
ishes-0.138
esty-0.126
 prett-0.125
 nic-0.124
 minerals-0.123
Token Anna
Token ID11735
Feature activation+1.85e-01

Pos logit contributions
ishes+0.089
esty+0.080
sters+0.079
 minerals+0.079
 Majesty+0.079
Neg logit contributions
 crash-0.057
iren-0.054
 knock-0.054
't-0.052
storm-0.052
Token has
Token ID468
Feature activation+3.39e-02

Pos logit contributions
iren+0.360
 crash+0.343
storm+0.333
 knock+0.319
 aids+0.316
Neg logit contributions
ishes-0.279
 seas-0.259
 minerals-0.258
 favorites-0.258
 shells-0.253
Token a
Token ID257
Feature activation-1.55e-01

Pos logit contributions
iren+0.079
 crash+0.076
storm+0.074
 knock+0.071
 aids+0.071
Neg logit contributions
ishes-0.039
 favorites-0.035
 seas-0.035
 minerals-0.035
 shells-0.034
Token new
Token ID649
Feature activation-6.69e-02

Pos logit contributions
 favorites+0.245
 seas+0.241
ishes+0.240
 minerals+0.230
 ones+0.228
Neg logit contributions
iren-0.297
 crash-0.261
aned-0.260
storm-0.256
 aids-0.250
Token doll
Token ID3654
Feature activation+1.10e-01

Pos logit contributions
ishes+0.101
 favorites+0.099
 seas+0.097
 minerals+0.095
 shells+0.094
Neg logit contributions
iren-0.131
 crash-0.121
storm-0.118
 aids-0.113
 collapse-0.111
Token not
Token ID407
Feature activation+2.15e-01

Pos logit contributions
ishes+0.139
 luck+0.136
 minerals+0.134
 shells+0.130
 prett+0.129
Neg logit contributions
iren-0.184
storm-0.182
 crash-0.169
 aids-0.163
bell-0.162
Token bad
Token ID2089
Feature activation+2.35e-01

Pos logit contributions
iren+0.430
storm+0.417
 aids+0.380
 crash+0.379
bell+0.375
Neg logit contributions
ishes-0.333
 luck-0.324
 minerals-0.305
 shells-0.294
 favorites-0.289
Token.
Token ID13
Feature activation+3.54e-02

Pos logit contributions
iren+0.382
 crash+0.366
storm+0.340
 earthquake+0.331
 knock+0.327
Neg logit contributions
ishes-0.433
 seas-0.416
 favorites-0.407
 minerals-0.401
 shells-0.397
Token The
Token ID383
Feature activation+7.18e-02

Pos logit contributions
iren+0.058
 crash+0.053
 earthquake+0.049
storm+0.049
 aids+0.049
Neg logit contributions
ishes-0.066
 seas-0.065
 favorites-0.062
 shells-0.062
 minerals-0.061
Token eggs
Token ID9653
Feature activation-1.40e-01

Pos logit contributions
iren+0.147
 crash+0.142
storm+0.137
 knock+0.132
 earthquake+0.131
Neg logit contributions
ishes-0.102
 favorites-0.093
 seas-0.093
 minerals-0.093
 shells-0.090
Token are
Token ID389
Feature activation-9.21e-02

Pos logit contributions
ishes+0.123
ish+0.104
 dreams+0.099
 shells+0.099
 luck+0.096
Neg logit contributions
iren-0.357
 aids-0.342
storm-0.341
unt-0.328
 crash-0.327
Token not
Token ID407
Feature activation+2.17e-01

Pos logit contributions
ishes+0.150
 luck+0.147
 prett+0.145
 minerals+0.145
 shells+0.135
Neg logit contributions
iren-0.186
storm-0.167
 crash-0.159
 aids-0.158
chair-0.150
Token broken
Token ID5445
Feature activation+2.69e-01

Pos logit contributions
iren+0.438
storm+0.405
 crash+0.400
 aids+0.387
 knock+0.376
Neg logit contributions
ishes-0.343
 minerals-0.314
 luck-0.305
 shells-0.302
 seas-0.296
Token,
Token ID11
Feature activation-2.08e-02

Pos logit contributions
iren+0.497
 crash+0.468
storm+0.456
 aids+0.434
 knock+0.434
Neg logit contributions
ishes-0.440
 minerals-0.408
 seas-0.407
 favorites-0.406
 shells-0.399
Token they
Token ID484
Feature activation-8.49e-03

Pos logit contributions
ishes+0.032
 minerals+0.030
 seas+0.030
 shells+0.029
 seaw+0.029
Neg logit contributions
iren-0.041
 crash-0.038
storm-0.037
 knock-0.036
 aids-0.035
Token are
Token ID389
Feature activation-9.09e-02

Pos logit contributions
ishes+0.010
 favorites+0.009
 minerals+0.009
 seas+0.009
 shells+0.009
Neg logit contributions
iren-0.019
 crash-0.018
storm-0.018
 aids-0.017
 knock-0.017
Token
Token ID198
Feature activation-2.15e-03

Pos logit contributions
 favorites+0.003
 seas+0.003
ishes+0.003
 minerals+0.003
 shells+0.003
Neg logit contributions
iren-0.005
storm-0.005
 crash-0.005
 earthquake-0.005
 aids-0.005
TokenTwo
Token ID7571
Feature activation-4.02e-02

Pos logit contributions
 seas+0.002
 ones+0.002
 minerals+0.002
 favorites+0.002
 seaw+0.002
Neg logit contributions
iren-0.004
 crash-0.004
 earthquake-0.004
aned-0.004
storm-0.004
Token curious
Token ID11040
Feature activation-9.33e-02

Pos logit contributions
ishes+0.044
 favorites+0.039
 seas+0.039
 shells+0.038
 minerals+0.038
Neg logit contributions
iren-0.098
 crash-0.094
storm-0.093
 aids-0.087
 knock-0.087
Token little
Token ID1310
Feature activation+6.56e-02

Pos logit contributions
ishes+0.140
 minerals+0.131
 seas+0.130
 favorites+0.128
 shells+0.127
Neg logit contributions
iren-0.186
 crash-0.177
storm-0.174
 knock-0.165
 collapse-0.164
Token children
Token ID1751
Feature activation-1.78e-02

Pos logit contributions
 crash+0.108
iren+0.108
 knock+0.099
 earthquake+0.099
storm+0.097
Neg logit contributions
ishes-0.107
 favorites-0.103
 seas-0.101
 seaw-0.101
 minerals-0.097
Token,
Token ID11
Feature activation-3.39e-02

Pos logit contributions
ishes+0.032
 seas+0.031
 favorites+0.031
 minerals+0.030
 shells+0.030
Neg logit contributions
iren-0.029
 crash-0.028
storm-0.026
 knock-0.025
 aids-0.025
Token called
Token ID1444
Feature activation+1.27e-01

Pos logit contributions
ishes+0.056
 minerals+0.053
 seas+0.053
 favorites+0.052
 shells+0.052
Neg logit contributions
iren-0.062
 crash-0.058
storm-0.057
 aids-0.053
 knock-0.053
Token Max
Token ID5436
Feature activation+1.24e-01

Pos logit contributions
iren+0.200
 crash+0.190
storm+0.180
 knock+0.173
 aids+0.171
Neg logit contributions
ishes-0.241
 favorites-0.226
 seas-0.225
 minerals-0.223
 shells-0.219
Token and
Token ID290
Feature activation+2.24e-02

Pos logit contributions
iren+0.234
 crash+0.221
storm+0.215
 knock+0.204
 aids+0.204
Neg logit contributions
ishes-0.200
 favorites-0.185
 minerals-0.184
 seas-0.183
 shells-0.180
Token Jenny
Token ID28437
Feature activation+5.61e-02

Pos logit contributions
iren+0.032
 crash+0.032
storm+0.029
 knock+0.029
 aids+0.028
Neg logit contributions
ishes-0.045
 favorites-0.042
 seas-0.042
 minerals-0.041
sters-0.040
Token,
Token ID11
Feature activation-3.24e-02

Pos logit contributions
iren+0.103
 crash+0.098
storm+0.095
 knock+0.090
 aids+0.090
Neg logit contributions
ishes-0.092
 favorites-0.085
 seas-0.085
 minerals-0.085
 shells-0.083
Token under
Token ID739
Feature activation+1.52e-01

Pos logit contributions
iren+0.206
storm+0.188
 crash+0.187
 aids+0.180
 knock+0.178
Neg logit contributions
 seas-0.108
 minerals-0.107
 shells-0.101
 luck-0.101
ishes-0.100
Token a
Token ID257
Feature activation-1.23e-01

Pos logit contributions
iren+0.312
 crash+0.297
storm+0.289
 knock+0.276
 aids+0.275
Neg logit contributions
ishes-0.217
 favorites-0.200
 seas-0.198
 minerals-0.198
 shells-0.194
Token big
Token ID1263
Feature activation+1.67e-01

Pos logit contributions
 seas+0.214
ishes+0.211
 minerals+0.209
 seaw+0.208
 shells+0.206
Neg logit contributions
iren-0.204
 crash-0.186
storm-0.183
 aids-0.180
aned-0.174
Token tree
Token ID5509
Feature activation+1.05e-01

Pos logit contributions
iren+0.317
 aids+0.300
aned+0.296
storm+0.285
 crash+0.278
Neg logit contributions
 seas-0.252
 seaw-0.245
 minerals-0.244
ishes-0.241
 shells-0.239
Token with
Token ID351
Feature activation+8.26e-02

Pos logit contributions
iren+0.191
 crash+0.180
storm+0.174
 aids+0.166
 knock+0.165
Neg logit contributions
ishes-0.172
 seas-0.162
 favorites-0.161
 minerals-0.161
 shells-0.158
Token lots
Token ID6041
Feature activation-1.69e-01

Pos logit contributions
iren+0.176
 crash+0.172
storm+0.161
 aids+0.159
 knock+0.158
Neg logit contributions
ishes-0.109
 favorites-0.096
 minerals-0.091
sters-0.090
 seas-0.090
Token of
Token ID286
Feature activation+2.89e-01

Pos logit contributions
 minerals+0.379
 shells+0.378
ishes+0.378
 seas+0.372
 seaw+0.367
Neg logit contributions
storm-0.199
iren-0.194
 crash-0.184
 aids-0.169
 knock-0.167
Token shade
Token ID17979
Feature activation+3.69e-02

Pos logit contributions
iren+0.573
 crash+0.547
storm+0.527
 knock+0.508
 aids+0.504
Neg logit contributions
ishes-0.429
 favorites-0.393
 seas-0.391
 minerals-0.389
 shells-0.381
Token to
Token ID284
Feature activation+7.16e-02

Pos logit contributions
iren+0.072
 crash+0.071
 aids+0.070
 knock+0.068
storm+0.067
Neg logit contributions
ishes-0.053
 seas-0.051
 shells-0.051
 minerals-0.051
 seaw-0.049
Token protect
Token ID1805
Feature activation+1.84e-02

Pos logit contributions
iren+0.127
 crash+0.123
storm+0.117
 knock+0.115
 aids+0.111
Neg logit contributions
ishes-0.122
 favorites-0.112
 seas-0.111
 minerals-0.111
 shells-0.107
Token him
Token ID683
Feature activation-7.93e-02

Pos logit contributions
iren+0.038
 crash+0.036
storm+0.036
 knock+0.034
 aids+0.033
Neg logit contributions
ishes-0.026
 minerals-0.024
 seas-0.024
 shells-0.024
 favorites-0.024
Token Joe
Token ID5689
Feature activation-2.25e-02

Pos logit contributions
iren+0.017
 crash+0.016
storm+0.016
 knock+0.015
 aids+0.015
Neg logit contributions
ishes-0.015
 favorites-0.014
 minerals-0.014
 seas-0.014
 shells-0.014
Token hugged
Token ID41130
Feature activation+1.12e-01

Pos logit contributions
ishes+0.037
 favorites+0.034
 seas+0.034
 minerals+0.033
 shells+0.033
Neg logit contributions
iren-0.042
 crash-0.039
storm-0.038
 earthquake-0.037
 aids-0.036
Token his
Token ID465
Feature activation-1.10e-02

Pos logit contributions
iren+0.219
 crash+0.207
storm+0.206
 knock+0.191
 aids+0.190
Neg logit contributions
ishes-0.170
 seas-0.159
 minerals-0.158
 shells-0.157
 favorites-0.157
Token dad
Token ID9955
Feature activation-7.07e-02

Pos logit contributions
ishes+0.018
 minerals+0.016
 seas+0.016
 seaw+0.016
 favorites+0.016
Neg logit contributions
iren-0.019
 crash-0.018
 knock-0.018
 aids-0.017
lf-0.017
Token tightly
Token ID17707
Feature activation+1.12e-02

Pos logit contributions
ishes+0.130
 favorites+0.123
 minerals+0.121
 seas+0.121
 shells+0.120
Neg logit contributions
iren-0.113
 crash-0.109
storm-0.101
 knock-0.100
 aids-0.099
Token,
Token ID11
Feature activation-3.37e-02

Pos logit contributions
iren+0.021
 crash+0.020
storm+0.019
 knock+0.018
 aids+0.018
Neg logit contributions
ishes-0.017
 seas-0.016
 minerals-0.016
 favorites-0.016
 shells-0.016
Token and
Token ID290
Feature activation+2.17e-02

Pos logit contributions
ishes+0.051
 seas+0.049
 minerals+0.048
 shells+0.048
 favorites+0.048
Neg logit contributions
iren-0.065
 crash-0.060
storm-0.060
 earthquake-0.057
 aids-0.057
Token he
Token ID339
Feature activation-1.22e-01

Pos logit contributions
iren+0.037
 crash+0.036
storm+0.034
 knock+0.034
 aids+0.033
Neg logit contributions
ishes-0.038
 favorites-0.035
 minerals-0.034
 seas-0.034
 shells-0.033
Token was
Token ID373
Feature activation+7.63e-02

Pos logit contributions
ishes+0.210
 favorites+0.197
 seas+0.197
 minerals+0.195
 shells+0.193
Neg logit contributions
iren-0.214
 crash-0.200
storm-0.195
 earthquake-0.183
 aids-0.183
Token so
Token ID523
Feature activation-5.86e-04

Pos logit contributions
iren+0.176
storm+0.165
 crash+0.155
 earthquake+0.153
 aids+0.149
Neg logit contributions
 luck-0.089
 nic-0.082
 dreams-0.082
 favorites-0.081
ishes-0.080
Token happy
Token ID3772
Feature activation+5.54e-02

Pos logit contributions
 luck+0.001
ishes+0.001
 favorites+0.001
 seas+0.001
 shells+0.001
Neg logit contributions
iren-0.001
storm-0.001
 crash-0.001
 earthquake-0.001
 aids-0.001
Token sw
Token ID1509
Feature activation-9.52e-02

Pos logit contributions
iren+0.084
 crash+0.082
storm+0.079
 knock+0.077
 aids+0.073
Neg logit contributions
ishes-0.096
 seas-0.093
 favorites-0.092
 minerals-0.090
 shells-0.088
Tokenam
Token ID321
Feature activation-1.36e-01

Pos logit contributions
 minerals+0.141
 seas+0.141
 ones+0.141
 favorites+0.139
 seaw+0.138
Neg logit contributions
iren-0.163
aned-0.159
 crash-0.153
 aids-0.148
 collapsed-0.145
Token to
Token ID284
Feature activation+4.37e-02

Pos logit contributions
ishes+0.240
 seas+0.225
 minerals+0.224
 favorites+0.223
 shells+0.221
Neg logit contributions
iren-0.237
 crash-0.223
storm-0.217
 knock-0.205
 aids-0.204
Token the
Token ID262
Feature activation+4.87e-02

Pos logit contributions
iren+0.065
 crash+0.065
 knock+0.059
storm+0.059
 earthquake+0.056
Neg logit contributions
ishes-0.087
 favorites-0.082
 seas-0.079
 minerals-0.079
sters-0.078
Token oy
Token ID35104
Feature activation-2.81e-01

Pos logit contributions
 crash+0.095
 knock+0.093
iren+0.090
 earthquake+0.087
storm+0.086
Neg logit contributions
ishes-0.071
 favorites-0.065
lets-0.061
 combinations-0.058
 experiences-0.057
Tokenster
Token ID1706
Feature activation-3.44e-01

Pos logit contributions
 First+0.445
First+0.418
 combinations+0.418
 favorites+0.410
 experiences+0.406
Neg logit contributions
iren-0.444
ork-0.409
ggy-0.405
 knock-0.400
 crash-0.394
Token and
Token ID290
Feature activation+8.20e-03

Pos logit contributions
ishes+0.671
 favorites+0.655
 seas+0.633
 minerals+0.616
 luck+0.612
Neg logit contributions
 crash-0.485
iren-0.484
 knock-0.440
storm-0.426
 aids-0.412
Token spoke
Token ID5158
Feature activation+7.43e-02

Pos logit contributions
iren+0.013
 crash+0.013
storm+0.012
 knock+0.012
 aids+0.011
Neg logit contributions
ishes-0.015
 favorites-0.015
 seas-0.014
 minerals-0.014
 shells-0.013
Token softly
Token ID26625
Feature activation+2.96e-02

Pos logit contributions
 crash+0.096
iren+0.096
 aids+0.090
 brewing+0.086
 knock+0.085
Neg logit contributions
ishes-0.155
 favorites-0.148
 seas-0.141
 minerals-0.137
 seaw-0.136
Token.
Token ID13
Feature activation+3.42e-03

Pos logit contributions
iren+0.044
 crash+0.043
storm+0.040
 aids+0.039
 knock+0.039
Neg logit contributions
ishes-0.057
 seas-0.055
 favorites-0.053
 minerals-0.052
 shells-0.052
Token
Token ID220
Feature activation-9.58e-02

Pos logit contributions
iren+0.005
 crash+0.005
storm+0.005
 knock+0.004
 aids+0.004
Neg logit contributions
ishes-0.007
 seas-0.006
 favorites-0.006
 minerals-0.006
 shells-0.006
Token time
Token ID640
Feature activation+2.60e-01

Pos logit contributions
ishes+0.277
 favorites+0.275
 seas+0.272
 minerals+0.266
 seaw+0.263
Neg logit contributions
iren-0.144
 crash-0.127
storm-0.116
 aids-0.108
 knock-0.107
Token there
Token ID612
Feature activation-4.84e-02

Pos logit contributions
iren+0.505
 crash+0.481
storm+0.467
 knock+0.445
 aids+0.443
Neg logit contributions
ishes-0.397
 favorites-0.366
 seas-0.365
 minerals-0.364
 shells-0.357
Token was
Token ID373
Feature activation+8.92e-02

Pos logit contributions
 favorites+0.060
 seas+0.059
 dreams+0.058
 minerals+0.058
ishes+0.058
Neg logit contributions
iren-0.109
 crash-0.096
storm-0.094
 aids-0.093
aned-0.091
Token an
Token ID281
Feature activation-1.65e-01

Pos logit contributions
iren+0.160
 crash+0.158
storm+0.155
 earthquake+0.152
 tornado+0.147
Neg logit contributions
ishes-0.147
sters-0.132
 minerals-0.125
 favorites-0.123
esty-0.122
Token oy
Token ID35104
Feature activation-2.59e-01

Pos logit contributions
ishes+0.275
 minerals+0.266
 seas+0.265
 shells+0.260
 favorites+0.257
Neg logit contributions
iren-0.298
 crash-0.284
storm-0.276
 aids-0.257
 collapse-0.257
Tokenster
Token ID1706
Feature activation-3.18e-01

Pos logit contributions
 First+0.334
 combinations+0.328
 favorites+0.306
 experiences+0.296
First+0.291
Neg logit contributions
iren-0.490
lf-0.479
ggy-0.478
 knock-0.458
maker-0.452
Token that
Token ID326
Feature activation+9.40e-02

Pos logit contributions
ishes+0.614
 favorites+0.581
 seas+0.571
 minerals+0.570
 seaw+0.556
Neg logit contributions
iren-0.490
 crash-0.456
storm-0.438
 knock-0.427
 aids-0.407
Token lived
Token ID5615
Feature activation+5.71e-02

Pos logit contributions
 crash+0.100
 knock+0.099
storm+0.094
 shattered+0.092
 knocking+0.091
Neg logit contributions
ishes-0.213
 favorites-0.197
 combinations-0.189
esty-0.186
lets-0.183
Token at
Token ID379
Feature activation-4.14e-02

Pos logit contributions
iren+0.080
 crash+0.075
storm+0.070
 knock+0.067
 aids+0.065
Neg logit contributions
ishes-0.118
 favorites-0.111
 minerals-0.109
 seas-0.108
 shells-0.106
Token the
Token ID262
Feature activation+7.86e-02

Pos logit contributions
ishes+0.083
lets+0.077
 favorites+0.076
esty+0.075
sters+0.073
Neg logit contributions
 crash-0.060
iren-0.059
storm-0.057
 earthquake-0.056
 knock-0.055
Token bottom
Token ID4220
Feature activation+1.29e-01

Pos logit contributions
storm+0.131
 crash+0.130
iren+0.130
 knock+0.128
 earthquake+0.124
Neg logit contributions
ishes-0.139
 favorites-0.120
lets-0.119
 combinations-0.114
 experiences-0.112
Token and
Token ID290
Feature activation-7.04e-03

Pos logit contributions
iren+0.072
 crash+0.068
storm+0.067
 knock+0.063
 aids+0.062
Neg logit contributions
ishes-0.067
 minerals-0.063
 seas-0.062
 favorites-0.062
 shells-0.062
Token slowly
Token ID6364
Feature activation+1.43e-02

Pos logit contributions
ishes+0.013
 favorites+0.012
 seas+0.012
 minerals+0.012
 shells+0.011
Neg logit contributions
iren-0.012
 crash-0.011
storm-0.011
 knock-0.010
 aids-0.010
Token walk
Token ID2513
Feature activation-7.59e-02

Pos logit contributions
iren+0.026
storm+0.025
 crash+0.024
 knock+0.023
 aids+0.023
Neg logit contributions
ishes-0.023
 favorites-0.021
 minerals-0.021
 shells-0.021
 luck-0.020
Token away
Token ID1497
Feature activation-2.93e-03

Pos logit contributions
ishes+0.128
 seas+0.119
 minerals+0.119
 favorites+0.118
 shells+0.117
Neg logit contributions
iren-0.136
 crash-0.129
storm-0.125
 knock-0.119
 aids-0.118
Token."
Token ID526
Feature activation-2.47e-02

Pos logit contributions
ishes+0.005
 minerals+0.005
 favorites+0.005
 seas+0.005
 shells+0.004
Neg logit contributions
iren-0.005
 crash-0.005
storm-0.005
 knock-0.005
 aids-0.005
Token So
Token ID1406
Feature activation-3.11e-01

Pos logit contributions
ishes+0.041
 favorites+0.039
 minerals+0.038
 seas+0.038
 shells+0.037
Neg logit contributions
iren-0.045
 crash-0.042
storm-0.041
 knock-0.039
 aids-0.039
Token,
Token ID11
Feature activation-5.91e-02

Pos logit contributions
ishes+0.536
 favorites+0.501
 seas+0.497
 minerals+0.496
 shells+0.486
Neg logit contributions
iren-0.540
 crash-0.523
storm-0.497
 knock-0.479
 earthquake-0.470
Token Lily
Token ID20037
Feature activation+1.47e-01

Pos logit contributions
ishes+0.105
 minerals+0.100
 seas+0.100
 shells+0.099
 favorites+0.098
Neg logit contributions
iren-0.102
 crash-0.091
storm-0.091
 aids-0.085
 outage-0.084
Token did
Token ID750
Feature activation-2.84e-03

Pos logit contributions
iren+0.273
 crash+0.259
storm+0.251
 knock+0.238
 aids+0.237
Neg logit contributions
ishes-0.239
 favorites-0.221
 seas-0.221
 minerals-0.220
 shells-0.217
Token just
Token ID655
Feature activation-9.64e-02

Pos logit contributions
ishes+0.005
 seas+0.005
 favorites+0.005
 minerals+0.005
 shells+0.005
Neg logit contributions
iren-0.004
 crash-0.004
storm-0.004
 knock-0.004
 aids-0.004
Token that
Token ID326
Feature activation+6.01e-02

Pos logit contributions
ishes+0.166
 seas+0.155
 favorites+0.154
 minerals+0.150
 shells+0.146
Neg logit contributions
iren-0.167
 crash-0.167
storm-0.156
 knock-0.154
 earthquake-0.151
Token,
Token ID11
Feature activation-4.58e-02

Pos logit contributions
iren+0.048
 crash+0.046
storm+0.044
 knock+0.042
 aids+0.042
Neg logit contributions
ishes-0.043
 favorites-0.040
 seas-0.040
 minerals-0.040
 shells-0.039
Token "
Token ID366
Feature activation+6.21e-02

Pos logit contributions
ishes+0.089
 favorites+0.084
 minerals+0.084
 seas+0.084
 shells+0.082
Neg logit contributions
iren-0.070
 crash-0.065
storm-0.063
 knock-0.059
 aids-0.059
TokenWhat
Token ID2061
Feature activation-9.02e-02

Pos logit contributions
iren+0.093
storm+0.082
 knock+0.082
 crash+0.080
unt+0.079
Neg logit contributions
ishes-0.128
 favorites-0.118
 seas-0.117
 luck-0.116
 dreams-0.115
Token is
Token ID318
Feature activation+9.29e-03

Pos logit contributions
ishes+0.195
 seas+0.173
 favorites+0.170
 minerals+0.168
esty+0.168
Neg logit contributions
ggy-0.113
 crash-0.112
 aids-0.108
 knock-0.106
iren-0.103
Token your
Token ID534
Feature activation-5.66e-02

Pos logit contributions
iren+0.017
 crash+0.016
storm+0.015
 knock+0.015
 aids+0.015
Neg logit contributions
ishes-0.016
 favorites-0.014
 seas-0.014
 minerals-0.014
 shells-0.014
Token favorite
Token ID4004
Feature activation-2.92e-01

Pos logit contributions
ishes+0.082
 seas+0.075
 minerals+0.073
 shells+0.072
 seaw+0.071
Neg logit contributions
iren-0.114
 crash-0.110
storm-0.105
 knock-0.103
 aids-0.103
Token color
Token ID3124
Feature activation-5.43e-02

Pos logit contributions
ishes+0.507
 favorites+0.472
 seas+0.471
 minerals+0.470
 shells+0.462
Neg logit contributions
iren-0.507
 crash-0.479
storm-0.463
 knock-0.440
 aids-0.438
Token?"
Token ID1701
Feature activation+9.01e-03

Pos logit contributions
ishes+0.080
 minerals+0.077
 seas+0.076
 favorites+0.075
 shells+0.074
Neg logit contributions
iren-0.106
 crash-0.101
storm-0.098
 collapse-0.093
 aids-0.093
Token
Token ID198
Feature activation-1.31e-02

Pos logit contributions
iren+0.018
 crash+0.017
storm+0.017
 earthquake+0.016
 knock+0.016
Neg logit contributions
ishes-0.013
 favorites-0.012
 minerals-0.012
 seas-0.012
 shells-0.012
TokenThe
Token ID464
Feature activation+3.10e-02

Pos logit contributions
ishes+0.014
 seas+0.014
 favorites+0.014
 minerals+0.013
 shells+0.013
Neg logit contributions
storm-0.029
 earthquake-0.028
 crash-0.028
iren-0.028
 collapse-0.026
Token child
Token ID1200
Feature activation-7.61e-02

Pos logit contributions
iren+0.057
 crash+0.054
storm+0.052
 knock+0.050
 aids+0.050
Neg logit contributions
ishes-0.051
 favorites-0.047
 seas-0.047
 minerals-0.047
 shells-0.046
Token.
Token ID13
Feature activation+6.89e-03

Pos logit contributions
ishes+0.136
 favorites+0.122
 minerals+0.121
 shells+0.117
 ones+0.115
Neg logit contributions
iren-0.175
 crash-0.166
storm-0.163
 aids-0.155
 earthquake-0.153
Token They
Token ID1119
Feature activation+2.36e-02

Pos logit contributions
iren+0.012
 crash+0.011
storm+0.011
 aids+0.010
 knock+0.010
Neg logit contributions
ishes-0.012
 seas-0.012
 favorites-0.011
 shells-0.011
 minerals-0.011
Token will
Token ID481
Feature activation-2.20e-01

Pos logit contributions
iren+0.050
 crash+0.046
storm+0.046
 aids+0.044
 knock+0.043
Neg logit contributions
ishes-0.033
 favorites-0.030
 minerals-0.030
 seas-0.030
 shells-0.029
Token be
Token ID307
Feature activation+6.00e-02

Pos logit contributions
 shells+0.285
 minerals+0.284
 luck+0.279
 dreams+0.278
 ones+0.276
Neg logit contributions
iren-0.480
storm-0.399
aned-0.398
 aids-0.394
chair-0.387
Token angry
Token ID7954
Feature activation+2.55e-01

Pos logit contributions
iren+0.106
storm+0.104
 crash+0.097
 outage+0.091
 aids+0.090
Neg logit contributions
ishes-0.109
 favorites-0.099
 luck-0.099
 shells-0.099
 prett-0.097
Token if
Token ID611
Feature activation-2.98e-01

Pos logit contributions
iren+0.469
 crash+0.446
storm+0.430
 knock+0.410
 aids+0.406
Neg logit contributions
ishes-0.417
 seas-0.390
 favorites-0.387
 minerals-0.385
 shells-0.379
Token we
Token ID356
Feature activation-9.94e-02

Pos logit contributions
ishes+0.434
 favorites+0.400
 seas+0.399
 minerals+0.398
 shells+0.390
Neg logit contributions
iren-0.600
 crash-0.572
storm-0.556
 knock-0.531
 aids-0.529
Token touch
Token ID3638
Feature activation-1.10e-02

Pos logit contributions
ishes+0.153
 favorites+0.140
 shells+0.138
 minerals+0.136
 seaw+0.133
Neg logit contributions
iren-0.211
storm-0.185
 crash-0.185
 aids-0.181
lf-0.178
Token it
Token ID340
Feature activation+9.13e-03

Pos logit contributions
ishes+0.020
 favorites+0.020
 seas+0.019
 minerals+0.019
sters+0.019
Neg logit contributions
iren-0.016
 crash-0.015
 aids-0.014
storm-0.014
 knock-0.014
Token."
Token ID526
Feature activation-2.68e-03

Pos logit contributions
iren+0.019
 crash+0.018
storm+0.017
 aids+0.017
 knock+0.017
Neg logit contributions
ishes-0.013
 favorites-0.012
 minerals-0.012
 ones-0.011
 seas-0.011
Token But
Token ID887
Feature activation-7.12e-02

Pos logit contributions
ishes+0.005
 seas+0.005
 minerals+0.005
 favorites+0.005
 shells+0.005
Neg logit contributions
iren-0.004
 crash-0.004
storm-0.004
 knock-0.004
 aids-0.004