TOP ACTIVATIONS
MAX = 13.836

B izzy nodded solemn ly . She knew she
smile . Mary anx iously opened up the pass
! â Jim said anx iously . His
to break ." Molly nodded solemn ly , understanding the lesson
's that ?" Jun o replied , " I
are you ?" she shouted anx iously .
the answer . She asked anx iously , " What is
underwater kingdom ?" Gab ri ella was so excited
to stop . Emb arrass ed , Jimmy stopped
â So Beat rice tried ! She started
" Me ow ," m ew ed the cat ,
time , my love ?" Ily a nodded happily . She
bouncing around , an unpleasant od our wa ft ed into
't it ?" Ron ny nodded . Tears filled
M ummy watched him anx iously as Ali waited for
" Oh , look ," B ess ie said . She
ummy snack !" Sh awn said , " We
stitch ." Ron said , " That 's
That bow was pretty ," B izzy said plead ingly .
old , clean , fluffy self . Bob and the cat

MIN ACTIVATIONS
MIN = -17.103

examine it with the magn ifying glass ?" "
When Daisy put the magn ifying glass down , the cater
and handed him the magn ifying glass . He
, handing him the magn ifying glass . She looked around
cried , dropping the magn ifying glass . "
borrowed her mom 's magn ifying glass to take a closer
. Lily had a magn ifying glass that she found in
the necklace and the magn ifying glass and told him that
the watch with the magn ifying glass . He saw the
She takes out a magn ifying glass . She looks at
flashlight , and a magn ifying glass . As
the necklace and the magn ifying glass and started to examine
She took out a magn ifying glass and looked very carefully
. They had a magn ifying glass and a small box
She had a big magn ifying glass that made things look
He took out a magn ifying glass and a notebook and
, next to her magn ifying glass . She looked at
a flashlight and a magn ifying glass to examine their finds
hat and grabbed her magn ifying glass . She was ready
said , holding the magn ifying glass over a black ant

INTERVAL 6.101 - 13.836
CONTAINS 9.450%

Go away ." L ily ran to mom and
in the garden ," Lily said . " We
girl heard their words and believed them . She knew that
<|endoftext|> Once upon a time , there was a polite little
andy opened the cup board and saw a big , fat

INTERVAL -1.634 - 6.101
CONTAINS 52.986%

ran after it . It caught the ball in its mouth
and they did everything together . One day , Lily went
. <|endoftext|> Sam and Mia were playing on the beach .
As Tim walked , he saw a big rock .
to play both games . First , they played hide and

INTERVAL -9.368 - -1.634
CONTAINS 37.230%

many rooms and windows and stairs . A friendly man with
tree , she sees a problem . The arrow is stuck
't belong to her . She said she would not give
vinegar was very sour and made a big mess on the
depend able ! And I can go on adventures whenever I

INTERVAL -17.103 - -9.368
CONTAINS 0.333%

his frown and asked him what was wrong . Tim told
sunshine , excited to see what adventures awaited her . <|endoftext|>
. He wanted to know what was inside it , so
enny asked Jack , " What is that wreck ?".
now . You must do what I say . You are
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
atted+0.071
lee+0.069
 impressed+0.067
omo+0.066
 mad+0.065
Neg logit contributions
Ready-0.044
Left-0.036
sc-0.031
alis-0.031
Three-0.030
Token
Token ID198
Feature activation-2.08e+00

Pos logit contributions
Ready+0.067
Left+0.058
sc+0.050
alis+0.049
Three+0.048
Neg logit contributions
atted-0.096
lee-0.094
 impressed-0.089
 mad-0.086
omo-0.085
TokenB
Token ID33
Feature activation+9.92e+00

Pos logit contributions
Ready+0.077
Left+0.066
sc+0.059
Three+0.057
alis+0.057
Neg logit contributions
atted-0.095
lee-0.093
 impressed-0.086
 mad-0.083
 smiling-0.083
Tokenizzy
Token ID40593
Feature activation+5.75e+00

Pos logit contributions
lee+0.435
atted+0.433
 impressed+0.415
 smiling+0.387
omo+0.387
Neg logit contributions
Ready-0.363
Left-0.315
alis-0.286
sc-0.284
 bust-0.265
Token nodded
Token ID14464
Feature activation+5.74e+00

Pos logit contributions
atted+0.188
 impressed+0.182
lee+0.182
 glad+0.176
omo+0.175
Neg logit contributions
Ready-0.232
Left-0.214
 bust-0.207
alis-0.201
 summit-0.191
Token solemn
Token ID26322
Feature activation+1.38e+01

Pos logit contributions
atted+0.224
omo+0.218
lee+0.205
inches+0.198
 impressed+0.192
Neg logit contributions
Left-0.180
Ready-0.174
 begin-0.166
 form-0.163
 across-0.163
Tokenly
Token ID306
Feature activation+8.13e+00

Pos logit contributions
omo+0.649
 impressed+0.648
atted+0.632
lee+0.612
 glad+0.602
Neg logit contributions
Left-0.328
Ready-0.322
sc-0.290
 bust-0.284
alis-0.264
Token.
Token ID13
Feature activation+3.55e-01

Pos logit contributions
omo+0.341
atted+0.297
lee+0.293
 impressed+0.281
 glad+0.273
Neg logit contributions
Ready-0.256
sc-0.246
Left-0.246
tted-0.225
fire-0.223
Token She
Token ID1375
Feature activation-1.13e+00

Pos logit contributions
atted+0.014
lee+0.014
 impressed+0.014
 mad+0.013
omo+0.013
Neg logit contributions
Ready-0.014
Left-0.012
alis-0.011
sc-0.011
Three-0.010
Token knew
Token ID2993
Feature activation+8.12e+00

Pos logit contributions
Ready+0.045
Left+0.039
sc+0.038
tted+0.037
 bust+0.037
Neg logit contributions
atted-0.042
lee-0.041
 mad-0.037
ummies-0.037
 impressed-0.037
Token she
Token ID673
Feature activation-2.55e+00

Pos logit contributions
atted+0.296
lee+0.292
 impressed+0.272
omo+0.271
 mad+0.256
Neg logit contributions
Ready-0.338
Left-0.298
alis-0.276
 summit-0.267
 south-0.263
Token smile
Token ID8212
Feature activation+4.11e+00

Pos logit contributions
lee+0.072
atted+0.070
 impressed+0.062
omo+0.059
anted+0.055
Neg logit contributions
Ready-0.087
 flap-0.076
Left-0.075
 shortcut-0.074
alis-0.072
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
atted+0.158
lee+0.156
 impressed+0.149
omo+0.144
 glad+0.139
Neg logit contributions
Ready-0.153
Left-0.135
alis-0.132
sc-0.128
tr-0.124
Token
Token ID198
Feature activation-2.90e+00

Pos logit contributions
atted+0.011
lee+0.011
 impressed+0.010
 mad+0.010
ies+0.009
Neg logit contributions
Ready-0.007
Left-0.006
 Ready-0.005
Three-0.004
sc-0.004
Token
Token ID198
Feature activation-2.64e+00

Pos logit contributions
Ready+0.085
Left+0.072
sc+0.056
Three+0.056
 Ready+0.055
Neg logit contributions
atted-0.148
lee-0.144
 impressed-0.137
 mad-0.133
 smiling-0.133
TokenMary
Token ID24119
Feature activation+7.02e+00

Pos logit contributions
Ready+0.116
Left+0.101
Three+0.088
sc+0.087
Skip+0.087
Neg logit contributions
atted-0.109
lee-0.107
 impressed-0.093
 smiling-0.092
 mad-0.089
Token anx
Token ID7296
Feature activation+1.36e+01

Pos logit contributions
lee+0.234
atted+0.231
 impressed+0.227
omo+0.225
 glad+0.224
Neg logit contributions
Ready-0.279
Left-0.257
 bust-0.246
alis-0.241
 summit-0.230
Tokeniously
Token ID6819
Feature activation+8.23e+00

Pos logit contributions
 impressed+0.528
 glad+0.487
 pleased+0.481
omo+0.435
lee+0.432
Neg logit contributions
Ready-0.372
 peak-0.367
alis-0.364
Left-0.358
 base-0.349
Token opened
Token ID4721
Feature activation+2.88e+00

Pos logit contributions
omo+0.258
lee+0.243
atted+0.238
 impressed+0.221
 glad+0.208
Neg logit contributions
Ready-0.347
 bust-0.309
Left-0.306
 belong-0.300
sc-0.296
Token up
Token ID510
Feature activation-1.77e-01

Pos logit contributions
atted+0.116
lee+0.113
omo+0.111
 impressed+0.111
 glad+0.101
Neg logit contributions
Ready-0.109
Left-0.097
 south-0.089
 summit-0.088
alis-0.087
Token the
Token ID262
Feature activation-5.26e+00

Pos logit contributions
Ready+0.007
Left+0.006
sc+0.006
 bust+0.006
alis+0.006
Neg logit contributions
lee-0.007
atted-0.007
omo-0.007
 impressed-0.006
 glad-0.006
Token pass
Token ID1208
Feature activation-3.35e-01

Pos logit contributions
Ready+0.197
Left+0.184
Whe+0.171
Skip+0.163
alis+0.162
Neg logit contributions
atted-0.212
lee-0.204
 smiling-0.203
 mad-0.201
 impressed-0.196
Token!
Token ID0
Feature activation+3.16e-01

Pos logit contributions
Ready+0.265
Left+0.237
alis+0.220
sc+0.215
 bust+0.208
Neg logit contributions
lee-0.209
atted-0.208
 impressed-0.191
omo-0.180
 smiling-0.176
Tokenâ
Token ID22940
Feature activation+8.93e+00

Pos logit contributions
lee+0.014
atted+0.014
 impressed+0.013
omo+0.012
 smiling+0.012
Neg logit contributions
Ready-0.012
Left-0.010
alis-0.009
sc-0.009
 bust-0.009
Token
Token ID26391
Feature activation+3.97e+00

Pos logit contributions
lee+0.455
atted+0.454
 impressed+0.419
omo+0.414
 mad+0.410
Neg logit contributions
Ready-0.253
Left-0.213
alis-0.186
sc-0.182
 summit-0.180
Token Jim
Token ID5395
Feature activation+5.81e+00

Pos logit contributions
atted+0.176
lee+0.175
 impressed+0.164
omo+0.154
 mad+0.153
Neg logit contributions
Ready-0.146
Left-0.127
alis-0.113
sc-0.110
 bust-0.107
Token said
Token ID531
Feature activation+6.08e+00

Pos logit contributions
lee+0.194
atted+0.190
 impressed+0.180
omo+0.164
 glad+0.162
Neg logit contributions
Ready-0.265
Left-0.237
sc-0.221
alis-0.221
 bust-0.216
Token anx
Token ID7296
Feature activation+1.35e+01

Pos logit contributions
lee+0.181
atted+0.179
 impressed+0.162
omo+0.153
 mad+0.143
Neg logit contributions
Ready-0.309
Left-0.281
alis-0.258
sc-0.258
 bust-0.251
Tokeniously
Token ID6819
Feature activation+8.12e+00

Pos logit contributions
 impressed+0.424
 glad+0.387
atted+0.375
lee+0.374
 pleased+0.360
Neg logit contributions
Ready-0.542
Left-0.515
alis-0.499
tr-0.480
 summit-0.468
Token.
Token ID13
Feature activation+7.57e-01

Pos logit contributions
atted+0.245
lee+0.240
 impressed+0.220
omo+0.209
 mad+0.194
Neg logit contributions
Ready-0.392
Left-0.353
sc-0.333
alis-0.322
 summit-0.319
Token
Token ID198
Feature activation-2.03e+00

Pos logit contributions
lee+0.031
atted+0.031
 impressed+0.029
omo+0.027
 smiling+0.027
Neg logit contributions
Ready-0.030
Left-0.027
alis-0.024
sc-0.024
 bust-0.023
Token
Token ID198
Feature activation-1.65e+00

Pos logit contributions
Ready+0.077
Left+0.067
alis+0.061
sc+0.060
 bust+0.057
Neg logit contributions
lee-0.088
atted-0.088
 impressed-0.081
omo-0.078
 smiling-0.077
TokenHis
Token ID6653
Feature activation+7.17e+00

Pos logit contributions
Ready+0.066
Left+0.058
alis+0.051
sc+0.051
Three+0.049
Neg logit contributions
lee-0.069
atted-0.069
 impressed-0.063
omo-0.060
 smiling-0.060
Token to
Token ID284
Feature activation-4.06e+00

Pos logit contributions
Ready+0.162
Left+0.144
alis+0.133
sc+0.131
 bust+0.126
Neg logit contributions
lee-0.141
atted-0.140
 impressed-0.129
omo-0.123
 smiling-0.120
Token break
Token ID2270
Feature activation+1.36e-01

Pos logit contributions
Ready+0.188
Left+0.169
sc+0.156
alis+0.156
 bust+0.149
Neg logit contributions
lee-0.143
atted-0.139
 impressed-0.130
 smiling-0.123
 glad-0.122
Token."
Token ID526
Feature activation+1.55e+00

Pos logit contributions
atted+0.006
lee+0.006
 impressed+0.005
omo+0.005
 glad+0.005
Neg logit contributions
Ready-0.005
Left-0.005
sc-0.004
alis-0.004
 south-0.004
Token Molly
Token ID30236
Feature activation+7.01e+00

Pos logit contributions
atted+0.063
lee+0.061
 impressed+0.060
omo+0.057
 mad+0.056
Neg logit contributions
Ready-0.060
Left-0.053
alis-0.047
sc-0.047
Three-0.045
Token nodded
Token ID14464
Feature activation+5.17e+00

Pos logit contributions
lee+0.224
atted+0.223
 impressed+0.203
omo+0.197
 glad+0.197
Neg logit contributions
Ready-0.297
Left-0.280
 bust-0.264
alis-0.256
 will-0.251
Token solemn
Token ID26322
Feature activation+1.32e+01

Pos logit contributions
omo+0.191
atted+0.191
inches+0.173
lee+0.170
ummies+0.164
Neg logit contributions
Left-0.169
 begin-0.162
 end-0.157
 make-0.157
Ready-0.156
Tokenly
Token ID306
Feature activation+7.43e+00

Pos logit contributions
omo+0.627
 impressed+0.611
atted+0.598
lee+0.583
irling+0.567
Neg logit contributions
Left-0.311
Ready-0.301
 bust-0.279
sc-0.268
 south-0.248
Token,
Token ID11
Feature activation+9.52e+00

Pos logit contributions
omo+0.260
lee+0.218
atted+0.214
 impressed+0.208
irling+0.191
Neg logit contributions
Ready-0.284
sc-0.273
Left-0.270
 bust-0.262
 across-0.257
Token understanding
Token ID4547
Feature activation+5.27e+00

Pos logit contributions
lee+0.293
atted+0.291
omo+0.267
ummies+0.254
ins+0.236
Neg logit contributions
Ready-0.414
Left-0.372
alis-0.370
 distance-0.363
 bust-0.359
Token the
Token ID262
Feature activation-3.43e+00

Pos logit contributions
atted+0.179
lee+0.178
omo+0.165
 impressed+0.162
 mad+0.146
Neg logit contributions
Ready-0.230
Left-0.209
sc-0.189
alis-0.188
 south-0.187
Token lesson
Token ID11483
Feature activation+2.67e+00

Pos logit contributions
Ready+0.178
Left+0.162
alis+0.153
sc+0.151
 bust+0.147
Neg logit contributions
lee-0.098
atted-0.098
 impressed-0.088
omo-0.086
 smiling-0.083
Token's
Token ID338
Feature activation-1.32e+00

Pos logit contributions
Ready+0.284
Left+0.242
alis+0.218
sc+0.211
 bust+0.201
Neg logit contributions
lee-0.414
atted-0.412
 impressed-0.388
omo-0.372
 smiling-0.367
Token that
Token ID326
Feature activation-4.65e+00

Pos logit contributions
Ready+0.063
Left+0.056
sc+0.053
alis+0.052
Three+0.051
Neg logit contributions
atted-0.043
lee-0.043
 impressed-0.041
 mad-0.039
 glad-0.038
Token?"
Token ID1701
Feature activation+1.64e+00

Pos logit contributions
Ready+0.211
Left+0.189
sc+0.177
alis+0.177
Three+0.168
Neg logit contributions
lee-0.155
atted-0.154
 impressed-0.153
 mad-0.146
 smiling-0.146
Token
Token ID198
Feature activation-1.89e+00

Pos logit contributions
atted+0.064
lee+0.064
 impressed+0.059
omo+0.056
 mad+0.055
Neg logit contributions
Ready-0.069
Left-0.061
alis-0.056
sc-0.055
 bust-0.053
Token
Token ID198
Feature activation-1.91e+00

Pos logit contributions
Ready+0.076
Left+0.066
alis+0.062
sc+0.060
 bust+0.058
Neg logit contributions
lee-0.077
atted-0.076
 impressed-0.071
omo-0.068
 smiling-0.066
TokenJun
Token ID22396
Feature activation+1.31e+01

Pos logit contributions
Ready+0.075
Left+0.065
alis+0.060
sc+0.058
 bust+0.056
Neg logit contributions
lee-0.080
atted-0.079
 impressed-0.074
omo-0.071
 smiling-0.069
Tokeno
Token ID78
Feature activation+7.46e+00

Pos logit contributions
 impressed+0.469
atted+0.458
lee+0.448
 glad+0.429
 mad+0.421
Neg logit contributions
Ready-0.566
Left-0.504
alis-0.468
sc-0.461
Skip-0.448
Token replied
Token ID8712
Feature activation+6.27e+00

Pos logit contributions
atted+0.232
 glad+0.218
lee+0.215
 impressed+0.211
omo+0.206
Neg logit contributions
Ready-0.311
Left-0.298
 bust-0.284
alis-0.270
 Museum-0.266
Token,
Token ID11
Feature activation+1.02e+01

Pos logit contributions
lee+0.195
omo+0.191
atted+0.185
 impressed+0.168
 glad+0.152
Neg logit contributions
Ready-0.280
Left-0.276
br-0.244
sc-0.241
fire-0.237
Token "
Token ID366
Feature activation-8.74e-01

Pos logit contributions
atted+0.480
lee+0.470
omo+0.450
 impressed+0.420
 mad+0.417
Neg logit contributions
Ready-0.324
Left-0.297
alis-0.228
 Museum-0.224
Skip-0.223
TokenI
Token ID40
Feature activation-3.06e+00

Pos logit contributions
Ready+0.027
Left+0.023
alis+0.021
sc+0.020
 bust+0.019
Neg logit contributions
lee-0.043
atted-0.042
 impressed-0.041
omo-0.039
 smiling-0.038
Token are
Token ID389
Feature activation-1.46e+00

Pos logit contributions
Ready+0.337
Left+0.294
alis+0.267
sc+0.260
 bust+0.249
Neg logit contributions
lee-0.396
atted-0.395
 impressed-0.368
omo-0.352
 smiling-0.346
Token you
Token ID345
Feature activation-2.47e+00

Pos logit contributions
Ready+0.060
Left+0.053
alis+0.049
sc+0.048
 bust+0.046
Neg logit contributions
lee-0.058
atted-0.058
 impressed-0.054
omo-0.051
 smiling-0.050
Token?"
Token ID1701
Feature activation+9.16e-01

Pos logit contributions
Ready+0.101
Left+0.091
alis+0.088
 hunt+0.086
 belong+0.086
Neg logit contributions
atted-0.092
lee-0.090
omo-0.083
 impressed-0.076
ushed-0.069
Token she
Token ID673
Feature activation+1.90e-01

Pos logit contributions
atted+0.036
lee+0.034
omo+0.034
 impressed+0.032
rou+0.030
Neg logit contributions
Ready-0.037
 bust-0.031
Left-0.031
 gra-0.029
 hunt-0.029
Token shouted
Token ID17293
Feature activation+7.83e+00

Pos logit contributions
atted+0.008
omo+0.007
lee+0.007
 glad+0.006
rou+0.006
Neg logit contributions
Ready-0.007
 bust-0.006
Left-0.006
 flap-0.006
 hunt-0.006
Token anx
Token ID7296
Feature activation+1.31e+01

Pos logit contributions
omo+0.368
atted+0.349
lee+0.333
 impressed+0.297
ins+0.288
Neg logit contributions
Ready-0.235
Left-0.223
 across-0.202
sc-0.201
fire-0.192
Tokeniously
Token ID6819
Feature activation+7.87e+00

Pos logit contributions
 impressed+0.457
 glad+0.438
omo+0.435
 pleased+0.431
atted+0.419
Neg logit contributions
 hunt-0.417
 edge-0.405
alis-0.398
 base-0.396
fire-0.396
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
omo+0.391
atted+0.368
lee+0.357
ushed+0.314
 impressed+0.305
Neg logit contributions
Ready-0.183
 pass-0.168
 rest-0.157
 hunt-0.156
 source-0.155
Token
Token ID220
Feature activation-1.71e+00

Pos logit contributions
Ready+0.000
Left+0.000
alis+0.000
Three+0.000
 bust+0.000
Neg logit contributions
atted-0.000
lee-0.000
 impressed-0.000
omo-0.000
 mad-0.000
Token
Token ID198
Feature activation-3.03e+00

Pos logit contributions
Ready+0.063
Left+0.055
alis+0.049
sc+0.048
ready+0.046
Neg logit contributions
lee-0.075
atted-0.075
 impressed-0.070
omo-0.067
 smiling-0.066
Token
Token ID198
Feature activation-2.79e+00

Pos logit contributions
Ready+0.107
Left+0.093
sc+0.080
alis+0.079
Three+0.077
Neg logit contributions
atted-0.141
lee-0.140
 impressed-0.129
omo-0.126
 mad-0.122
Token the
Token ID262
Feature activation-3.95e+00

Pos logit contributions
lee+0.099
atted+0.099
 impressed+0.091
omo+0.089
 mad+0.081
Neg logit contributions
Ready-0.124
Left-0.111
alis-0.102
sc-0.101
 south-0.099
Token answer
Token ID3280
Feature activation+3.06e+00

Pos logit contributions
Ready+0.150
Left+0.137
alis+0.130
 bust+0.128
sc+0.128
Neg logit contributions
 smiling-0.148
 mad-0.147
atted-0.142
lee-0.141
omo-0.141
Token.
Token ID13
Feature activation-3.69e-01

Pos logit contributions
lee+0.099
atted+0.098
 impressed+0.090
omo+0.085
 glad+0.081
Neg logit contributions
Ready-0.146
Left-0.131
alis-0.122
sc-0.121
 bust-0.117
Token She
Token ID1375
Feature activation-1.22e+00

Pos logit contributions
Ready+0.015
Left+0.013
alis+0.012
sc+0.012
 bust+0.011
Neg logit contributions
atted-0.015
lee-0.015
 impressed-0.014
omo-0.013
 smiling-0.013
Token asked
Token ID1965
Feature activation+3.87e+00

Pos logit contributions
Ready+0.056
Left+0.050
 bust+0.047
alis+0.047
sc+0.045
Neg logit contributions
atted-0.040
lee-0.039
 impressed-0.036
omo-0.035
 glad-0.035
Token anx
Token ID7296
Feature activation+1.29e+01

Pos logit contributions
lee+0.132
atted+0.130
 impressed+0.124
omo+0.120
 mad+0.109
Neg logit contributions
Ready-0.179
Left-0.162
sc-0.145
alis-0.145
 bust-0.141
Tokeniously
Token ID6819
Feature activation+7.87e+00

Pos logit contributions
 impressed+0.431
 glad+0.410
omo+0.406
 pleased+0.391
atted+0.386
Neg logit contributions
Ready-0.436
Left-0.415
alis-0.409
 hunt-0.403
 edge-0.396
Token,
Token ID11
Feature activation+9.37e+00

Pos logit contributions
lee+0.250
atted+0.249
omo+0.244
 impressed+0.215
 mad+0.195
Neg logit contributions
Ready-0.347
Left-0.304
 south-0.296
sc-0.294
 Ready-0.284
Token "
Token ID366
Feature activation-1.47e+00

Pos logit contributions
lee+0.370
atted+0.370
omo+0.338
 impressed+0.327
 mad+0.307
Neg logit contributions
Ready-0.394
Left-0.347
sc-0.309
alis-0.309
 south-0.301
TokenWhat
Token ID2061
Feature activation-8.25e+00

Pos logit contributions
Ready+0.044
Left+0.039
alis+0.038
sc+0.036
 bust+0.034
Neg logit contributions
lee-0.067
atted-0.067
 impressed-0.065
omo-0.063
 understanding-0.063
Token is
Token ID318
Feature activation-2.42e-01

Pos logit contributions
Ready+0.271
Left+0.230
alis+0.209
sc+0.200
 bust+0.190
Neg logit contributions
lee-0.396
atted-0.395
 impressed-0.375
omo-0.358
 smiling-0.354
Token underwater
Token ID21258
Feature activation+1.57e+00

Pos logit contributions
Ready+0.023
Left+0.019
alis+0.018
sc+0.017
Three+0.017
Neg logit contributions
lee-0.028
atted-0.028
 impressed-0.026
omo-0.025
 smiling-0.025
Token kingdom
Token ID13239
Feature activation-4.50e+00

Pos logit contributions
lee+0.072
atted+0.070
 impressed+0.067
omo+0.065
 smiling+0.064
Neg logit contributions
Ready-0.056
Left-0.047
alis-0.042
Whe-0.040
ready-0.040
Token?"
Token ID1701
Feature activation+7.95e-01

Pos logit contributions
Ready+0.222
Left+0.198
alis+0.184
Three+0.177
sc+0.176
Neg logit contributions
lee-0.143
atted-0.140
 impressed-0.135
 smiling-0.124
omo-0.122
Token
Token ID198
Feature activation-2.49e+00

Pos logit contributions
atted+0.033
lee+0.033
 impressed+0.031
omo+0.029
 mad+0.028
Neg logit contributions
Ready-0.032
Left-0.028
alis-0.025
sc-0.025
 bust-0.024
Token
Token ID198
Feature activation-2.46e+00

Pos logit contributions
Ready+0.097
Left+0.085
alis+0.078
sc+0.076
 bust+0.073
Neg logit contributions
lee-0.105
atted-0.104
 impressed-0.097
omo-0.093
 smiling-0.091
TokenGab
Token ID46079
Feature activation+1.28e+01

Pos logit contributions
Ready+0.107
Left+0.095
alis+0.087
sc+0.086
 bust+0.083
Neg logit contributions
atted-0.093
lee-0.093
 impressed-0.084
omo-0.081
 smiling-0.079
Tokenri
Token ID380
Feature activation+6.67e+00

Pos logit contributions
atted+0.474
lee+0.472
 impressed+0.438
omo+0.417
 smiling+0.410
Neg logit contributions
Ready-0.555
Left-0.492
alis-0.455
sc-0.450
 bust-0.435
Tokenella
Token ID12627
Feature activation+5.07e+00

Pos logit contributions
lee+0.289
atted+0.289
 impressed+0.276
omo+0.266
 mad+0.264
Neg logit contributions
Ready-0.232
Left-0.207
sc-0.186
alis-0.184
 bust-0.178
Token was
Token ID373
Feature activation+4.01e+00

Pos logit contributions
atted+0.164
lee+0.163
 impressed+0.155
omo+0.154
 glad+0.148
Neg logit contributions
Ready-0.226
Left-0.207
 bust-0.194
sc-0.189
alis-0.189
Token so
Token ID523
Feature activation+4.01e+00

Pos logit contributions
atted+0.137
lee+0.132
omo+0.120
ies+0.108
ummies+0.104
Neg logit contributions
Ready-0.177
Left-0.166
alis-0.155
 bust-0.150
Skip-0.148
Token excited
Token ID6568
Feature activation+8.36e+00

Pos logit contributions
atted+0.104
lee+0.101
omo+0.088
ries+0.075
ittens+0.072
Neg logit contributions
Ready-0.208
Left-0.193
 bust-0.188
 am-0.181
Skip-0.178
Token to
Token ID284
Feature activation-2.05e+00

Pos logit contributions
atted+0.088
lee+0.088
 impressed+0.082
omo+0.079
 smiling+0.073
Neg logit contributions
Ready-0.112
Left-0.101
alis-0.092
sc-0.091
 bust-0.090
Token stop
Token ID2245
Feature activation+4.32e+00

Pos logit contributions
Ready+0.067
Left+0.057
alis+0.051
sc+0.050
 bust+0.047
Neg logit contributions
lee-0.099
atted-0.098
 impressed-0.092
omo-0.089
 smiling-0.088
Token.
Token ID13
Feature activation+6.35e-02

Pos logit contributions
atted+0.151
omo+0.146
lee+0.146
 impressed+0.138
ushed+0.120
Neg logit contributions
Ready-0.180
Left-0.159
 south-0.151
alis-0.144
sc-0.142
Token
Token ID198
Feature activation-2.78e+00

Pos logit contributions
atted+0.003
lee+0.003
 impressed+0.002
omo+0.002
 mad+0.002
Neg logit contributions
Ready-0.002
Left-0.002
sc-0.002
alis-0.002
Three-0.002
Token
Token ID198
Feature activation-2.45e+00

Pos logit contributions
Ready+0.090
Left+0.078
sc+0.065
Three+0.064
tted+0.061
Neg logit contributions
atted-0.140
lee-0.138
 impressed-0.124
 mad-0.122
 smiling-0.121
TokenEmb
Token ID31567
Feature activation+1.27e+01

Pos logit contributions
Ready+0.112
Left+0.100
sc+0.088
Three+0.088
Skip+0.084
Neg logit contributions
atted-0.094
lee-0.094
 impressed-0.079
 smiling-0.078
omo-0.076
Tokenarrass
Token ID9187
Feature activation+2.66e+00

Pos logit contributions
lee+0.617
atted+0.610
omo+0.599
 impressed+0.591
 smiling+0.586
Neg logit contributions
Ready-0.398
Left-0.315
sc-0.291
alis-0.276
ready-0.273
Tokened
Token ID276
Feature activation+7.50e+00

Pos logit contributions
lee+0.093
atted+0.091
 impressed+0.085
omo+0.081
 smiling+0.078
Neg logit contributions
Ready-0.122
Left-0.109
sc-0.100
alis-0.100
 bust-0.097
Token,
Token ID11
Feature activation+9.27e+00

Pos logit contributions
lee+0.193
atted+0.182
 impressed+0.170
omo+0.167
 glad+0.142
Neg logit contributions
Ready-0.401
Left-0.368
sc-0.350
 bust-0.339
alis-0.337
Token Jimmy
Token ID12963
Feature activation+8.19e+00

Pos logit contributions
atted+0.308
lee+0.305
 impressed+0.261
omo+0.255
 mad+0.236
Neg logit contributions
Ready-0.447
Left-0.401
alis-0.363
 bust-0.363
sc-0.361
Token stopped
Token ID5025
Feature activation+4.88e+00

Pos logit contributions
atted+0.292
lee+0.289
 impressed+0.275
omo+0.273
 glad+0.257
Neg logit contributions
Ready-0.341
Left-0.309
 bust-0.286
alis-0.285
sc-0.284
Tokenâ
Token ID22940
Feature activation+8.71e+00

Pos logit contributions
lee+0.013
atted+0.012
 impressed+0.011
omo+0.011
 glad+0.011
Neg logit contributions
Ready-0.013
Left-0.012
alis-0.011
sc-0.010
 summit-0.010
Token
Token ID26391
Feature activation+4.23e+00

Pos logit contributions
lee+0.409
atted+0.397
 impressed+0.364
 mad+0.356
omo+0.355
Neg logit contributions
Ready-0.255
Left-0.220
 summit-0.215
Find-0.205
 south-0.197
Token
Token ID198
Feature activation-2.90e+00

Pos logit contributions
lee+0.180
atted+0.178
 impressed+0.166
omo+0.159
 smiling+0.156
Neg logit contributions
Ready-0.162
Left-0.142
alis-0.130
sc-0.127
 bust-0.122
Token
Token ID198
Feature activation-2.47e+00

Pos logit contributions
Ready+0.114
Left+0.100
alis+0.093
sc+0.089
 bust+0.087
Neg logit contributions
lee-0.121
atted-0.119
 impressed-0.112
omo-0.107
 smiling-0.104
TokenSo
Token ID2396
Feature activation+4.86e+00

Pos logit contributions
Ready+0.096
Left+0.084
alis+0.079
sc+0.075
 bust+0.074
Neg logit contributions
lee-0.103
atted-0.101
 impressed-0.096
omo-0.092
 smiling-0.089
Token Beat
Token ID12568
Feature activation+1.26e+01

Pos logit contributions
lee+0.138
atted+0.136
 impressed+0.121
omo+0.114
 smiling+0.111
Neg logit contributions
Ready-0.254
Left-0.231
alis-0.219
sc-0.212
Three-0.208
Tokenrice
Token ID20970
Feature activation+5.85e+00

Pos logit contributions
atted+0.486
lee+0.486
 impressed+0.448
omo+0.433
 smiling+0.416
Neg logit contributions
Ready-0.535
Left-0.475
alis-0.433
sc-0.432
 bust-0.412
Token tried
Token ID3088
Feature activation+2.90e+00

Pos logit contributions
lee+0.197
atted+0.197
 impressed+0.184
omo+0.178
 glad+0.172
Neg logit contributions
Ready-0.270
Left-0.233
alis-0.223
sc-0.221
 bust-0.215
Token!
Token ID0
Feature activation+1.27e+00

Pos logit contributions
atted+0.121
lee+0.119
omo+0.112
 impressed+0.106
 glad+0.099
Neg logit contributions
Ready-0.112
Left-0.097
alis-0.088
 summit-0.086
 highest-0.085
Token She
Token ID1375
Feature activation-6.55e-01

Pos logit contributions
lee+0.049
atted+0.048
 impressed+0.043
omo+0.041
 smiling+0.041
Neg logit contributions
Ready-0.054
Left-0.049
alis-0.045
sc-0.044
 bust-0.043
Token started
Token ID2067
Feature activation+1.38e+00

Pos logit contributions
Ready+0.028
Left+0.025
alis+0.023
sc+0.023
 bust+0.022
Neg logit contributions
lee-0.025
atted-0.024
 impressed-0.023
omo-0.022
 glad-0.021
Token
Token ID198
Feature activation-2.76e+00

Pos logit contributions
Ready+0.110
Left+0.094
sc+0.082
Three+0.080
alis+0.078
Neg logit contributions
atted-0.148
lee-0.146
 impressed-0.135
omo-0.131
 mad-0.128
Token"
Token ID1
Feature activation-1.64e+00

Pos logit contributions
Ready+0.138
Left+0.122
Three+0.112
sc+0.111
ready+0.109
Neg logit contributions
atted-0.091
lee-0.087
 impressed-0.076
omo-0.074
 smiling-0.073
TokenMe
Token ID5308
Feature activation+5.50e+00

Pos logit contributions
Ready+0.050
Left+0.044
alis+0.043
sc+0.041
 summit+0.040
Neg logit contributions
lee-0.075
atted-0.074
omo-0.071
 impressed-0.071
 smiling-0.069
Tokenow
Token ID322
Feature activation+4.00e+00

Pos logit contributions
lee+0.206
atted+0.204
 impressed+0.189
omo+0.178
 smiling+0.174
Neg logit contributions
Ready-0.242
Left-0.216
alis-0.200
sc-0.195
 bust-0.189
Token,"
Token ID553
Feature activation+2.75e+00

Pos logit contributions
lee+0.124
atted+0.123
 impressed+0.113
omo+0.105
 smiling+0.102
Neg logit contributions
Ready-0.196
Left-0.178
alis-0.166
sc-0.164
 bust-0.160
Token m
Token ID285
Feature activation+1.24e+01

Pos logit contributions
atted+0.081
lee+0.078
omo+0.070
 impressed+0.068
 glad+0.059
Neg logit contributions
Ready-0.136
Left-0.117
 bust-0.113
ready-0.111
sc-0.109
Tokenew
Token ID413
Feature activation+6.86e+00

Pos logit contributions
lee+0.423
 impressed+0.421
atted+0.389
 knowing+0.379
 glad+0.377
Neg logit contributions
Ready-0.478
Left-0.436
Three-0.430
tr-0.429
 summit-0.422
Tokened
Token ID276
Feature activation+8.62e+00

Pos logit contributions
atted+0.212
 impressed+0.210
lee+0.206
omo+0.204
 glad+0.196
Neg logit contributions
Ready-0.303
Left-0.272
sc-0.257
 bust-0.257
alis-0.254
Token the
Token ID262
Feature activation-1.13e+00

Pos logit contributions
atted+0.265
omo+0.255
lee+0.250
 impressed+0.245
 glad+0.221
Neg logit contributions
Ready-0.390
Left-0.343
 bust-0.332
sc-0.321
ready-0.317
Token cat
Token ID3797
Feature activation+2.66e+00

Pos logit contributions
Ready+0.044
Left+0.039
alis+0.035
sc+0.035
 bust+0.034
Neg logit contributions
lee-0.047
atted-0.046
 impressed-0.043
omo-0.042
 smiling-0.042
Token,
Token ID11
Feature activation+1.01e+01

Pos logit contributions
lee+0.081
atted+0.081
 impressed+0.074
omo+0.072
 glad+0.067
Neg logit contributions
Ready-0.130
Left-0.118
alis-0.112
sc-0.111
 bust-0.107
Token time
Token ID640
Feature activation-2.74e+00

Pos logit contributions
lee+0.085
atted+0.081
 impressed+0.077
omo+0.067
 mad+0.066
Neg logit contributions
Ready-0.074
Left-0.065
alis-0.060
 place-0.059
 am-0.059
Token,
Token ID11
Feature activation+7.44e+00

Pos logit contributions
Ready+0.123
Left+0.111
alis+0.104
sc+0.102
 south+0.099
Neg logit contributions
lee-0.095
atted-0.094
 impressed-0.086
omo-0.082
 mad-0.078
Token my
Token ID616
Feature activation+2.27e+00

Pos logit contributions
atted+0.265
lee+0.254
 impressed+0.223
aged+0.203
 mad+0.200
Neg logit contributions
Ready-0.341
Left-0.305
alis-0.285
 Ready-0.271
 south-0.270
Token love
Token ID1842
Feature activation+3.43e+00

Pos logit contributions
lee+0.074
atted+0.072
 impressed+0.067
omo+0.060
 mad+0.058
Neg logit contributions
Ready-0.103
Left-0.095
alis-0.088
 summit-0.087
sc-0.084
Token?"
Token ID1701
Feature activation+1.63e+00

Pos logit contributions
lee+0.125
atted+0.123
 impressed+0.115
omo+0.105
 mad+0.104
Neg logit contributions
Ready-0.152
Left-0.136
alis-0.126
sc-0.125
ready-0.118
Token Ily
Token ID49804
Feature activation+1.23e+01

Pos logit contributions
atted+0.077
lee+0.075
 impressed+0.073
omo+0.071
 mad+0.071
Neg logit contributions
Ready-0.054
Left-0.045
alis-0.040
sc-0.038
Three-0.037
Tokena
Token ID64
Feature activation+8.20e+00

Pos logit contributions
lee+0.531
atted+0.508
 impressed+0.487
 smiling+0.478
omo+0.467
Neg logit contributions
Ready-0.425
Left-0.383
sc-0.361
 bust-0.345
alis-0.334
Token nodded
Token ID14464
Feature activation+6.03e+00

Pos logit contributions
atted+0.242
lee+0.239
 glad+0.228
omo+0.227
ummies+0.222
Neg logit contributions
Ready-0.316
Left-0.316
 bust-0.297
sc-0.289
Three-0.282
Token happily
Token ID18177
Feature activation+7.96e+00

Pos logit contributions
atted+0.198
omo+0.191
lee+0.181
inches+0.177
ummies+0.165
Neg logit contributions
Left-0.227
Ready-0.216
 grant-0.209
 begin-0.208
 south-0.203
Token.
Token ID13
Feature activation+4.50e-01

Pos logit contributions
omo+0.253
atted+0.253
lee+0.247
 impressed+0.215
ummies+0.207
Neg logit contributions
Ready-0.321
Left-0.308
sc-0.305
fire-0.300
tted-0.297
Token She
Token ID1375
Feature activation-7.99e-01

Pos logit contributions
atted+0.020
lee+0.020
 impressed+0.019
 mad+0.019
omo+0.018
Neg logit contributions
Ready-0.016
Left-0.014
alis-0.012
sc-0.012
 Ready-0.011
Token bouncing
Token ID30713
Feature activation+1.68e+00

Pos logit contributions
lee+0.197
atted+0.191
 impressed+0.170
omo+0.169
 mad+0.147
Neg logit contributions
Ready-0.356
Left-0.324
alis-0.305
sc-0.302
 south-0.291
Token around
Token ID1088
Feature activation-3.53e+00

Pos logit contributions
lee+0.058
atted+0.058
 impressed+0.053
omo+0.049
 smiling+0.049
Neg logit contributions
Ready-0.079
Left-0.070
alis-0.066
sc-0.064
 bust-0.062
Token,
Token ID11
Feature activation+8.95e+00

Pos logit contributions
Ready+0.187
Left+0.170
alis+0.159
sc+0.157
 bust+0.152
Neg logit contributions
lee-0.100
atted-0.100
 impressed-0.089
omo-0.085
 mad-0.079
Token an
Token ID281
Feature activation+1.70e+00

Pos logit contributions
atted+0.321
lee+0.312
 impressed+0.283
omo+0.279
 mad+0.260
Neg logit contributions
Ready-0.414
Left-0.366
alis-0.336
sc-0.327
 bust-0.323
Token unpleasant
Token ID22029
Feature activation+4.81e+00

Pos logit contributions
atted+0.073
omo+0.066
lee+0.063
 impressed+0.063
 smiling+0.063
Neg logit contributions
Ready-0.055
alis-0.051
 bust-0.048
 south-0.048
Left-0.047
Token od
Token ID16298
Feature activation+1.23e+01

Pos logit contributions
lee+0.192
atted+0.188
 impressed+0.174
 mad+0.174
omo+0.172
Neg logit contributions
Ready-0.197
Left-0.174
sc-0.155
ready-0.155
alis-0.154
Tokenour
Token ID454
Feature activation-6.60e-01

Pos logit contributions
atted+0.397
 impressed+0.395
lee+0.389
omo+0.371
 understanding+0.367
Neg logit contributions
Ready-0.539
Left-0.493
alis-0.485
sc-0.451
 bust-0.440
Token wa
Token ID2082
Feature activation+8.39e+00

Pos logit contributions
Ready+0.030
Left+0.027
alis+0.024
sc+0.024
ready+0.023
Neg logit contributions
lee-0.025
atted-0.024
 impressed-0.022
omo-0.021
 smiling-0.020
Tokenft
Token ID701
Feature activation-1.38e+00

Pos logit contributions
atted+0.304
lee+0.304
 impressed+0.279
omo+0.260
 mad+0.258
Neg logit contributions
Ready-0.375
Left-0.333
alis-0.311
sc-0.305
ready-0.292
Tokened
Token ID276
Feature activation+5.51e+00

Pos logit contributions
Ready+0.071
Left+0.064
alis+0.062
 summit+0.058
ready+0.057
Neg logit contributions
atted-0.041
lee-0.041
 impressed-0.035
 mad-0.033
 smiling-0.033
Token into
Token ID656
Feature activation-1.93e+00

Pos logit contributions
lee+0.220
atted+0.218
 impressed+0.204
omo+0.197
 glad+0.187
Neg logit contributions
Ready-0.226
Left-0.200
sc-0.182
alis-0.181
 bust-0.173
Token't
Token ID470
Feature activation-1.26e-01

Pos logit contributions
lee+0.157
atted+0.155
 impressed+0.147
 mad+0.144
 glad+0.142
Neg logit contributions
Ready-0.128
Left-0.109
alis-0.100
sc-0.099
ready-0.093
Token it
Token ID340
Feature activation-6.40e+00

Pos logit contributions
Ready+0.006
Left+0.005
alis+0.005
sc+0.005
 bust+0.005
Neg logit contributions
lee-0.004
atted-0.004
 impressed-0.004
omo-0.004
 smiling-0.004
Token?"
Token ID1701
Feature activation+8.83e-01

Pos logit contributions
Ready+0.291
Left+0.260
alis+0.241
sc+0.237
 bust+0.229
Neg logit contributions
lee-0.228
atted-0.226
 impressed-0.208
omo-0.196
 smiling-0.191
Token
Token ID198
Feature activation-2.85e+00

Pos logit contributions
atted+0.043
lee+0.042
 impressed+0.040
omo+0.039
 mad+0.037
Neg logit contributions
Ready-0.030
Left-0.025
alis-0.021
sc-0.020
Three-0.020
Token
Token ID198
Feature activation-2.82e+00

Pos logit contributions
Ready+0.098
Left+0.085
alis+0.072
Three+0.071
sc+0.071
Neg logit contributions
atted-0.133
lee-0.132
 impressed-0.124
omo-0.118
 mad-0.117
TokenRon
Token ID23672
Feature activation+1.22e+01

Pos logit contributions
Ready+0.107
Left+0.093
Three+0.080
alis+0.079
sc+0.079
Neg logit contributions
atted-0.125
lee-0.125
 impressed-0.115
omo-0.109
 smiling-0.108
Tokenny
Token ID3281
Feature activation+7.29e+00

Pos logit contributions
lee+0.530
atted+0.521
 impressed+0.502
omo+0.464
 glad+0.463
Neg logit contributions
Ready-0.460
Left-0.408
alis-0.362
sc-0.361
 bust-0.347
Token nodded
Token ID14464
Feature activation+5.21e+00

Pos logit contributions
atted+0.251
lee+0.244
 impressed+0.238
 glad+0.236
omo+0.228
Neg logit contributions
Ready-0.289
Left-0.268
 bust-0.248
alis-0.245
Three-0.237
Token.
Token ID13
Feature activation+3.03e-01

Pos logit contributions
atted+0.209
omo+0.204
lee+0.194
inches+0.184
 impressed+0.181
Neg logit contributions
Left-0.161
Ready-0.156
 begin-0.144
 across-0.143
 form-0.142
Token Tears
Token ID40328
Feature activation-4.12e+00

Pos logit contributions
lee+0.011
atted+0.011
 impressed+0.011
omo+0.010
 mad+0.010
Neg logit contributions
Ready-0.013
Left-0.012
alis-0.011
sc-0.010
 bust-0.010
Token filled
Token ID5901
Feature activation-1.73e+00

Pos logit contributions
Ready+0.168
Left+0.149
sc+0.137
alis+0.136
 bust+0.131
Neg logit contributions
lee-0.163
atted-0.161
 impressed-0.150
omo-0.145
 glad-0.140
Token
Token ID198
Feature activation-3.20e+00

Pos logit contributions
Ready+0.146
Left+0.128
alis+0.119
sc+0.115
 bust+0.111
Neg logit contributions
lee-0.151
atted-0.150
 impressed-0.141
omo-0.134
 smiling-0.130
TokenM
Token ID44
Feature activation+5.55e+00

Pos logit contributions
Ready+0.132
Left+0.117
alis+0.112
sc+0.107
 bust+0.104
Neg logit contributions
lee-0.122
atted-0.120
 impressed-0.115
omo-0.109
 understanding-0.105
Tokenummy
Token ID13513
Feature activation+8.05e+00

Pos logit contributions
lee+0.182
atted+0.179
 impressed+0.172
 smiling+0.159
 glad+0.154
Neg logit contributions
Ready-0.261
Left-0.238
alis-0.221
Three-0.214
 summit-0.214
Token watched
Token ID7342
Feature activation+4.10e+00

Pos logit contributions
atted+0.274
lee+0.263
 glad+0.253
 impressed+0.250
omo+0.241
Neg logit contributions
Ready-0.340
Left-0.300
 bust-0.297
alis-0.283
Three-0.280
Token him
Token ID683
Feature activation+2.46e+00

Pos logit contributions
atted+0.146
lee+0.145
omo+0.140
 impressed+0.136
 glad+0.127
Neg logit contributions
Ready-0.173
Left-0.163
sc-0.147
alis-0.143
 south-0.141
Token anx
Token ID7296
Feature activation+1.22e+01

Pos logit contributions
lee+0.092
atted+0.091
 impressed+0.083
omo+0.083
 glad+0.076
Neg logit contributions
Ready-0.105
Left-0.093
alis-0.087
sc-0.086
 summit-0.083
Tokeniously
Token ID6819
Feature activation+6.93e+00

Pos logit contributions
 impressed+0.442
 glad+0.424
 pleased+0.396
lee+0.386
atted+0.385
Neg logit contributions
Ready-0.404
alis-0.390
 peak-0.380
 summit-0.374
Left-0.372
Token as
Token ID355
Feature activation-2.67e+00

Pos logit contributions
atted+0.202
lee+0.201
omo+0.195
 impressed+0.169
 glad+0.154
Neg logit contributions
Ready-0.340
Left-0.305
 bust-0.287
 summit-0.285
alis-0.282
Token Ali
Token ID12104
Feature activation+3.53e+00

Pos logit contributions
Ready+0.124
Left+0.109
 bust+0.099
 summit+0.099
sc+0.099
Neg logit contributions
atted-0.094
lee-0.094
omo-0.082
 impressed-0.082
 mad-0.075
Token waited
Token ID13488
Feature activation+5.17e+00

Pos logit contributions
lee+0.128
atted+0.126
 impressed+0.118
omo+0.113
 glad+0.109
Neg logit contributions
Ready-0.156
Left-0.139
alis-0.129
sc-0.127
 bust-0.123
Token for
Token ID329
Feature activation-2.37e+00

Pos logit contributions
atted+0.186
lee+0.180
omo+0.175
 impressed+0.162
 mad+0.151
Neg logit contributions
Ready-0.218
Left-0.197
sc-0.186
 south-0.185
alis-0.180
Token"
Token ID1
Feature activation-1.79e+00

Pos logit contributions
Ready+0.111
Left+0.098
alis+0.091
sc+0.087
 bust+0.085
Neg logit contributions
lee-0.116
atted-0.114
 impressed-0.108
omo-0.102
 smiling-0.099
TokenOh
Token ID5812
Feature activation+6.60e-01

Pos logit contributions
Ready+0.058
Left+0.051
 hunt+0.051
 shortcut+0.050
sc+0.050
Neg logit contributions
lee-0.074
 impressed-0.073
atted-0.072
omo-0.071
 smiling-0.070
Token,
Token ID11
Feature activation+8.11e+00

Pos logit contributions
lee+0.019
atted+0.019
 impressed+0.017
omo+0.016
 smiling+0.015
Neg logit contributions
Ready-0.034
Left-0.031
alis-0.029
sc-0.028
 bust-0.028
Token look
Token ID804
Feature activation+1.48e+00

Pos logit contributions
lee+0.276
atted+0.269
 impressed+0.248
omo+0.239
 glad+0.236
Neg logit contributions
Ready-0.383
Left-0.347
sc-0.322
alis-0.320
Three-0.307
Token,"
Token ID553
Feature activation+2.86e+00

Pos logit contributions
atted+0.046
lee+0.045
 impressed+0.040
omo+0.040
 smiling+0.036
Neg logit contributions
Ready-0.070
Left-0.065
alis-0.060
sc-0.059
 bust-0.058
Token B
Token ID347
Feature activation+1.21e+01

Pos logit contributions
atted+0.072
lee+0.072
 impressed+0.064
omo+0.060
 smiling+0.056
Neg logit contributions
Ready-0.159
Left-0.144
alis-0.135
sc-0.134
 bust-0.132
Tokeness
Token ID408
Feature activation+9.91e+00

Pos logit contributions
atted+0.535
lee+0.531
 impressed+0.521
omo+0.485
 smiling+0.485
Neg logit contributions
Ready-0.420
Left-0.373
alis-0.345
sc-0.330
 bust-0.309
Tokenie
Token ID494
Feature activation+5.97e+00

Pos logit contributions
 impressed+0.297
atted+0.295
lee+0.291
omo+0.282
 glad+0.270
Neg logit contributions
Ready-0.428
Left-0.394
sc-0.376
alis-0.373
 bust-0.369
Token said
Token ID531
Feature activation+7.29e+00

Pos logit contributions
atted+0.176
lee+0.166
omo+0.159
 glad+0.152
 impressed+0.149
Neg logit contributions
Ready-0.268
Left-0.242
alis-0.237
 bust-0.236
sc-0.231
Token.
Token ID13
Feature activation+6.80e-01

Pos logit contributions
atted+0.259
lee+0.254
omo+0.254
 impressed+0.228
 glad+0.204
Neg logit contributions
Ready-0.299
Left-0.280
sc-0.260
 bust-0.257
fire-0.256
Token She
Token ID1375
Feature activation-9.95e-01

Pos logit contributions
atted+0.026
lee+0.026
 impressed+0.024
omo+0.023
 mad+0.023
Neg logit contributions
Ready-0.029
Left-0.026
alis-0.023
sc-0.023
 bust-0.022
Tokenummy
Token ID13513
Feature activation+5.69e+00

Pos logit contributions
atted+0.069
 impressed+0.069
lee+0.068
 glad+0.058
 smiling+0.053
Neg logit contributions
Ready-0.177
Left-0.167
alis-0.158
 summit-0.158
sc-0.155
Token snack
Token ID26906
Feature activation-5.25e-01

Pos logit contributions
lee+0.254
atted+0.252
 impressed+0.235
omo+0.218
 glad+0.216
Neg logit contributions
Ready-0.211
Left-0.181
alis-0.165
sc-0.162
ready-0.154
Token!"
Token ID2474
Feature activation+2.38e+00

Pos logit contributions
Ready+0.026
Left+0.023
alis+0.022
sc+0.021
 bust+0.021
Neg logit contributions
lee-0.017
atted-0.017
 impressed-0.015
omo-0.014
 smiling-0.014
Token
Token ID198
Feature activation-1.61e+00

Pos logit contributions
lee+0.097
atted+0.097
 impressed+0.090
omo+0.086
 smiling+0.084
Neg logit contributions
Ready-0.096
Left-0.084
alis-0.077
sc-0.075
 bust-0.073
Token
Token ID198
Feature activation-1.66e+00

Pos logit contributions
Ready+0.063
Left+0.055
alis+0.051
sc+0.049
 bust+0.048
Neg logit contributions
lee-0.068
atted-0.067
 impressed-0.063
omo-0.060
 smiling-0.058
TokenSh
Token ID2484
Feature activation+1.21e+01

Pos logit contributions
Ready+0.060
Left+0.053
alis+0.051
sc+0.047
 summit+0.047
Neg logit contributions
lee-0.071
atted-0.070
 impressed-0.068
omo-0.065
 understanding-0.063
Tokenawn
Token ID3832
Feature activation+1.08e+01

Pos logit contributions
atted+0.432
lee+0.420
 glad+0.402
 impressed+0.400
 mad+0.399
Neg logit contributions
Ready-0.463
Left-0.438
tted-0.421
alis-0.421
fire-0.399
Token said
Token ID531
Feature activation+6.90e+00

Pos logit contributions
 glad+0.325
atted+0.303
 impressed+0.299
lee+0.298
omo+0.288
Neg logit contributions
Ready-0.468
Left-0.440
 bust-0.429
sc-0.413
alis-0.399
Token,
Token ID11
Feature activation+9.95e+00

Pos logit contributions
lee+0.188
atted+0.182
omo+0.176
 impressed+0.162
 mad+0.142
Neg logit contributions
Ready-0.355
Left-0.337
sc-0.306
br-0.297
 bust-0.296
Token "
Token ID366
Feature activation-1.40e+00

Pos logit contributions
atted+0.448
lee+0.430
omo+0.410
 impressed+0.383
 mad+0.382
Neg logit contributions
Ready-0.358
Left-0.321
sc-0.269
alis-0.268
 bust-0.263
TokenWe
Token ID1135
Feature activation-4.14e+00

Pos logit contributions
Ready+0.046
Left+0.042
alis+0.041
 bust+0.037
sc+0.037
Neg logit contributions
lee-0.060
atted-0.059
 impressed-0.058
omo-0.056
 smiling-0.055
Token stitch
Token ID24695
Feature activation-2.20e+00

Pos logit contributions
Ready+0.152
Left+0.131
sc+0.113
 bust+0.113
ready+0.112
Neg logit contributions
lee-0.178
atted-0.173
 smiling-0.167
 gigg-0.166
 impressed-0.165
Token."
Token ID526
Feature activation+1.37e+00

Pos logit contributions
Ready+0.105
Left+0.094
alis+0.088
sc+0.085
 bust+0.084
Neg logit contributions
lee-0.073
atted-0.072
 impressed-0.065
omo-0.061
 smiling-0.061
Token
Token ID220
Feature activation-9.99e-01

Pos logit contributions
lee+0.059
atted+0.059
 impressed+0.055
omo+0.052
 smiling+0.052
Neg logit contributions
Ready-0.052
Left-0.045
alis-0.040
sc-0.040
 bust-0.038
Token
Token ID198
Feature activation-2.21e+00

Pos logit contributions
Ready+0.042
Left+0.037
alis+0.036
sc+0.034
 bust+0.033
Neg logit contributions
lee-0.038
atted-0.038
 impressed-0.035
omo-0.034
 glad-0.033
Token
Token ID198
Feature activation-2.07e+00

Pos logit contributions
Ready+0.089
Left+0.078
alis+0.075
sc+0.070
 bust+0.069
Neg logit contributions
lee-0.088
atted-0.088
 impressed-0.082
omo-0.079
 glad-0.076
TokenRon
Token ID23672
Feature activation+1.21e+01

Pos logit contributions
Ready+0.084
Left+0.074
alis+0.068
sc+0.066
 bust+0.064
Neg logit contributions
lee-0.084
atted-0.084
 impressed-0.078
omo-0.075
 smiling-0.072
Token said
Token ID531
Feature activation+6.63e+00

Pos logit contributions
lee+0.368
atted+0.365
 impressed+0.338
omo+0.313
 glad+0.306
Neg logit contributions
Ready-0.595
Left-0.546
alis-0.500
sc-0.495
 bust-0.490
Token,
Token ID11
Feature activation+9.76e+00

Pos logit contributions
lee+0.201
atted+0.188
omo+0.186
 impressed+0.168
 mad+0.146
Neg logit contributions
Ready-0.316
Left-0.302
sc-0.277
br-0.275
fire-0.268
Token "
Token ID366
Feature activation-1.34e+00

Pos logit contributions
atted+0.431
lee+0.422
omo+0.400
 impressed+0.377
 mad+0.374
Neg logit contributions
Ready-0.354
Left-0.317
sc-0.275
alis-0.266
 bust-0.261
TokenThat
Token ID2504
Feature activation-2.91e+00

Pos logit contributions
Ready+0.045
Left+0.040
alis+0.040
 Museum+0.038
 shortcut+0.038
Neg logit contributions
atted-0.055
 impressed-0.054
lee-0.054
 understanding-0.052
omo-0.051
Token's
Token ID338
Feature activation-3.92e-01

Pos logit contributions
Ready+0.113
Left+0.099
alis+0.091
sc+0.089
 bust+0.085
Neg logit contributions
lee-0.123
atted-0.123
 impressed-0.114
omo-0.109
 smiling-0.106
TokenThat
Token ID2504
Feature activation-2.47e+00

Pos logit contributions
Ready+0.043
Left+0.038
alis+0.038
 summit+0.036
 shortcut+0.035
Neg logit contributions
lee-0.065
atted-0.064
 impressed-0.064
omo-0.062
 smiling-0.061
Token bow
Token ID9563
Feature activation+1.26e+00

Pos logit contributions
Ready+0.105
Left+0.094
alis+0.086
sc+0.083
Three+0.082
Neg logit contributions
lee-0.094
atted-0.093
 impressed-0.086
 smiling-0.084
omo-0.083
Token was
Token ID373
Feature activation+1.83e+00

Pos logit contributions
atted+0.044
lee+0.044
 impressed+0.040
 smiling+0.038
omo+0.037
Neg logit contributions
Ready-0.058
Left-0.052
alis-0.048
sc-0.046
ready-0.046
Token pretty
Token ID2495
Feature activation+1.23e+00

Pos logit contributions
atted+0.065
lee+0.065
 impressed+0.058
omo+0.056
 smiling+0.053
Neg logit contributions
Ready-0.082
Left-0.074
alis-0.069
sc-0.068
ready-0.064
Token,"
Token ID553
Feature activation+2.82e+00

Pos logit contributions
atted+0.049
lee+0.049
 impressed+0.044
omo+0.042
 glad+0.042
Neg logit contributions
Ready-0.048
Left-0.043
sc-0.043
alis-0.040
 highest-0.039
Token B
Token ID347
Feature activation+1.19e+01

Pos logit contributions
atted+0.090
lee+0.087
 impressed+0.081
omo+0.077
 glad+0.071
Neg logit contributions
Ready-0.136
Left-0.119
sc-0.111
 bust-0.110
alis-0.110
Tokenizzy
Token ID40593
Feature activation+6.73e+00

Pos logit contributions
atted+0.502
lee+0.499
 impressed+0.482
 smiling+0.448
omo+0.445
Neg logit contributions
Ready-0.452
Left-0.394
alis-0.365
sc-0.357
 bust-0.336
Token said
Token ID531
Feature activation+7.80e+00

Pos logit contributions
atted+0.208
omo+0.202
 glad+0.194
lee+0.192
 impressed+0.189
Neg logit contributions
Ready-0.274
 bust-0.256
Left-0.250
alis-0.243
sc-0.242
Token plead
Token ID30701
Feature activation+8.29e+00

Pos logit contributions
omo+0.328
atted+0.317
lee+0.305
 impressed+0.284
irling+0.260
Neg logit contributions
Ready-0.253
Left-0.239
sc-0.221
fire-0.219
 bust-0.217
Tokeningly
Token ID4420
Feature activation+8.14e+00

Pos logit contributions
omo+0.331
atted+0.318
lee+0.310
 impressed+0.304
aj+0.270
Neg logit contributions
 across-0.249
tted-0.241
 edge-0.240
fire-0.240
Ready-0.238
Token.
Token ID13
Feature activation+5.93e-01

Pos logit contributions
atted+0.369
lee+0.358
omo+0.349
 impressed+0.334
 glad+0.304
Neg logit contributions
Ready-0.255
Left-0.228
sc-0.213
 south-0.205
fire-0.201
Token old
Token ID1468
Feature activation+3.19e+00

Pos logit contributions
Ready+0.029
Left+0.025
alis+0.023
sc+0.022
 summit+0.022
Neg logit contributions
atted-0.031
lee-0.031
 impressed-0.028
omo-0.027
 glad-0.026
Token,
Token ID11
Feature activation+8.20e+00

Pos logit contributions
atted+0.120
lee+0.119
 impressed+0.109
omo+0.099
 glad+0.098
Neg logit contributions
Ready-0.137
Left-0.118
alis-0.113
sc-0.108
 hunt-0.108
Token clean
Token ID3424
Feature activation+4.37e+00

Pos logit contributions
atted+0.299
lee+0.292
omo+0.256
 impressed+0.254
 mad+0.232
Neg logit contributions
Ready-0.362
Left-0.309
alis-0.301
sc-0.297
 south-0.290
Token,
Token ID11
Feature activation+8.36e+00

Pos logit contributions
atted+0.182
lee+0.179
 impressed+0.172
 glad+0.160
omo+0.160
Neg logit contributions
Ready-0.167
Left-0.143
alis-0.137
sc-0.132
 bust-0.126
Token fluffy
Token ID39145
Feature activation+5.21e+00

Pos logit contributions
atted+0.241
lee+0.238
omo+0.203
 impressed+0.195
 mad+0.180
Neg logit contributions
Ready-0.427
Left-0.372
alis-0.365
sc-0.361
 south-0.355
Token self
Token ID2116
Feature activation+1.19e+01

Pos logit contributions
atted+0.202
lee+0.201
 impressed+0.196
omo+0.179
 glad+0.177
Neg logit contributions
Ready-0.211
Left-0.188
alis-0.175
sc-0.171
 bust-0.164
Token.
Token ID13
Feature activation+2.06e-01

Pos logit contributions
lee+0.378
atted+0.375
 impressed+0.340
omo+0.323
 mad+0.308
Neg logit contributions
Ready-0.588
Left-0.530
alis-0.494
sc-0.488
 bust-0.472
Token Bob
Token ID5811
Feature activation+6.28e+00

Pos logit contributions
lee+0.008
atted+0.008
 impressed+0.007
omo+0.007
 smiling+0.007
Neg logit contributions
Ready-0.009
Left-0.008
alis-0.007
sc-0.007
 bust-0.007
Token and
Token ID290
Feature activation+8.50e+00

Pos logit contributions
lee+0.237
atted+0.232
 impressed+0.223
 mad+0.219
omo+0.218
Neg logit contributions
Ready-0.228
Left-0.207
 bust-0.194
sc-0.188
 will-0.187
Token the
Token ID262
Feature activation-2.11e+00

Pos logit contributions
lee+0.292
atted+0.289
 impressed+0.265
omo+0.249
 smiling+0.245
Neg logit contributions
Ready-0.402
Left-0.361
alis-0.336
sc-0.331
 bust-0.317
Token cat
Token ID3797
Feature activation+1.23e+00

Pos logit contributions
Ready+0.087
Left+0.078
alis+0.071
sc+0.071
 summit+0.067
Neg logit contributions
lee-0.083
atted-0.083
 impressed-0.079
 smiling-0.075
 mad-0.075
Token examine
Token ID10716
Feature activation-7.99e-01

Pos logit contributions
Ready+0.283
Left+0.249
sc+0.223
alis+0.221
ready+0.214
Neg logit contributions
lee-0.325
atted-0.312
 impressed-0.296
 smiling-0.294
 understanding-0.290
Token it
Token ID340
Feature activation-8.43e+00

Pos logit contributions
Ready+0.038
Left+0.035
alis+0.032
sc+0.032
 bust+0.031
Neg logit contributions
lee-0.026
atted-0.026
 impressed-0.024
omo-0.023
 smiling-0.022
Token with
Token ID351
Feature activation-3.31e+00

Pos logit contributions
Ready+0.455
Left+0.407
alis+0.379
 bust+0.369
sc+0.368
Neg logit contributions
lee-0.217
 impressed-0.215
atted-0.214
 smiling-0.196
 mad-0.188
Token the
Token ID262
Feature activation-7.59e+00

Pos logit contributions
Ready+0.141
Left+0.125
alis+0.114
sc+0.112
 bust+0.108
Neg logit contributions
atted-0.127
lee-0.127
 impressed-0.117
omo-0.113
 smiling-0.107
Token magn
Token ID7842
Feature activation-3.37e+00

Pos logit contributions
Ready+0.291
Left+0.275
 bust+0.252
sc+0.247
alis+0.246
Neg logit contributions
 smiling-0.288
lee-0.283
atted-0.277
 glad-0.265
 impressed-0.265
Tokenifying
Token ID4035
Feature activation-1.68e+01

Pos logit contributions
Ready+0.096
Left+0.071
Whe+0.062
ready+0.059
Three+0.056
Neg logit contributions
lee-0.188
atted-0.183
 smiling-0.164
 impressed-0.161
omo-0.160
Token glass
Token ID5405
Feature activation-4.53e+00

Pos logit contributions
Ready+0.799
Left+0.723
Skip+0.669
alis+0.658
ready+0.655
Neg logit contributions
atted-0.500
lee-0.491
omo-0.486
 smiling-0.485
 mad-0.480
Token?"
Token ID1701
Feature activation-6.08e-01

Pos logit contributions
Ready+0.229
Left+0.206
alis+0.189
Three+0.182
 bust+0.182
Neg logit contributions
atted-0.140
lee-0.140
 impressed-0.125
omo-0.122
 smiling-0.117
Token
Token ID198
Feature activation-4.11e+00

Pos logit contributions
Ready+0.024
Left+0.021
alis+0.019
sc+0.019
ready+0.018
Neg logit contributions
lee-0.025
atted-0.025
 impressed-0.023
omo-0.022
 smiling-0.022
Token
Token ID198
Feature activation-4.08e+00

Pos logit contributions
Ready+0.156
Left+0.137
alis+0.123
sc+0.121
 bust+0.116
Neg logit contributions
lee-0.177
atted-0.176
 impressed-0.164
omo-0.156
 smiling-0.154
Token"
Token ID1
Feature activation-3.39e+00

Pos logit contributions
Ready+0.182
Left+0.162
sc+0.147
alis+0.146
Three+0.141
Neg logit contributions
lee-0.153
atted-0.151
 impressed-0.139
 smiling-0.130
omo-0.129
Token When
Token ID1649
Feature activation-4.98e+00

Pos logit contributions
Ready+0.116
Left+0.098
sc+0.088
alis+0.088
ready+0.084
Neg logit contributions
atted-0.135
lee-0.134
 impressed-0.126
omo-0.119
 mad-0.118
Token Daisy
Token ID40355
Feature activation+1.62e+00

Pos logit contributions
Ready+0.249
Left+0.225
alis+0.210
sc+0.206
 bust+0.201
Neg logit contributions
lee-0.154
atted-0.153
 impressed-0.138
omo-0.129
 smiling-0.125
Token put
Token ID1234
Feature activation-7.22e-01

Pos logit contributions
lee+0.064
atted+0.064
 impressed+0.060
omo+0.057
 glad+0.055
Neg logit contributions
Ready-0.067
Left-0.058
alis-0.053
sc-0.053
 bust-0.051
Token the
Token ID262
Feature activation-6.19e+00

Pos logit contributions
Ready+0.034
Left+0.030
alis+0.028
sc+0.028
 bust+0.027
Neg logit contributions
lee-0.025
atted-0.025
 impressed-0.022
 smiling-0.021
omo-0.021
Token magn
Token ID7842
Feature activation-3.06e+00

Pos logit contributions
Ready+0.256
Left+0.234
alis+0.213
sc+0.203
 bust+0.201
Neg logit contributions
atted-0.235
lee-0.233
 impressed-0.217
 smiling-0.213
 mad-0.210
Tokenifying
Token ID4035
Feature activation-1.61e+01

Pos logit contributions
Ready+0.070
Left+0.053
alis+0.042
Whe+0.038
ready+0.038
Neg logit contributions
atted-0.181
lee-0.180
 impressed-0.165
 smiling-0.163
omo-0.158
Token glass
Token ID5405
Feature activation-2.79e+00

Pos logit contributions
Ready+0.709
Left+0.631
alis+0.559
sc+0.551
ready+0.548
Neg logit contributions
atted-0.582
lee-0.582
omo-0.555
 impressed-0.525
 smiling-0.525
Token down
Token ID866
Feature activation-5.72e+00

Pos logit contributions
Ready+0.154
Left+0.141
alis+0.133
sc+0.132
 bust+0.128
Neg logit contributions
lee-0.070
atted-0.070
 impressed-0.062
omo-0.057
 smiling-0.054
Token,
Token ID11
Feature activation+6.65e+00

Pos logit contributions
Ready+0.316
Left+0.288
sc+0.271
alis+0.270
 bust+0.261
Neg logit contributions
lee-0.145
atted-0.143
 impressed-0.128
omo-0.119
 mad-0.109
Token the
Token ID262
Feature activation-4.58e+00

Pos logit contributions
lee+0.163
atted+0.157
 impressed+0.143
 smiling+0.129
 glad+0.126
Neg logit contributions
Ready-0.373
Left-0.345
alis-0.325
sc-0.319
Three-0.311
Token cater
Token ID20825
Feature activation+4.05e+00

Pos logit contributions
Ready+0.177
Left+0.158
alis+0.143
sc+0.140
 bust+0.135
Neg logit contributions
lee-0.190
atted-0.188
 impressed-0.175
omo-0.169
 smiling-0.168
Token and
Token ID290
Feature activation+5.92e+00

Pos logit contributions
atted+0.170
lee+0.166
 impressed+0.146
omo+0.140
 glad+0.128
Neg logit contributions
Ready-0.301
Left-0.279
sc-0.262
 hunt-0.260
alis-0.256
Token handed
Token ID10158
Feature activation+1.33e+00

Pos logit contributions
lee+0.200
atted+0.196
omo+0.182
 impressed+0.172
 mad+0.164
Neg logit contributions
Ready-0.275
Left-0.238
sc-0.229
alis-0.220
 bust-0.219
Token him
Token ID683
Feature activation-1.50e-01

Pos logit contributions
lee+0.044
atted+0.044
 impressed+0.040
omo+0.038
 smiling+0.037
Neg logit contributions
Ready-0.064
Left-0.057
alis-0.053
sc-0.052
ready-0.050
Token the
Token ID262
Feature activation-6.78e+00

Pos logit contributions
Ready+0.007
Left+0.006
alis+0.006
sc+0.006
 bust+0.005
Neg logit contributions
lee-0.005
atted-0.005
 impressed-0.005
 smiling-0.005
 mad-0.004
Token magn
Token ID7842
Feature activation-2.30e+00

Pos logit contributions
Ready+0.311
Left+0.289
Three+0.264
 bust+0.264
Ro+0.264
Neg logit contributions
lee-0.215
atted-0.206
 smiling-0.205
 impressed-0.200
 mad-0.191
Tokenifying
Token ID4035
Feature activation-1.57e+01

Pos logit contributions
Ready+0.060
Left+0.047
Whe+0.038
alis+0.035
ready+0.035
Neg logit contributions
lee-0.133
atted-0.131
 impressed-0.119
 smiling-0.117
omo-0.113
Token glass
Token ID5405
Feature activation-3.36e+00

Pos logit contributions
Ready+0.721
Left+0.652
alis+0.584
Skip+0.584
sc+0.581
Neg logit contributions
lee-0.532
atted-0.520
omo-0.488
 smiling-0.487
 mad-0.475
Token.
Token ID13
Feature activation-9.56e-01

Pos logit contributions
Ready+0.161
Left+0.145
sc+0.137
alis+0.135
 bust+0.129
Neg logit contributions
lee-0.108
atted-0.107
 impressed-0.099
omo-0.093
 glad-0.090
Token
Token ID198
Feature activation-4.60e+00

Pos logit contributions
Ready+0.041
Left+0.037
alis+0.033
sc+0.033
 bust+0.031
Neg logit contributions
atted-0.037
lee-0.037
 impressed-0.034
omo-0.032
 smiling-0.031
Token
Token ID198
Feature activation-4.19e+00

Pos logit contributions
Ready+0.161
Left+0.139
sc+0.121
alis+0.118
Three+0.115
Neg logit contributions
atted-0.215
lee-0.212
 impressed-0.197
omo-0.191
 smiling-0.187
TokenHe
Token ID1544
Feature activation-1.53e+00

Pos logit contributions
Ready+0.148
Left+0.124
sc+0.110
Three+0.105
alis+0.102
Neg logit contributions
atted-0.205
lee-0.203
 impressed-0.182
omo-0.178
 smiling-0.176
Token,
Token ID11
Feature activation+8.85e+00

Pos logit contributions
lee+0.207
omo+0.202
atted+0.191
 impressed+0.181
 mad+0.164
Neg logit contributions
Ready-0.212
Left-0.210
sc-0.187
 will-0.182
 rest-0.181
Token handing
Token ID22786
Feature activation+4.18e+00

Pos logit contributions
lee+0.396
atted+0.395
omo+0.365
 impressed+0.330
 mad+0.323
Neg logit contributions
Ready-0.321
Left-0.285
alis-0.245
sc-0.236
Skip-0.231
Token him
Token ID683
Feature activation+1.39e+00

Pos logit contributions
lee+0.119
atted+0.118
 impressed+0.104
omo+0.098
 smiling+0.096
Neg logit contributions
Ready-0.219
Left-0.199
alis-0.188
sc-0.184
 bust-0.180
Token the
Token ID262
Feature activation-5.52e+00

Pos logit contributions
lee+0.051
atted+0.051
 impressed+0.046
omo+0.044
 smiling+0.043
Neg logit contributions
Ready-0.062
Left-0.055
alis-0.051
sc-0.050
 bust-0.048
Token magn
Token ID7842
Feature activation-1.65e+00

Pos logit contributions
Ready+0.216
Left+0.198
alis+0.181
sc+0.178
 bust+0.175
Neg logit contributions
atted-0.213
lee-0.209
 smiling-0.202
 impressed-0.202
 mad-0.198
Tokenifying
Token ID4035
Feature activation-1.55e+01

Pos logit contributions
Ready+0.038
Left+0.028
alis+0.022
ready+0.020
Whe+0.020
Neg logit contributions
atted-0.099
lee-0.099
 impressed-0.090
 smiling-0.089
omo-0.088
Token glass
Token ID5405
Feature activation-2.30e+00

Pos logit contributions
Ready+0.691
Left+0.615
alis+0.556
sc+0.544
ready+0.541
Neg logit contributions
atted-0.549
lee-0.541
omo-0.526
 smiling-0.504
 mad-0.501
Token.
Token ID13
Feature activation-6.10e-01

Pos logit contributions
Ready+0.107
Left+0.096
sc+0.090
alis+0.089
 bust+0.085
Neg logit contributions
lee-0.078
atted-0.076
 impressed-0.071
omo-0.066
 glad-0.065
Token She
Token ID1375
Feature activation-2.06e+00

Pos logit contributions
Ready+0.022
Left+0.019
alis+0.016
sc+0.016
 Ready+0.016
Neg logit contributions
atted-0.028
lee-0.028
 impressed-0.026
 mad-0.025
omo-0.025
Token looked
Token ID3114
Feature activation+3.03e+00

Pos logit contributions
Ready+0.080
Left+0.071
sc+0.068
 will+0.065
Skip+0.065
Neg logit contributions
lee-0.078
atted-0.076
 glad-0.070
ummies-0.068
 impressed-0.067
Token around
Token ID1088
Feature activation-3.26e+00

Pos logit contributions
omo+0.114
lee+0.112
atted+0.104
ummies+0.093
ittens+0.091
Neg logit contributions
Ready-0.119
Left-0.112
sc-0.106
 south-0.105
 will-0.098
Token cried
Token ID16896
Feature activation+7.22e+00

Pos logit contributions
atted+0.239
 glad+0.211
omo+0.205
lee+0.201
 pleased+0.199
Neg logit contributions
Ready-0.181
Left-0.166
 hunt-0.166
 bust-0.160
alis-0.159
Token,
Token ID11
Feature activation+9.02e+00

Pos logit contributions
atted+0.287
lee+0.283
 impressed+0.280
omo+0.262
 pleased+0.248
Neg logit contributions
Ready-0.286
Left-0.268
sc-0.230
alis-0.227
 south-0.224
Token dropping
Token ID12047
Feature activation+2.36e+00

Pos logit contributions
lee+0.324
atted+0.319
omo+0.315
ummy+0.267
ummies+0.264
Neg logit contributions
Ready-0.350
Left-0.331
 flap-0.325
 south-0.322
 source-0.316
Token the
Token ID262
Feature activation-5.51e+00

Pos logit contributions
lee+0.079
atted+0.078
 impressed+0.072
omo+0.068
 smiling+0.065
Neg logit contributions
Ready-0.113
Left-0.102
alis-0.094
sc-0.093
 bust-0.090
Token magn
Token ID7842
Feature activation-1.68e+00

Pos logit contributions
Ready+0.225
Left+0.203
alis+0.183
sc+0.180
 bust+0.177
Neg logit contributions
lee-0.219
atted-0.218
 impressed-0.203
 smiling-0.197
 mad-0.196
Tokenifying
Token ID4035
Feature activation-1.53e+01

Pos logit contributions
Ready+0.041
Left+0.030
ready+0.023
Whe+0.023
alis+0.023
Neg logit contributions
lee-0.099
atted-0.098
 smiling-0.088
 impressed-0.088
omo-0.088
Token glass
Token ID5405
Feature activation-2.76e+00

Pos logit contributions
Ready+0.683
Left+0.613
alis+0.552
ready+0.544
sc+0.542
Neg logit contributions
lee-0.531
atted-0.524
omo-0.500
 smiling-0.489
 mad-0.486
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
Ready+0.129
Left+0.116
alis+0.108
sc+0.107
 bust+0.103
Neg logit contributions
lee-0.093
atted-0.093
 impressed-0.085
omo-0.080
 smiling-0.078
Token
Token ID198
Feature activation-4.47e+00

Pos logit contributions
Ready+0.043
Left+0.038
alis+0.034
sc+0.033
Three+0.032
Neg logit contributions
atted-0.044
lee-0.044
 impressed-0.040
omo-0.039
 mad-0.037
Token
Token ID198
Feature activation-4.27e+00

Pos logit contributions
Ready+0.135
Left+0.117
Three+0.094
 Ready+0.089
sc+0.089
Neg logit contributions
atted-0.231
lee-0.228
 impressed-0.214
 smiling-0.205
omo-0.204
Token"
Token ID1
Feature activation-3.56e+00

Pos logit contributions
Ready+0.180
Left+0.155
Three+0.136
tted+0.132
Skip+0.131
Neg logit contributions
atted-0.183
lee-0.182
 impressed-0.162
 smiling-0.156
omo-0.150
Token borrowed
Token ID22546
Feature activation+1.61e+00

Pos logit contributions
Ready+0.086
Left+0.080
Skip+0.071
 bust+0.069
Ro+0.069
Neg logit contributions
atted-0.110
lee-0.103
ummies-0.100
omo-0.098
 glad-0.098
Token her
Token ID607
Feature activation-1.52e+00

Pos logit contributions
atted+0.064
lee+0.064
 impressed+0.059
omo+0.059
 glad+0.054
Neg logit contributions
Ready-0.066
Left-0.058
alis-0.053
sc-0.052
ready-0.050
Token mom
Token ID1995
Feature activation+2.77e+00

Pos logit contributions
Ready+0.060
Left+0.053
alis+0.049
sc+0.048
 summit+0.046
Neg logit contributions
atted-0.062
lee-0.062
 impressed-0.058
omo-0.056
 mad-0.053
Token's
Token ID338
Feature activation-2.66e+00

Pos logit contributions
lee+0.091
atted+0.091
 impressed+0.086
omo+0.081
 glad+0.076
Neg logit contributions
Ready-0.124
Left-0.111
sc-0.109
alis-0.108
 hunt-0.102
Token magn
Token ID7842
Feature activation-1.82e+00

Pos logit contributions
Ready+0.105
Left+0.092
alis+0.085
sc+0.084
 summit+0.079
Neg logit contributions
lee-0.109
atted-0.109
 impressed-0.101
omo-0.098
 mad-0.093
Tokenifying
Token ID4035
Feature activation-1.52e+01

Pos logit contributions
Ready+0.026
Left+0.019
alis+0.015
sc+0.014
 summit+0.010
Neg logit contributions
lee-0.118
atted-0.118
 impressed-0.115
omo-0.112
 mad-0.110
Token glass
Token ID5405
Feature activation-3.10e+00

Pos logit contributions
Ready+0.656
Left+0.580
sc+0.518
ready+0.513
alis+0.512
Neg logit contributions
lee-0.585
atted-0.578
omo-0.532
 smiling-0.525
 impressed-0.520
Token to
Token ID284
Feature activation-5.46e+00

Pos logit contributions
Ready+0.149
Left+0.135
sc+0.132
alis+0.130
 summit+0.122
Neg logit contributions
lee-0.093
atted-0.093
 impressed-0.089
omo-0.081
 glad-0.081
Token take
Token ID1011
Feature activation-3.51e+00

Pos logit contributions
Ready+0.222
Left+0.201
sc+0.177
alis+0.173
 bust+0.170
Neg logit contributions
lee-0.225
atted-0.212
 impressed-0.206
 understanding-0.202
 smiling-0.201
Token a
Token ID257
Feature activation-4.54e+00

Pos logit contributions
Ready+0.172
Left+0.155
alis+0.144
sc+0.142
 bust+0.138
Neg logit contributions
lee-0.113
atted-0.112
 impressed-0.101
omo-0.095
 smiling-0.093
Token closer
Token ID5699
Feature activation-2.44e+00

Pos logit contributions
Ready+0.167
Left+0.148
alis+0.134
Whe+0.129
 bust+0.128
Neg logit contributions
lee-0.190
atted-0.187
 impressed-0.184
 smiling-0.178
 mad-0.177
Token.
Token ID13
Feature activation-1.30e+00

Pos logit contributions
Ready+0.239
Left+0.219
sc+0.211
alis+0.207
 south+0.200
Neg logit contributions
atted-0.136
lee-0.133
 impressed-0.118
omo-0.115
 mad-0.108
Token Lily
Token ID20037
Feature activation+3.40e+00

Pos logit contributions
Ready+0.060
Left+0.054
alis+0.053
 bust+0.051
works+0.050
Neg logit contributions
lee-0.045
atted-0.042
omo-0.040
 impressed-0.039
 glad-0.036
Token had
Token ID550
Feature activation-4.88e+00

Pos logit contributions
atted+0.150
lee+0.147
 mad+0.135
 glad+0.132
 impressed+0.132
Neg logit contributions
Ready-0.123
Left-0.103
sc-0.100
 hunt-0.096
 bust-0.095
Token a
Token ID257
Feature activation-2.99e+00

Pos logit contributions
Ready+0.212
Left+0.189
alis+0.175
sc+0.173
 summit+0.165
Neg logit contributions
lee-0.186
atted-0.180
 impressed-0.170
 smiling-0.160
 glad-0.157
Token magn
Token ID7842
Feature activation-1.38e+00

Pos logit contributions
Ready+0.111
Left+0.098
alis+0.088
sc+0.086
 bust+0.083
Neg logit contributions
lee-0.130
atted-0.128
 impressed-0.121
omo-0.116
 smiling-0.114
Tokenifying
Token ID4035
Feature activation-1.51e+01

Pos logit contributions
Ready+0.032
Left+0.023
alis+0.018
ready+0.017
Whe+0.017
Neg logit contributions
lee-0.083
atted-0.083
 impressed-0.076
 smiling-0.074
omo-0.074
Token glass
Token ID5405
Feature activation-2.80e+00

Pos logit contributions
Ready+0.710
Left+0.628
ready+0.588
sc+0.567
Skip+0.560
Neg logit contributions
omo-0.490
lee-0.473
atted-0.463
 smiling-0.459
 mad-0.447
Token that
Token ID326
Feature activation-6.19e+00

Pos logit contributions
Ready+0.149
Left+0.136
alis+0.127
sc+0.124
 bust+0.122
Neg logit contributions
lee-0.078
atted-0.078
 impressed-0.069
omo-0.065
 smiling-0.063
Token she
Token ID673
Feature activation-5.24e+00

Pos logit contributions
Ready+0.311
Left+0.281
alis+0.263
sc+0.259
 bust+0.251
Neg logit contributions
lee-0.189
atted-0.189
 impressed-0.170
omo-0.160
 smiling-0.154
Token found
Token ID1043
Feature activation-2.65e+00

Pos logit contributions
Ready+0.226
Left+0.199
alis+0.184
sc+0.183
 bust+0.176
Neg logit contributions
atted-0.198
lee-0.198
 impressed-0.181
omo-0.174
 smiling-0.169
Token in
Token ID287
Feature activation-7.14e+00

Pos logit contributions
Ready+0.124
Left+0.111
alis+0.103
sc+0.101
 bust+0.099
Neg logit contributions
lee-0.091
atted-0.090
 impressed-0.082
omo-0.076
 smiling-0.076
Token the
Token ID262
Feature activation-5.29e+00

Pos logit contributions
lee+0.051
atted+0.050
 impressed+0.048
omo+0.046
 glad+0.043
Neg logit contributions
Ready-0.065
Left-0.058
alis-0.053
sc-0.052
 bust-0.052
Token necklace
Token ID38987
Feature activation-3.63e+00

Pos logit contributions
Ready+0.245
Left+0.228
sc+0.202
Whe+0.202
alis+0.202
Neg logit contributions
lee-0.177
 impressed-0.168
atted-0.166
 smiling-0.165
 mad-0.158
Token and
Token ID290
Feature activation+6.47e+00

Pos logit contributions
Ready+0.190
Left+0.173
sc+0.170
alis+0.166
tr+0.164
Neg logit contributions
lee-0.095
atted-0.094
 impressed-0.084
omo-0.081
 glad-0.074
Token the
Token ID262
Feature activation-4.55e+00

Pos logit contributions
lee+0.208
atted+0.208
omo+0.191
 impressed+0.181
 glad+0.177
Neg logit contributions
Ready-0.297
Left-0.255
 bust-0.247
sc-0.245
 hunt-0.237
Token magn
Token ID7842
Feature activation-1.33e+00

Pos logit contributions
Ready+0.191
Left+0.178
alis+0.161
sc+0.158
Three+0.154
Neg logit contributions
lee-0.170
atted-0.164
 impressed-0.159
 smiling-0.157
 mad-0.151
Tokenifying
Token ID4035
Feature activation-1.48e+01

Pos logit contributions
Ready+0.037
Left+0.029
Whe+0.023
alis+0.023
ready+0.022
Neg logit contributions
lee-0.076
atted-0.075
 impressed-0.067
 smiling-0.066
omo-0.064
Token glass
Token ID5405
Feature activation-2.18e+00

Pos logit contributions
Ready+0.689
Left+0.623
sc+0.565
Skip+0.561
ready+0.554
Neg logit contributions
lee-0.490
atted-0.479
omo-0.459
 smiling-0.455
 mad-0.445
Token and
Token ID290
Feature activation+5.59e+00

Pos logit contributions
Ready+0.101
Left+0.091
alis+0.084
sc+0.084
 bust+0.080
Neg logit contributions
lee-0.074
atted-0.073
 impressed-0.068
omo-0.064
 glad-0.062
Token told
Token ID1297
Feature activation+4.18e+00

Pos logit contributions
atted+0.196
lee+0.196
omo+0.180
 impressed+0.175
 glad+0.168
Neg logit contributions
Ready-0.249
Left-0.212
sc-0.201
 bust-0.199
alis-0.199
Token him
Token ID683
Feature activation+8.63e-01

Pos logit contributions
atted+0.159
lee+0.154
 impressed+0.147
omo+0.144
 glad+0.134
Neg logit contributions
Ready-0.178
Left-0.160
sc-0.142
alis-0.141
 summit-0.137
Token that
Token ID326
Feature activation-5.23e+00

Pos logit contributions
atted+0.029
lee+0.029
 impressed+0.027
omo+0.026
 smiling+0.024
Neg logit contributions
Ready-0.040
Left-0.036
alis-0.033
sc-0.032
 bust-0.032
Token the
Token ID262
Feature activation-4.28e+00

Pos logit contributions
Ready+0.025
Left+0.023
alis+0.021
sc+0.021
 bust+0.020
Neg logit contributions
lee-0.017
atted-0.017
 impressed-0.015
omo-0.014
 smiling-0.014
Token watch
Token ID2342
Feature activation-9.20e-01

Pos logit contributions
Ready+0.153
Left+0.146
sc+0.134
 bust+0.131
alis+0.129
Neg logit contributions
 smiling-0.170
lee-0.166
 impressed-0.163
atted-0.162
 mad-0.158
Token with
Token ID351
Feature activation-6.39e-01

Pos logit contributions
Ready+0.048
Left+0.043
alis+0.040
sc+0.039
 bust+0.039
Neg logit contributions
lee-0.027
atted-0.027
 impressed-0.024
 smiling-0.023
omo-0.022
Token the
Token ID262
Feature activation-4.99e+00

Pos logit contributions
Ready+0.029
Left+0.026
alis+0.024
sc+0.023
 bust+0.023
Neg logit contributions
lee-0.023
atted-0.023
 impressed-0.021
omo-0.020
 smiling-0.020
Token magn
Token ID7842
Feature activation-1.21e+00

Pos logit contributions
Ready+0.178
Left+0.165
sc+0.151
alis+0.148
 bust+0.146
Neg logit contributions
lee-0.204
atted-0.203
 smiling-0.202
 impressed-0.197
 mad-0.191
Tokenifying
Token ID4035
Feature activation-1.48e+01

Pos logit contributions
Ready+0.031
Left+0.023
Whe+0.019
ready+0.018
 bust+0.017
Neg logit contributions
lee-0.069
atted-0.069
 smiling-0.062
 impressed-0.061
omo-0.060
Token glass
Token ID5405
Feature activation-2.00e+00

Pos logit contributions
Ready+0.663
Left+0.591
alis+0.533
sc+0.528
ready+0.526
Neg logit contributions
atted-0.509
lee-0.508
omo-0.487
 smiling-0.478
 mad-0.474
Token.
Token ID13
Feature activation-1.55e-02

Pos logit contributions
Ready+0.093
Left+0.083
alis+0.078
sc+0.077
 bust+0.074
Neg logit contributions
lee-0.068
atted-0.068
 impressed-0.062
omo-0.059
 glad-0.057
Token He
Token ID679
Feature activation-1.21e+00

Pos logit contributions
Ready+0.001
Left+0.001
alis+0.001
sc+0.001
 bust+0.001
Neg logit contributions
lee-0.001
atted-0.001
 impressed-0.001
omo-0.001
 smiling-0.001
Token saw
Token ID2497
Feature activation+1.74e+00

Pos logit contributions
Ready+0.042
Left+0.037
 bust+0.032
alis+0.031
Three+0.031
Neg logit contributions
atted-0.054
lee-0.053
omo-0.049
 impressed-0.047
 glad-0.047
Token the
Token ID262
Feature activation-4.36e+00

Pos logit contributions
lee+0.075
atted+0.074
 impressed+0.068
omo+0.067
 smiling+0.063
Neg logit contributions
Ready-0.066
Left-0.057
alis-0.051
sc-0.049
 bust-0.049
Token She
Token ID1375
Feature activation-1.96e+00

Pos logit contributions
atted+0.004
lee+0.004
 impressed+0.004
omo+0.004
 mad+0.004
Neg logit contributions
Ready-0.004
Left-0.003
sc-0.003
alis-0.003
Three-0.003
Token takes
Token ID2753
Feature activation+3.65e-01

Pos logit contributions
Ready+0.076
Left+0.067
alis+0.061
sc+0.059
 bust+0.057
Neg logit contributions
lee-0.083
atted-0.082
 impressed-0.077
omo-0.073
 smiling-0.072
Token out
Token ID503
Feature activation-2.07e+00

Pos logit contributions
lee+0.015
atted+0.014
 impressed+0.013
 mad+0.013
 smiling+0.012
Neg logit contributions
Ready-0.015
Left-0.013
alis-0.012
sc-0.012
 summit-0.011
Token a
Token ID257
Feature activation-2.58e+00

Pos logit contributions
Ready+0.079
Left+0.070
alis+0.063
sc+0.063
 bust+0.062
Neg logit contributions
atted-0.085
lee-0.085
 impressed-0.080
omo-0.077
 glad-0.074
Token magn
Token ID7842
Feature activation-9.45e-01

Pos logit contributions
Ready+0.102
Left+0.095
alis+0.086
Whe+0.081
sc+0.080
Neg logit contributions
lee-0.100
atted-0.099
 impressed-0.099
 smiling-0.094
 mad-0.094
Tokenifying
Token ID4035
Feature activation-1.48e+01

Pos logit contributions
Ready+0.022
Left+0.017
alis+0.013
ready+0.012
sc+0.012
Neg logit contributions
lee-0.056
atted-0.056
 impressed-0.051
 smiling-0.050
omo-0.049
Token glass
Token ID5405
Feature activation-2.06e+00

Pos logit contributions
Ready+0.643
Left+0.575
sc+0.516
alis+0.509
ready+0.501
Neg logit contributions
lee-0.540
atted-0.534
omo-0.510
 impressed-0.499
 mad-0.491
Token.
Token ID13
Feature activation-5.30e-01

Pos logit contributions
Ready+0.100
Left+0.090
sc+0.084
alis+0.084
 bust+0.080
Neg logit contributions
lee-0.067
atted-0.066
 impressed-0.061
omo-0.057
 glad-0.055
Token She
Token ID1375
Feature activation-2.43e+00

Pos logit contributions
Ready+0.021
Left+0.019
alis+0.017
sc+0.017
 bust+0.017
Neg logit contributions
lee-0.021
atted-0.021
 impressed-0.020
omo-0.019
 smiling-0.018
Token looks
Token ID3073
Feature activation+2.15e+00

Pos logit contributions
Ready+0.093
Left+0.080
alis+0.073
sc+0.072
 bust+0.069
Neg logit contributions
lee-0.104
atted-0.103
 impressed-0.097
omo-0.093
 smiling-0.090
Token at
Token ID379
Feature activation-1.58e+00

Pos logit contributions
atted+0.074
lee+0.074
omo+0.071
 impressed+0.063
 smiling+0.060
Neg logit contributions
Ready-0.098
Left-0.087
sc-0.083
alis-0.080
 bust-0.079
Token flashlight
Token ID38371
Feature activation-5.25e-01

Pos logit contributions
Ready+0.056
Left+0.049
alis+0.044
sc+0.043
 bust+0.042
Neg logit contributions
lee-0.063
atted-0.063
 impressed-0.058
omo-0.055
 smiling-0.054
Token,
Token ID11
Feature activation+7.12e+00

Pos logit contributions
Ready+0.028
Left+0.025
alis+0.024
sc+0.023
ready+0.023
Neg logit contributions
lee-0.015
atted-0.015
 impressed-0.013
 smiling-0.012
omo-0.012
Token and
Token ID290
Feature activation+6.19e+00

Pos logit contributions
lee+0.204
atted+0.202
 impressed+0.179
omo+0.170
 mad+0.159
Neg logit contributions
Ready-0.374
Left-0.337
alis-0.318
sc-0.318
 bust-0.306
Token a
Token ID257
Feature activation-1.27e+00

Pos logit contributions
lee+0.225
atted+0.223
 impressed+0.207
omo+0.193
 smiling+0.192
Neg logit contributions
Ready-0.274
Left-0.247
alis-0.227
sc-0.222
 bust-0.214
Token magn
Token ID7842
Feature activation-1.45e+00

Pos logit contributions
Ready+0.048
Left+0.042
alis+0.038
sc+0.037
 bust+0.036
Neg logit contributions
lee-0.055
atted-0.054
 impressed-0.051
omo-0.048
 smiling-0.047
Tokenifying
Token ID4035
Feature activation-1.47e+01

Pos logit contributions
Ready+0.038
Left+0.030
alis+0.025
Whe+0.023
ready+0.023
Neg logit contributions
lee-0.082
atted-0.081
 impressed-0.074
 smiling-0.073
omo-0.070
Token glass
Token ID5405
Feature activation-1.55e+00

Pos logit contributions
Ready+0.631
Left+0.565
sc+0.501
alis+0.495
ready+0.494
Neg logit contributions
lee-0.544
atted-0.537
omo-0.526
 smiling-0.500
 mad-0.491
Token.
Token ID13
Feature activation-1.42e+00

Pos logit contributions
Ready+0.072
Left+0.065
alis+0.060
sc+0.059
 bust+0.057
Neg logit contributions
lee-0.053
atted-0.053
 impressed-0.048
omo-0.045
 smiling-0.044
Token
Token ID198
Feature activation-3.95e+00

Pos logit contributions
Ready+0.062
Left+0.056
alis+0.052
sc+0.051
 bust+0.049
Neg logit contributions
lee-0.052
atted-0.052
 impressed-0.047
omo-0.045
 smiling-0.044
Token
Token ID198
Feature activation-3.46e+00

Pos logit contributions
Ready+0.149
Left+0.130
alis+0.118
sc+0.115
 bust+0.110
Neg logit contributions
lee-0.171
atted-0.171
 impressed-0.158
omo-0.151
 smiling-0.149
TokenAs
Token ID1722
Feature activation+9.33e-01

Pos logit contributions
Ready+0.151
Left+0.134
alis+0.124
sc+0.122
 bust+0.117
Neg logit contributions
lee-0.130
atted-0.129
 impressed-0.119
omo-0.112
 smiling-0.110
Token the
Token ID262
Feature activation-4.92e+00

Pos logit contributions
Ready+0.075
Left+0.069
 south+0.062
alis+0.062
sc+0.062
Neg logit contributions
lee-0.062
atted-0.062
 impressed-0.061
omo-0.058
 pleased-0.053
Token necklace
Token ID38987
Feature activation-3.52e+00

Pos logit contributions
Ready+0.198
Left+0.180
alis+0.162
 bust+0.157
sc+0.156
Neg logit contributions
atted-0.195
lee-0.195
 impressed-0.178
 smiling-0.177
omo-0.174
Token and
Token ID290
Feature activation+6.49e+00

Pos logit contributions
Ready+0.192
sc+0.177
Left+0.177
alis+0.173
tr+0.170
Neg logit contributions
lee-0.086
atted-0.084
 impressed-0.076
omo-0.070
 mad-0.065
Token the
Token ID262
Feature activation-4.24e+00

Pos logit contributions
lee+0.249
atted+0.248
 impressed+0.234
omo+0.227
 glad+0.218
Neg logit contributions
Ready-0.274
Left-0.233
sc-0.219
alis-0.216
 bust-0.215
Token magn
Token ID7842
Feature activation-1.03e+00

Pos logit contributions
Ready+0.169
Left+0.154
alis+0.140
sc+0.137
Three+0.132
Neg logit contributions
lee-0.169
atted-0.166
 impressed-0.156
 smiling-0.154
omo-0.149
Tokenifying
Token ID4035
Feature activation-1.46e+01

Pos logit contributions
Ready+0.028
Left+0.022
alis+0.018
ready+0.018
Whe+0.018
Neg logit contributions
atted-0.057
lee-0.057
 impressed-0.051
 smiling-0.051
omo-0.049
Token glass
Token ID5405
Feature activation-1.50e+00

Pos logit contributions
Ready+0.638
Left+0.569
sc+0.518
alis+0.512
ready+0.505
Neg logit contributions
lee-0.531
atted-0.524
omo-0.500
 smiling-0.485
 mad-0.477
Token and
Token ID290
Feature activation+5.92e+00

Pos logit contributions
Ready+0.069
Left+0.062
alis+0.058
sc+0.058
 bust+0.055
Neg logit contributions
lee-0.051
atted-0.051
 impressed-0.047
omo-0.044
 glad-0.043
Token started
Token ID2067
Feature activation-1.55e-01

Pos logit contributions
atted+0.226
lee+0.226
 impressed+0.209
omo+0.203
 glad+0.193
Neg logit contributions
Ready-0.253
Left-0.219
alis-0.204
sc-0.202
 bust-0.197
Token to
Token ID284
Feature activation-2.79e+00

Pos logit contributions
Ready+0.006
Left+0.005
alis+0.005
 gra+0.005
sc+0.005
Neg logit contributions
lee-0.006
atted-0.006
omo-0.006
 impressed-0.006
 mad-0.005
Token examine
Token ID10716
Feature activation+1.74e+00

Pos logit contributions
Ready+0.096
Left+0.086
sc+0.075
alis+0.072
ready+0.070
Neg logit contributions
lee-0.129
atted-0.125
 smiling-0.120
 impressed-0.120
 gigg-0.118
Token She
Token ID1375
Feature activation-1.99e+00

Pos logit contributions
Ready+0.040
Left+0.036
alis+0.033
sc+0.032
 summit+0.032
Neg logit contributions
lee-0.031
atted-0.030
 impressed-0.027
 glad-0.025
 smiling-0.025
Token took
Token ID1718
Feature activation+1.27e+00

Pos logit contributions
Ready+0.078
Left+0.066
sc+0.063
alis+0.063
 bust+0.062
Neg logit contributions
atted-0.079
lee-0.079
 impressed-0.073
omo-0.073
 mad-0.072
Token out
Token ID503
Feature activation-2.23e+00

Pos logit contributions
lee+0.048
atted+0.047
 impressed+0.042
 smiling+0.041
 mad+0.040
Neg logit contributions
Ready-0.055
Left-0.048
alis-0.046
sc-0.044
Three-0.043
Token a
Token ID257
Feature activation-2.59e+00

Pos logit contributions
Ready+0.088
Left+0.079
alis+0.072
sc+0.071
 bust+0.070
Neg logit contributions
lee-0.087
atted-0.087
 impressed-0.082
omo-0.081
 glad-0.075
Token magn
Token ID7842
Feature activation-1.02e+00

Pos logit contributions
Ready+0.102
Left+0.094
alis+0.086
Whe+0.083
 bust+0.079
Neg logit contributions
 impressed-0.099
lee-0.098
atted-0.097
 smiling-0.094
 mad-0.092
Tokenifying
Token ID4035
Feature activation-1.45e+01

Pos logit contributions
Ready+0.021
Left+0.015
alis+0.012
sc+0.010
ready+0.010
Neg logit contributions
lee-0.063
atted-0.063
 impressed-0.059
 smiling-0.057
omo-0.057
Token glass
Token ID5405
Feature activation-2.17e+00

Pos logit contributions
Ready+0.645
Left+0.579
ready+0.520
sc+0.516
Whe+0.508
Neg logit contributions
lee-0.500
atted-0.487
omo-0.466
 smiling-0.465
 impressed-0.459
Token and
Token ID290
Feature activation+5.78e+00

Pos logit contributions
Ready+0.116
Left+0.106
alis+0.100
sc+0.099
 bust+0.095
Neg logit contributions
lee-0.059
atted-0.058
 impressed-0.052
omo-0.048
 smiling-0.046
Token looked
Token ID3114
Feature activation+1.74e+00

Pos logit contributions
atted+0.220
lee+0.219
 impressed+0.202
omo+0.198
 mad+0.188
Neg logit contributions
Ready-0.249
Left-0.216
alis-0.202
sc-0.199
 bust-0.193
Token very
Token ID845
Feature activation+3.77e+00

Pos logit contributions
atted+0.074
lee+0.074
omo+0.071
 impressed+0.067
 smiling+0.064
Neg logit contributions
Ready-0.065
Left-0.057
sc-0.052
alis-0.051
 bust-0.050
Token carefully
Token ID7773
Feature activation+3.23e+00

Pos logit contributions
atted+0.129
omo+0.127
lee+0.123
 smiling+0.100
 impressed+0.100
Neg logit contributions
Ready-0.166
Left-0.151
 bust-0.139
 summit-0.138
 highest-0.138
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
Ready+0.169
Left+0.153
alis+0.142
 bust+0.139
Three+0.137
Neg logit contributions
lee-0.090
atted-0.088
 impressed-0.079
 smiling-0.075
omo-0.070
Token They
Token ID1119
Feature activation-3.42e+00

Pos logit contributions
Ready+0.046
Left+0.040
alis+0.038
sc+0.036
 bust+0.036
Neg logit contributions
lee-0.047
atted-0.046
 impressed-0.043
omo-0.041
 smiling-0.040
Token had
Token ID550
Feature activation-4.40e+00

Pos logit contributions
Ready+0.129
Left+0.109
 bust+0.101
alis+0.099
sc+0.098
Neg logit contributions
atted-0.147
lee-0.143
 impressed-0.133
omo-0.131
 glad-0.125
Token a
Token ID257
Feature activation-2.49e+00

Pos logit contributions
Ready+0.186
Left+0.164
alis+0.152
sc+0.149
 bust+0.143
Neg logit contributions
lee-0.172
atted-0.170
 impressed-0.159
omo-0.149
 smiling-0.149
Token magn
Token ID7842
Feature activation-8.02e-01

Pos logit contributions
Ready+0.084
Left+0.072
alis+0.064
sc+0.062
 bust+0.059
Neg logit contributions
lee-0.119
atted-0.119
 impressed-0.110
omo-0.105
 smiling-0.103
Tokenifying
Token ID4035
Feature activation-1.45e+01

Pos logit contributions
Ready+0.019
Left+0.014
ready+0.011
alis+0.011
Whe+0.010
Neg logit contributions
atted-0.048
lee-0.048
 impressed-0.043
 smiling-0.042
omo-0.042
Token glass
Token ID5405
Feature activation-2.05e+00

Pos logit contributions
Ready+0.656
Left+0.572
ready+0.538
sc+0.519
works+0.514
Neg logit contributions
omo-0.496
lee-0.479
atted-0.475
 smiling-0.462
 mad-0.462
Token and
Token ID290
Feature activation+5.57e+00

Pos logit contributions
Ready+0.097
Left+0.087
alis+0.081
sc+0.079
 bust+0.077
Neg logit contributions
lee-0.068
atted-0.068
 impressed-0.062
omo-0.059
 smiling-0.057
Token a
Token ID257
Feature activation-2.51e+00

Pos logit contributions
atted+0.234
lee+0.233
 impressed+0.217
omo+0.208
 smiling+0.202
Neg logit contributions
Ready-0.217
Left-0.188
alis-0.172
sc-0.170
 bust-0.162
Token small
Token ID1402
Feature activation+9.71e-01

Pos logit contributions
Ready+0.094
Left+0.082
alis+0.074
sc+0.073
 bust+0.070
Neg logit contributions
lee-0.109
atted-0.108
 impressed-0.101
omo-0.096
 smiling-0.094
Token box
Token ID3091
Feature activation-4.17e+00

Pos logit contributions
lee+0.043
atted+0.043
 impressed+0.040
omo+0.038
 smiling+0.038
Neg logit contributions
Ready-0.036
Left-0.031
alis-0.028
sc-0.027
 bust-0.026
Token She
Token ID1375
Feature activation-1.78e+00

Pos logit contributions
Ready+0.017
Left+0.015
alis+0.014
sc+0.014
 bust+0.013
Neg logit contributions
lee-0.018
atted-0.018
 impressed-0.016
omo-0.016
 glad-0.016
Token had
Token ID550
Feature activation-3.40e+00

Pos logit contributions
Ready+0.066
Left+0.058
 bust+0.053
alis+0.052
Three+0.052
Neg logit contributions
atted-0.074
lee-0.073
 impressed-0.067
 glad-0.065
omo-0.065
Token a
Token ID257
Feature activation-1.59e+00

Pos logit contributions
Ready+0.142
Left+0.125
alis+0.115
sc+0.113
 bust+0.109
Neg logit contributions
lee-0.135
atted-0.134
 impressed-0.124
omo-0.118
 smiling-0.116
Token big
Token ID1263
Feature activation+4.99e-01

Pos logit contributions
Ready+0.061
Left+0.053
alis+0.048
sc+0.047
 bust+0.045
Neg logit contributions
lee-0.069
atted-0.068
 impressed-0.063
omo-0.061
 smiling-0.059
Token magn
Token ID7842
Feature activation-3.52e-01

Pos logit contributions
lee+0.021
atted+0.021
 impressed+0.020
omo+0.018
 glad+0.018
Neg logit contributions
Ready-0.019
Left-0.016
alis-0.015
sc-0.014
 shortcut-0.014
Tokenifying
Token ID4035
Feature activation-1.41e+01

Pos logit contributions
Ready+0.008
Left+0.006
alis+0.005
ready+0.004
sc+0.004
Neg logit contributions
lee-0.021
atted-0.021
 impressed-0.020
 smiling-0.019
omo-0.019
Token glass
Token ID5405
Feature activation-1.47e+00

Pos logit contributions
Ready+0.646
Left+0.565
ready+0.525
sc+0.517
Skip+0.499
Neg logit contributions
lee-0.470
omo-0.469
atted-0.456
 smiling-0.449
 mad-0.448
Token that
Token ID326
Feature activation-5.10e+00

Pos logit contributions
Ready+0.075
Left+0.068
alis+0.064
sc+0.062
 bust+0.061
Neg logit contributions
lee-0.044
atted-0.043
 impressed-0.039
omo-0.036
 smiling-0.035
Token made
Token ID925
Feature activation-2.96e+00

Pos logit contributions
Ready+0.235
Left+0.211
alis+0.196
sc+0.192
 bust+0.185
Neg logit contributions
lee-0.178
atted-0.177
 impressed-0.162
omo-0.152
 smiling-0.150
Token things
Token ID1243
Feature activation-5.15e+00

Pos logit contributions
Ready+0.152
Left+0.138
alis+0.129
sc+0.127
 bust+0.123
Neg logit contributions
lee-0.088
atted-0.087
 impressed-0.078
omo-0.073
 smiling-0.071
Token look
Token ID804
Feature activation-1.17e+00

Pos logit contributions
Ready+0.188
Left+0.163
alis+0.148
sc+0.144
 bust+0.138
Neg logit contributions
lee-0.229
atted-0.227
 impressed-0.213
omo-0.203
 smiling-0.201
Token He
Token ID679
Feature activation+3.71e-01

Pos logit contributions
lee+0.065
atted+0.064
 impressed+0.059
 smiling+0.056
omo+0.055
Neg logit contributions
Ready-0.077
Left-0.069
alis-0.066
sc-0.065
 bust-0.061
Token took
Token ID1718
Feature activation+2.64e+00

Pos logit contributions
atted+0.014
lee+0.014
 glad+0.013
 impressed+0.013
omo+0.013
Neg logit contributions
Ready-0.015
Left-0.013
sc-0.012
 bust-0.012
alis-0.012
Token out
Token ID503
Feature activation-1.40e+00

Pos logit contributions
atted+0.088
lee+0.087
 impressed+0.079
 mad+0.076
 smiling+0.075
Neg logit contributions
Ready-0.125
Left-0.110
alis-0.107
sc-0.102
Three-0.098
Token a
Token ID257
Feature activation-1.57e+00

Pos logit contributions
Ready+0.057
Left+0.052
 bust+0.047
alis+0.047
sc+0.046
Neg logit contributions
lee-0.053
atted-0.052
 impressed-0.049
omo-0.048
 glad-0.045
Token magn
Token ID7842
Feature activation-2.12e-01

Pos logit contributions
Ready+0.059
Left+0.055
alis+0.049
sc+0.046
Whe+0.045
Neg logit contributions
lee-0.065
atted-0.063
 impressed-0.063
 smiling-0.060
 mad-0.059
Tokenifying
Token ID4035
Feature activation-1.40e+01

Pos logit contributions
Ready+0.005
Left+0.004
alis+0.003
ready+0.003
sc+0.002
Neg logit contributions
atted-0.013
lee-0.013
 impressed-0.012
 smiling-0.011
omo-0.011
Token glass
Token ID5405
Feature activation-1.28e+00

Pos logit contributions
Ready+0.612
Left+0.555
sc+0.501
ready+0.493
alis+0.490
Neg logit contributions
lee-0.487
atted-0.477
omo-0.472
 smiling-0.455
 mad-0.453
Token and
Token ID290
Feature activation+6.62e+00

Pos logit contributions
Ready+0.069
Left+0.062
alis+0.059
sc+0.059
 bust+0.056
Neg logit contributions
lee-0.035
atted-0.034
 impressed-0.031
omo-0.029
 glad-0.027
Token a
Token ID257
Feature activation-1.38e+00

Pos logit contributions
lee+0.243
atted+0.243
 impressed+0.221
omo+0.215
 glad+0.205
Neg logit contributions
Ready-0.295
Left-0.257
alis-0.240
sc-0.237
 bust-0.231
Token notebook
Token ID20922
Feature activation-2.17e+00

Pos logit contributions
Ready+0.054
Left+0.049
alis+0.044
sc+0.043
 bust+0.041
Neg logit contributions
lee-0.056
atted-0.055
 impressed-0.053
 smiling-0.051
omo-0.050
Token and
Token ID290
Feature activation+7.14e+00

Pos logit contributions
Ready+0.110
Left+0.100
alis+0.092
sc+0.090
 bust+0.089
Neg logit contributions
lee-0.066
atted-0.065
 impressed-0.060
 smiling-0.056
omo-0.055
Token,
Token ID11
Feature activation+8.01e+00

Pos logit contributions
Ready+0.164
Left+0.148
sc+0.147
alis+0.145
tr+0.139
Neg logit contributions
lee-0.072
atted-0.071
 impressed-0.062
omo-0.060
 mad-0.055
Token next
Token ID1306
Feature activation+1.70e-01

Pos logit contributions
lee+0.274
atted+0.262
omo+0.250
 impressed+0.226
 mad+0.206
Neg logit contributions
Ready-0.371
Left-0.327
alis-0.316
 south-0.316
 bust-0.301
Token to
Token ID284
Feature activation-2.98e+00

Pos logit contributions
lee+0.006
atted+0.006
 impressed+0.005
omo+0.005
 smiling+0.005
Neg logit contributions
Ready-0.008
Left-0.007
alis-0.007
sc-0.007
 bust-0.006
Token her
Token ID607
Feature activation+6.32e-01

Pos logit contributions
Ready+0.168
Left+0.154
alis+0.145
sc+0.144
 bust+0.138
Neg logit contributions
lee-0.076
atted-0.073
 impressed-0.066
 smiling-0.060
 glad-0.059
Token magn
Token ID7842
Feature activation-4.64e-01

Pos logit contributions
atted+0.018
lee+0.018
 impressed+0.016
omo+0.015
 mad+0.014
Neg logit contributions
Ready-0.032
Left-0.029
alis-0.028
sc-0.027
ready-0.026
Tokenifying
Token ID4035
Feature activation-1.39e+01

Pos logit contributions
Ready+0.009
Left+0.007
alis+0.005
sc+0.005
ready+0.005
Neg logit contributions
lee-0.029
atted-0.029
 impressed-0.027
 smiling-0.026
omo-0.026
Token glass
Token ID5405
Feature activation-1.25e+00

Pos logit contributions
Ready+0.599
Left+0.537
alis+0.480
sc+0.475
ready+0.466
Neg logit contributions
lee-0.521
atted-0.513
omo-0.492
 smiling-0.468
 impressed-0.467
Token.
Token ID13
Feature activation-2.57e-01

Pos logit contributions
Ready+0.054
Left+0.048
alis+0.045
sc+0.044
 bust+0.042
Neg logit contributions
lee-0.047
atted-0.047
 impressed-0.043
omo-0.041
 glad-0.040
Token She
Token ID1375
Feature activation-1.75e+00

Pos logit contributions
Ready+0.011
Left+0.010
alis+0.009
sc+0.009
 bust+0.009
Neg logit contributions
lee-0.010
atted-0.010
 impressed-0.009
omo-0.008
 smiling-0.008
Token looked
Token ID3114
Feature activation+3.41e+00

Pos logit contributions
Ready+0.073
Left+0.064
alis+0.060
sc+0.059
 bust+0.059
Neg logit contributions
lee-0.066
atted-0.065
 impressed-0.061
omo-0.058
 mad-0.057
Token at
Token ID379
Feature activation-1.07e+00

Pos logit contributions
omo+0.129
lee+0.127
atted+0.125
 impressed+0.109
 understanding+0.103
Neg logit contributions
Ready-0.138
Left-0.125
sc-0.118
 south-0.116
 bust-0.114
Token a
Token ID257
Feature activation-1.87e+00

Pos logit contributions
Ready+0.162
Left+0.142
alis+0.134
sc+0.130
 summit+0.127
Neg logit contributions
lee-0.136
atted-0.131
 impressed-0.125
 smiling-0.118
 glad-0.116
Token flashlight
Token ID38371
Feature activation-2.65e-02

Pos logit contributions
Ready+0.067
Left+0.058
alis+0.053
sc+0.052
 bust+0.049
Neg logit contributions
lee-0.084
atted-0.084
 impressed-0.079
omo-0.075
 smiling-0.074
Token and
Token ID290
Feature activation+6.82e+00

Pos logit contributions
Ready+0.001
Left+0.001
alis+0.001
sc+0.001
 bust+0.001
Neg logit contributions
lee-0.001
atted-0.001
 impressed-0.001
omo-0.001
 mad-0.001
Token a
Token ID257
Feature activation-1.20e+00

Pos logit contributions
lee+0.271
atted+0.269
 impressed+0.249
omo+0.237
 smiling+0.233
Neg logit contributions
Ready-0.281
Left-0.250
alis-0.229
sc-0.223
 bust-0.214
Token magn
Token ID7842
Feature activation-1.90e-01

Pos logit contributions
Ready+0.044
Left+0.038
alis+0.035
sc+0.034
 bust+0.032
Neg logit contributions
lee-0.052
atted-0.052
 impressed-0.049
omo-0.047
 smiling-0.046
Tokenifying
Token ID4035
Feature activation-1.38e+01

Pos logit contributions
Ready+0.006
Left+0.004
ready+0.004
Whe+0.004
alis+0.003
Neg logit contributions
lee-0.010
atted-0.010
 smiling-0.009
 impressed-0.009
omo-0.009
Token glass
Token ID5405
Feature activation-1.03e+00

Pos logit contributions
Ready+0.655
Left+0.575
ready+0.547
sc+0.527
works+0.515
Neg logit contributions
omo-0.444
lee-0.420
atted-0.402
 smiling-0.401
 mad-0.399
Token to
Token ID284
Feature activation-3.71e+00

Pos logit contributions
Ready+0.050
Left+0.045
alis+0.042
 bust+0.040
ready+0.040
Neg logit contributions
lee-0.034
atted-0.034
 impressed-0.030
omo-0.029
 smiling-0.028
Token examine
Token ID10716
Feature activation+9.24e-01

Pos logit contributions
Ready+0.146
Left+0.130
alis+0.111
sc+0.110
ready+0.108
Neg logit contributions
lee-0.159
atted-0.145
 gigg-0.141
 understanding-0.140
 impressed-0.138
Token their
Token ID511
Feature activation-1.21e+00

Pos logit contributions
lee+0.030
atted+0.029
 impressed+0.025
 smiling+0.024
 mad+0.023
Neg logit contributions
Ready-0.046
Left-0.041
alis-0.039
Three-0.037
sc-0.037
Token finds
Token ID7228
Feature activation-1.18e+00

Pos logit contributions
Ready+0.052
Left+0.046
alis+0.043
sc+0.042
 bust+0.040
Neg logit contributions
lee-0.047
atted-0.046
 impressed-0.042
omo-0.041
 smiling-0.040
Token hat
Token ID6877
Feature activation-1.25e+00

Pos logit contributions
lee+0.006
atted+0.006
 impressed+0.006
omo+0.005
 smiling+0.005
Neg logit contributions
Ready-0.008
Left-0.007
alis-0.006
sc-0.006
 bust-0.006
Token and
Token ID290
Feature activation+6.84e+00

Pos logit contributions
Ready+0.074
Left+0.068
alis+0.065
sc+0.065
tr+0.063
Neg logit contributions
lee-0.027
atted-0.026
 impressed-0.023
omo-0.021
 glad-0.019
Token grabbed
Token ID13176
Feature activation+2.81e+00

Pos logit contributions
atted+0.257
lee+0.255
 impressed+0.246
 glad+0.225
omo+0.222
Neg logit contributions
Ready-0.289
Left-0.249
sc-0.235
alis-0.231
 bust-0.230
Token her
Token ID607
Feature activation-2.84e-02

Pos logit contributions
lee+0.090
atted+0.090
 impressed+0.081
omo+0.076
 smiling+0.074
Neg logit contributions
Ready-0.138
Left-0.124
alis-0.116
sc-0.114
 bust-0.111
Token magn
Token ID7842
Feature activation-1.89e-01

Pos logit contributions
Ready+0.001
Left+0.001
alis+0.001
sc+0.001
 bust+0.001
Neg logit contributions
lee-0.001
atted-0.001
 impressed-0.001
omo-0.001
 smiling-0.001
Tokenifying
Token ID4035
Feature activation-1.38e+01

Pos logit contributions
Ready+0.003
Left+0.002
alis+0.002
sc+0.002
 bust+0.001
Neg logit contributions
lee-0.012
atted-0.012
 impressed-0.012
omo-0.011
 smiling-0.011
Token glass
Token ID5405
Feature activation-1.52e+00

Pos logit contributions
Ready+0.578
Left+0.509
alis+0.457
ready+0.445
sc+0.444
Neg logit contributions
lee-0.544
atted-0.538
omo-0.498
 impressed-0.484
 smiling-0.477
Token.
Token ID13
Feature activation-2.35e-01

Pos logit contributions
Ready+0.070
Left+0.063
alis+0.059
sc+0.059
 bust+0.056
Neg logit contributions
lee-0.052
atted-0.051
 impressed-0.048
omo-0.044
 glad-0.044
Token She
Token ID1375
Feature activation-2.09e+00

Pos logit contributions
Ready+0.010
Left+0.009
alis+0.008
sc+0.008
 bust+0.008
Neg logit contributions
lee-0.009
atted-0.009
 impressed-0.008
omo-0.008
 smiling-0.008
Token was
Token ID373
Feature activation+2.75e+00

Pos logit contributions
Ready+0.083
Left+0.072
sc+0.070
tr+0.067
alis+0.067
Neg logit contributions
lee-0.082
atted-0.081
 impressed-0.074
 glad-0.072
 mad-0.068
Token ready
Token ID3492
Feature activation+2.58e+00

Pos logit contributions
atted+0.094
lee+0.093
omo+0.084
ummy+0.072
ummies+0.071
Neg logit contributions
Ready-0.117
Left-0.106
alis-0.104
 highest-0.100
 south-0.098
Token said
Token ID531
Feature activation+7.68e+00

Pos logit contributions
atted+0.260
lee+0.247
 glad+0.238
omo+0.225
 impressed+0.222
Neg logit contributions
Ready-0.286
sc-0.259
Left-0.247
alis-0.240
 hunt-0.238
Token,
Token ID11
Feature activation+1.07e+01

Pos logit contributions
omo+0.316
lee+0.304
atted+0.290
 impressed+0.277
 glad+0.251
Neg logit contributions
Ready-0.250
Left-0.240
sc-0.230
fire-0.219
tted-0.216
Token holding
Token ID4769
Feature activation+3.12e+00

Pos logit contributions
atted+0.381
omo+0.372
lee+0.371
aj+0.303
ummy+0.301
Neg logit contributions
Ready-0.434
Left-0.392
 flap-0.391
alis-0.379
 gra-0.376
Token the
Token ID262
Feature activation-3.58e+00

Pos logit contributions
lee+0.124
atted+0.123
 impressed+0.116
omo+0.112
 smiling+0.106
Neg logit contributions
Ready-0.129
Left-0.115
alis-0.104
sc-0.102
 bust-0.099
Token magn
Token ID7842
Feature activation-3.74e-02

Pos logit contributions
Ready+0.156
Left+0.142
alis+0.128
sc+0.127
 bust+0.124
Neg logit contributions
lee-0.133
atted-0.130
 impressed-0.122
 smiling-0.118
 mad-0.117
Tokenifying
Token ID4035
Feature activation-1.37e+01

Pos logit contributions
Ready+0.001
Left+0.001
alis+0.000
ready+0.000
 bust+0.000
Neg logit contributions
lee-0.002
atted-0.002
 impressed-0.002
 smiling-0.002
omo-0.002
Token glass
Token ID5405
Feature activation-1.09e+00

Pos logit contributions
Ready+0.624
Left+0.561
sc+0.502
ready+0.501
alis+0.500
Neg logit contributions
lee-0.471
atted-0.458
omo-0.441
 smiling-0.431
 mad-0.429
Token over
Token ID625
Feature activation-2.13e+00

Pos logit contributions
Ready+0.049
Left+0.044
sc+0.042
alis+0.041
 summit+0.039
Neg logit contributions
lee-0.038
atted-0.038
 impressed-0.035
omo-0.033
 glad-0.032
Token a
Token ID257
Feature activation-2.56e+00

Pos logit contributions
Ready+0.082
Left+0.072
 south+0.062
ready+0.061
sc+0.060
Neg logit contributions
atted-0.088
lee-0.086
 impressed-0.084
omo-0.082
 glad-0.076
Token black
Token ID2042
Feature activation+5.18e-01

Pos logit contributions
Ready+0.096
Left+0.087
alis+0.079
 bust+0.074
sc+0.073
Neg logit contributions
lee-0.106
 impressed-0.102
atted-0.102
 smiling-0.098
omo-0.095
Token ant
Token ID1885
Feature activation-3.65e-01

Pos logit contributions
lee+0.021
atted+0.020
 smiling+0.019
omo+0.018
 understanding+0.018
Neg logit contributions
Ready-0.021
Left-0.018
 bust-0.016
alis-0.016
ready-0.016
Token Go
Token ID1514
Feature activation+5.38e-01

Pos logit contributions
Ready+0.049
Left+0.043
alis+0.038
sc+0.037
 bust+0.036
Neg logit contributions
lee-0.064
atted-0.064
 impressed-0.060
omo-0.057
 smiling-0.056
Token away
Token ID1497
Feature activation-8.55e-01

Pos logit contributions
atted+0.026
lee+0.026
 impressed+0.024
 mad+0.024
 smiling+0.024
Neg logit contributions
Ready-0.016
Left-0.014
alis-0.013
 bust-0.012
 summit-0.012
Token."
Token ID526
Feature activation+8.69e-01

Pos logit contributions
Ready+0.039
Left+0.035
sc+0.032
alis+0.032
 south+0.031
Neg logit contributions
lee-0.030
atted-0.030
 impressed-0.027
omo-0.026
 glad-0.025
Token
Token ID198
Feature activation-2.57e+00

Pos logit contributions
lee+0.042
atted+0.042
 impressed+0.039
 smiling+0.037
omo+0.036
Neg logit contributions
Ready-0.029
Left-0.025
sc-0.021
Three-0.020
alis-0.020
Token
Token ID198
Feature activation-2.43e+00

Pos logit contributions
Ready+0.093
Left+0.081
alis+0.070
sc+0.070
Three+0.067
Neg logit contributions
lee-0.117
atted-0.116
 impressed-0.108
omo-0.102
 smiling-0.102
TokenL
Token ID43
Feature activation+6.90e+00

Pos logit contributions
Ready+0.106
Left+0.094
Three+0.081
sc+0.081
Skip+0.079
Neg logit contributions
lee-0.101
atted-0.100
 impressed-0.088
 smiling-0.084
 glad-0.081
Tokenily
Token ID813
Feature activation+5.57e+00

Pos logit contributions
lee+0.280
atted+0.278
 impressed+0.262
 smiling+0.245
omo+0.245
Neg logit contributions
Ready-0.280
Left-0.247
alis-0.224
sc-0.219
Three-0.211
Token ran
Token ID4966
Feature activation+5.96e+00

Pos logit contributions
lee+0.217
atted+0.202
 impressed+0.198
 glad+0.195
omo+0.188
Neg logit contributions
Ready-0.219
Left-0.201
sc-0.189
 bust-0.177
alis-0.173
Token to
Token ID284
Feature activation-1.66e+00

Pos logit contributions
lee+0.265
atted+0.259
 impressed+0.242
omo+0.239
 smiling+0.220
Neg logit contributions
Ready-0.236
Left-0.208
sc-0.187
alis-0.173
ready-0.172
Token mom
Token ID1995
Feature activation+4.92e+00

Pos logit contributions
Ready+0.083
Left+0.075
alis+0.069
sc+0.068
 bust+0.066
Neg logit contributions
lee-0.053
atted-0.052
 impressed-0.047
omo-0.045
 smiling-0.042
Token and
Token ID290
Feature activation+7.85e+00

Pos logit contributions
lee+0.156
atted+0.153
 impressed+0.153
omo+0.152
 pleased+0.135
Neg logit contributions
Ready-0.219
sc-0.198
Left-0.194
 hunt-0.187
 south-0.183
Token in
Token ID287
Feature activation-6.08e+00

Pos logit contributions
Ready+0.098
Left+0.088
alis+0.083
sc+0.080
 bust+0.079
Neg logit contributions
lee-0.061
atted-0.061
 impressed-0.056
omo-0.052
 smiling-0.052
Token the
Token ID262
Feature activation-5.60e+00

Pos logit contributions
Ready+0.262
Left+0.232
alis+0.213
sc+0.209
 bust+0.202
Neg logit contributions
atted-0.232
lee-0.232
 impressed-0.212
omo-0.202
 smiling-0.196
Token garden
Token ID11376
Feature activation-4.39e+00

Pos logit contributions
Ready+0.231
Left+0.211
sc+0.201
alis+0.199
 bust+0.186
Neg logit contributions
lee-0.203
atted-0.196
 smiling-0.193
omo-0.188
 mad-0.187
Token,"
Token ID553
Feature activation+2.32e+00

Pos logit contributions
Ready+0.211
Left+0.190
alis+0.177
sc+0.175
 bust+0.168
Neg logit contributions
lee-0.144
atted-0.143
 impressed-0.129
omo-0.122
 smiling-0.118
Token Lily
Token ID20037
Feature activation+6.80e+00

Pos logit contributions
atted+0.095
lee+0.093
omo+0.083
 impressed+0.081
rou+0.078
Neg logit contributions
Ready-0.093
Left-0.076
 am-0.069
sc-0.069
ready-0.068
Token said
Token ID531
Feature activation+7.21e+00

Pos logit contributions
atted+0.271
lee+0.259
irling+0.245
 glad+0.243
 impressed+0.241
Neg logit contributions
Ready-0.226
Left-0.209
sc-0.207
 will-0.198
 hunt-0.195
Token.
Token ID13
Feature activation+1.31e+00

Pos logit contributions
omo+0.350
lee+0.333
atted+0.315
 impressed+0.310
 glad+0.277
Neg logit contributions
Ready-0.194
Left-0.189
sc-0.178
 flap-0.159
fire-0.158
Token
Token ID198
Feature activation-2.33e+00

Pos logit contributions
atted+0.065
lee+0.065
 impressed+0.060
omo+0.059
 mad+0.056
Neg logit contributions
Ready-0.043
Left-0.037
sc-0.031
Three-0.029
alis-0.029
Token
Token ID198
Feature activation-2.22e+00

Pos logit contributions
Ready+0.067
Left+0.056
Three+0.044
 Ready+0.043
sc+0.043
Neg logit contributions
atted-0.122
lee-0.121
 impressed-0.112
omo-0.109
 smiling-0.107
Token"
Token ID1
Feature activation-1.73e+00

Pos logit contributions
Ready+0.088
Left+0.075
Three+0.066
 south+0.065
 Ready+0.063
Neg logit contributions
lee-0.101
atted-0.100
 impressed-0.087
omo-0.082
 smiling-0.081
TokenWe
Token ID1135
Feature activation-4.15e+00

Pos logit contributions
Ready+0.061
Left+0.053
alis+0.050
sc+0.048
 summit+0.046
Neg logit contributions
atted-0.076
lee-0.076
 impressed-0.074
omo-0.070
 smiling-0.069
Token girl
Token ID2576
Feature activation+3.86e+00

Pos logit contributions
lee+0.261
atted+0.260
 impressed+0.244
omo+0.233
 glad+0.226
Neg logit contributions
Ready-0.215
Left-0.184
alis-0.169
sc-0.164
 bust-0.159
Token heard
Token ID2982
Feature activation+1.90e+00

Pos logit contributions
lee+0.160
atted+0.157
 impressed+0.147
omo+0.143
 mad+0.142
Neg logit contributions
Ready-0.132
Left-0.112
 will-0.109
 bust-0.107
 am-0.105
Token their
Token ID511
Feature activation+1.39e+00

Pos logit contributions
atted+0.061
lee+0.059
 impressed+0.054
omo+0.053
 glad+0.049
Neg logit contributions
Ready-0.092
Left-0.083
alis-0.077
 bust-0.075
sc-0.075
Token words
Token ID2456
Feature activation-1.42e+00

Pos logit contributions
atted+0.058
lee+0.058
 impressed+0.053
omo+0.052
 glad+0.049
Neg logit contributions
Ready-0.054
Left-0.048
alis-0.043
sc-0.042
 summit-0.041
Token and
Token ID290
Feature activation+7.67e+00

Pos logit contributions
Ready+0.080
Left+0.073
alis+0.069
sc+0.068
ready+0.066
Neg logit contributions
lee-0.035
atted-0.034
 impressed-0.031
 smiling-0.028
omo-0.027
Token believed
Token ID4762
Feature activation+6.79e+00

Pos logit contributions
atted+0.254
lee+0.253
omo+0.243
 impressed+0.221
 glad+0.212
Neg logit contributions
Ready-0.345
Left-0.295
 bust-0.290
alis-0.276
sc-0.273
Token them
Token ID606
Feature activation-2.24e+00

Pos logit contributions
atted+0.224
lee+0.223
omo+0.204
 impressed+0.202
 smiling+0.182
Neg logit contributions
Ready-0.316
Left-0.287
alis-0.263
sc-0.262
 bust-0.254
Token.
Token ID13
Feature activation+2.51e-01

Pos logit contributions
Ready+0.117
Left+0.105
alis+0.100
sc+0.096
Three+0.095
Neg logit contributions
lee-0.066
atted-0.064
 impressed-0.059
 smiling-0.055
 mad-0.054
Token She
Token ID1375
Feature activation-1.20e+00

Pos logit contributions
lee+0.010
atted+0.010
 impressed+0.009
omo+0.009
 smiling+0.009
Neg logit contributions
Ready-0.010
Left-0.009
alis-0.008
sc-0.008
 bust-0.008
Token knew
Token ID2993
Feature activation+8.12e+00

Pos logit contributions
Ready+0.049
Left+0.042
 bust+0.040
alis+0.039
sc+0.039
Neg logit contributions
atted-0.046
lee-0.044
omo-0.040
 impressed-0.040
 glad-0.040
Token that
Token ID326
Feature activation-3.77e+00

Pos logit contributions
atted+0.286
lee+0.285
omo+0.257
 impressed+0.253
 mad+0.235
Neg logit contributions
Ready-0.359
Left-0.316
alis-0.290
ready-0.284
 summit-0.282
Token<|endoftext|>
Token ID50256
Feature activation-7.35e+00

Pos logit contributions
Ready+0.019
Left+0.017
alis+0.016
sc+0.016
 bust+0.015
Neg logit contributions
lee-0.017
atted-0.017
 impressed-0.016
omo-0.015
 glad-0.015
TokenOnce
Token ID7454
Feature activation-3.55e-01

Pos logit contributions
Ready+0.357
alis+0.329
 bust+0.314
 summit+0.312
Left+0.305
Neg logit contributions
lee-0.205
atted-0.194
 smiling-0.188
omo-0.178
 glad-0.170
Token upon
Token ID2402
Feature activation-5.47e+00

Pos logit contributions
Ready+0.012
Left+0.011
sc+0.010
alis+0.010
 summit+0.009
Neg logit contributions
lee-0.015
atted-0.015
 impressed-0.014
omo-0.014
 smiling-0.014
Token a
Token ID257
Feature activation-4.60e-01

Pos logit contributions
Ready+0.254
Left+0.222
alis+0.217
sc+0.209
 bust+0.206
Neg logit contributions
lee-0.177
atted-0.175
 impressed-0.174
 glad-0.164
 smiling-0.163
Token time
Token ID640
Feature activation-7.04e-01

Pos logit contributions
Ready+0.012
Left+0.010
alis+0.009
sc+0.008
Three+0.008
Neg logit contributions
lee-0.025
atted-0.025
 impressed-0.024
 smiling-0.022
omo-0.022
Token,
Token ID11
Feature activation+8.25e+00

Pos logit contributions
Ready+0.034
Left+0.033
 am+0.030
sc+0.029
 shortcut+0.028
Neg logit contributions
lee-0.022
atted-0.020
 impressed-0.018
omo-0.017
 understanding-0.016
Token there
Token ID612
Feature activation-7.97e+00

Pos logit contributions
atted+0.246
lee+0.236
 impressed+0.228
 glad+0.216
 mad+0.209
Neg logit contributions
Ready-0.420
Left-0.371
alis-0.360
sc-0.343
 summit-0.340
Token was
Token ID373
Feature activation+3.50e+00

Pos logit contributions
Ready+0.335
Left+0.297
alis+0.271
sc+0.267
 bust+0.257
Neg logit contributions
lee-0.311
atted-0.308
 impressed-0.285
omo-0.270
 smiling-0.264
Token a
Token ID257
Feature activation-1.83e-01

Pos logit contributions
atted+0.167
lee+0.166
 impressed+0.151
omo+0.145
 smiling+0.141
Neg logit contributions
Ready-0.122
Left-0.106
alis-0.094
sc-0.091
ready-0.087
Token polite
Token ID23507
Feature activation+5.62e+00

Pos logit contributions
Ready+0.008
Left+0.007
alis+0.006
 bust+0.006
Three+0.006
Neg logit contributions
atted-0.007
lee-0.007
 impressed-0.006
omo-0.006
 smiling-0.006
Token little
Token ID1310
Feature activation+4.92e+00

Pos logit contributions
atted+0.265
lee+0.255
 impressed+0.240
 mad+0.222
omo+0.221
Neg logit contributions
Ready-0.189
Left-0.164
alis-0.150
 bust-0.141
Skip-0.138
Tokenandy
Token ID10757
Feature activation+6.85e+00

Pos logit contributions
 impressed+0.186
 smiling+0.174
 glad+0.173
atted+0.170
 hugging+0.170
Neg logit contributions
Ready-0.235
Left-0.208
 summit-0.205
Three-0.203
alis-0.198
Token opened
Token ID4721
Feature activation+1.73e+00

Pos logit contributions
atted+0.240
lee+0.239
 impressed+0.229
 glad+0.227
omo+0.220
Neg logit contributions
Ready-0.280
Left-0.249
sc-0.243
 bust-0.239
alis-0.235
Token the
Token ID262
Feature activation-5.54e+00

Pos logit contributions
atted+0.075
lee+0.075
 impressed+0.072
omo+0.069
 glad+0.067
Neg logit contributions
Ready-0.060
Left-0.053
 south-0.047
 summit-0.047
alis-0.047
Token cup
Token ID6508
Feature activation-1.12e+00

Pos logit contributions
Ready+0.254
Left+0.233
alis+0.213
Skip+0.207
Whe+0.205
Neg logit contributions
lee-0.192
atted-0.187
 impressed-0.175
 smiling-0.174
 mad-0.170
Tokenboard
Token ID3526
Feature activation-1.89e+00

Pos logit contributions
Ready+0.033
Left+0.028
alis+0.024
sc+0.024
 bust+0.022
Neg logit contributions
lee-0.057
atted-0.057
 impressed-0.054
omo-0.052
 glad-0.051
Token and
Token ID290
Feature activation+6.16e+00

Pos logit contributions
Ready+0.107
sc+0.097
Left+0.097
alis+0.093
 summit+0.090
Neg logit contributions
lee-0.044
atted-0.044
 impressed-0.038
omo-0.038
 glad-0.034
Token saw
Token ID2497
Feature activation+3.85e-01

Pos logit contributions
lee+0.246
atted+0.246
omo+0.231
 impressed+0.228
 glad+0.213
Neg logit contributions
Ready-0.253
Left-0.214
 bust-0.200
sc-0.198
ready-0.189
Token a
Token ID257
Feature activation-2.42e+00

Pos logit contributions
atted+0.017
lee+0.017
 impressed+0.016
omo+0.016
 mad+0.015
Neg logit contributions
Ready-0.013
Left-0.011
alis-0.010
sc-0.010
 summit-0.010
Token big
Token ID1263
Feature activation-2.36e-01

Pos logit contributions
Ready+0.095
Left+0.081
sc+0.073
alis+0.073
 bust+0.070
Neg logit contributions
atted-0.105
lee-0.103
 impressed-0.091
omo-0.088
 glad-0.085
Token,
Token ID11
Feature activation+7.23e+00

Pos logit contributions
Ready+0.009
Left+0.007
alis+0.007
 hunt+0.007
 shortcut+0.007
Neg logit contributions
atted-0.010
lee-0.010
 impressed-0.009
omo-0.008
aged-0.008
Token fat
Token ID3735
Feature activation+1.84e+00

Pos logit contributions
atted+0.296
lee+0.284
 impressed+0.245
omo+0.245
 glad+0.227
Neg logit contributions
Ready-0.305
Left-0.260
sc-0.244
alis-0.240
 bust-0.236
Token ran
Token ID4966
Feature activation+2.96e+00

Pos logit contributions
Ready+0.040
Left+0.036
alis+0.033
sc+0.033
 bust+0.032
Neg logit contributions
lee-0.031
atted-0.030
 impressed-0.028
omo-0.027
 smiling-0.026
Token after
Token ID706
Feature activation-3.61e+00

Pos logit contributions
lee+0.147
atted+0.147
 impressed+0.138
omo+0.135
 glad+0.129
Neg logit contributions
Ready-0.096
Left-0.082
sc-0.073
alis-0.069
ready-0.065
Token it
Token ID340
Feature activation-7.62e+00

Pos logit contributions
Ready+0.175
Left+0.158
alis+0.145
sc+0.145
ready+0.139
Neg logit contributions
atted-0.117
lee-0.116
 impressed-0.106
omo-0.102
 glad-0.095
Token.
Token ID13
Feature activation-1.51e+00

Pos logit contributions
Ready+0.352
Left+0.317
sc+0.297
alis+0.292
 south+0.276
Neg logit contributions
lee-0.263
atted-0.259
 impressed-0.238
omo-0.231
 glad-0.217
Token It
Token ID632
Feature activation-6.48e+00

Pos logit contributions
Ready+0.061
Left+0.053
alis+0.049
sc+0.048
 bust+0.046
Neg logit contributions
lee-0.062
atted-0.061
 impressed-0.057
omo-0.054
 smiling-0.053
Token caught
Token ID4978
Feature activation+4.29e+00

Pos logit contributions
Ready+0.291
Left+0.259
alis+0.242
sc+0.233
ready+0.229
Neg logit contributions
atted-0.233
lee-0.233
 impressed-0.216
omo-0.203
 smiling-0.200
Token the
Token ID262
Feature activation-5.35e+00

Pos logit contributions
lee+0.160
atted+0.159
 impressed+0.149
omo+0.142
 glad+0.135
Neg logit contributions
Ready-0.188
Left-0.169
alis-0.153
sc-0.151
ready-0.144
Token ball
Token ID2613
Feature activation-1.74e+00

Pos logit contributions
Ready+0.199
Left+0.177
alis+0.160
sc+0.155
 bust+0.152
Neg logit contributions
lee-0.227
atted-0.225
 impressed-0.213
omo-0.207
 smiling-0.205
Token in
Token ID287
Feature activation-6.39e+00

Pos logit contributions
Ready+0.093
Left+0.085
sc+0.084
alis+0.081
 highest+0.079
Neg logit contributions
lee-0.048
atted-0.046
 impressed-0.040
omo-0.039
 glad-0.035
Token its
Token ID663
Feature activation-1.99e+00

Pos logit contributions
Ready+0.269
Left+0.237
alis+0.213
sc+0.210
Three+0.203
Neg logit contributions
atted-0.261
lee-0.254
 impressed-0.232
omo-0.216
 glad-0.211
Token mouth
Token ID5422
Feature activation-2.96e+00

Pos logit contributions
Ready+0.100
Left+0.090
alis+0.083
sc+0.083
 bust+0.081
Neg logit contributions
lee-0.063
atted-0.063
 impressed-0.056
omo-0.054
 smiling-0.053
Token and
Token ID290
Feature activation+7.19e+00

Pos logit contributions
lee+0.007
atted+0.007
 impressed+0.007
 mad+0.006
 pleased+0.006
Neg logit contributions
Ready-0.011
Left-0.010
sc-0.010
 will-0.009
 am-0.009
Token they
Token ID484
Feature activation-3.34e+00

Pos logit contributions
atted+0.293
lee+0.292
 impressed+0.263
omo+0.250
 mad+0.249
Neg logit contributions
Ready-0.287
Left-0.252
alis-0.224
sc-0.224
Skip-0.221
Token did
Token ID750
Feature activation-1.07e+00

Pos logit contributions
Ready+0.157
Left+0.139
alis+0.131
sc+0.128
ready+0.125
Neg logit contributions
lee-0.117
atted-0.114
 impressed-0.105
omo-0.098
 smiling-0.098
Token everything
Token ID2279
Feature activation-7.74e+00

Pos logit contributions
Ready+0.048
Left+0.043
alis+0.040
sc+0.039
 bust+0.038
Neg logit contributions
lee-0.038
atted-0.038
 impressed-0.035
omo-0.033
 smiling-0.032
Token together
Token ID1978
Feature activation-6.37e-01

Pos logit contributions
Ready+0.377
Left+0.345
sc+0.325
alis+0.316
 bust+0.308
Neg logit contributions
lee-0.246
atted-0.242
omo-0.213
 impressed-0.207
 understanding-0.186
Token.
Token ID13
Feature activation-4.24e-01

Pos logit contributions
Ready+0.034
Left+0.030
alis+0.029
 bust+0.028
sc+0.028
Neg logit contributions
lee-0.018
atted-0.017
 impressed-0.016
 smiling-0.015
 mad-0.014
Token One
Token ID1881
Feature activation-3.69e+00

Pos logit contributions
Ready+0.019
Left+0.016
 summit+0.016
 bust+0.016
alis+0.016
Neg logit contributions
lee-0.015
omo-0.015
atted-0.014
 impressed-0.013
 glad-0.013
Token day
Token ID1110
Feature activation-2.12e-01

Pos logit contributions
Ready+0.110
Left+0.093
alis+0.081
sc+0.079
 bust+0.074
Neg logit contributions
lee-0.191
atted-0.190
 impressed-0.178
omo-0.170
 smiling-0.168
Token,
Token ID11
Feature activation+8.50e+00

Pos logit contributions
Ready+0.012
Left+0.011
sc+0.011
alis+0.010
ready+0.010
Neg logit contributions
lee-0.005
atted-0.005
 impressed-0.005
omo-0.004
 mad-0.004
Token Lily
Token ID20037
Feature activation+4.54e+00

Pos logit contributions
lee+0.256
atted+0.255
 impressed+0.230
omo+0.215
 smiling+0.209
Neg logit contributions
Ready-0.434
Left-0.393
alis-0.368
sc-0.362
 bust-0.352
Token went
Token ID1816
Feature activation+3.63e+00

Pos logit contributions
atted+0.210
 impressed+0.193
lee+0.193
 understanding+0.191
 glad+0.187
Neg logit contributions
Ready-0.150
 hunt-0.125
sc-0.121
Left-0.118
alis-0.115
Token.
Token ID13
Feature activation+9.08e-02

Pos logit contributions
lee+0.014
atted+0.014
 impressed+0.012
 smiling+0.011
omo+0.011
Neg logit contributions
Ready-0.023
Left-0.021
alis-0.019
sc-0.019
 bust-0.019
Token<|endoftext|>
Token ID50256
Feature activation-7.29e+00

Pos logit contributions
lee+0.003
atted+0.003
 impressed+0.003
 glad+0.003
omo+0.003
Neg logit contributions
Ready-0.004
Left-0.003
alis-0.003
sc-0.003
 bust-0.003
TokenSam
Token ID16305
Feature activation+4.86e+00

Pos logit contributions
Ready+0.246
alis+0.225
 bust+0.211
 summit+0.211
Left+0.196
Neg logit contributions
lee-0.296
atted-0.296
 smiling-0.294
omo-0.272
 and-0.270
Token and
Token ID290
Feature activation+8.16e+00

Pos logit contributions
 impressed+0.175
atted+0.175
lee+0.171
 understanding+0.157
 pleased+0.155
Neg logit contributions
Ready-0.211
Left-0.182
 am-0.168
alis-0.166
sc-0.166
Token Mia
Token ID32189
Feature activation+3.85e+00

Pos logit contributions
atted+0.278
lee+0.277
 impressed+0.253
omo+0.242
 smiling+0.224
Neg logit contributions
Ready-0.385
Left-0.345
 bust-0.314
alis-0.309
sc-0.306
Token were
Token ID547
Feature activation+2.75e+00

Pos logit contributions
lee+0.175
atted+0.175
 impressed+0.166
omo+0.157
 glad+0.152
Neg logit contributions
Ready-0.136
Left-0.116
alis-0.101
 bust-0.101
sc-0.101
Token playing
Token ID2712
Feature activation-7.08e-01

Pos logit contributions
lee+0.088
atted+0.084
omo+0.079
 impressed+0.076
ushed+0.074
Neg logit contributions
Ready-0.110
Left-0.101
 same-0.100
 middle-0.100
alis-0.099
Token on
Token ID319
Feature activation-4.17e+00

Pos logit contributions
Ready+0.036
Left+0.032
alis+0.030
 bust+0.030
 summit+0.029
Neg logit contributions
atted-0.021
lee-0.020
 impressed-0.019
 smiling-0.018
 mad-0.018
Token the
Token ID262
Feature activation-5.05e+00

Pos logit contributions
Ready+0.191
Left+0.170
alis+0.158
sc+0.156
 bust+0.151
Neg logit contributions
lee-0.148
atted-0.145
 impressed-0.134
omo-0.127
 smiling-0.126
Token beach
Token ID10481
Feature activation+7.67e-01

Pos logit contributions
Ready+0.180
Left+0.160
alis+0.142
sc+0.138
 bust+0.134
Neg logit contributions
lee-0.226
atted-0.220
 impressed-0.210
omo-0.201
 smiling-0.200
Token.
Token ID13
Feature activation-9.95e-01

Pos logit contributions
lee+0.024
atted+0.024
 impressed+0.022
omo+0.020
 smiling+0.020
Neg logit contributions
Ready-0.038
Left-0.034
alis-0.032
sc-0.031
 bust-0.031
Token
Token ID198
Feature activation-3.80e+00

Pos logit contributions
Ready+0.175
Left+0.152
alis+0.146
sc+0.138
 bust+0.137
Neg logit contributions
lee-0.157
atted-0.155
 impressed-0.148
omo-0.139
 glad-0.137
TokenAs
Token ID1722
Feature activation+7.05e-01

Pos logit contributions
Ready+0.154
Left+0.136
alis+0.131
 bust+0.123
sc+0.121
Neg logit contributions
atted-0.146
lee-0.146
 impressed-0.141
omo-0.137
 mad-0.128
Token Tim
Token ID5045
Feature activation+4.61e+00

Pos logit contributions
atted+0.027
lee+0.027
 impressed+0.023
 understanding+0.021
 pleased+0.021
Neg logit contributions
Ready-0.032
Left-0.028
ready-0.025
Three-0.025
 south-0.025
Token walked
Token ID6807
Feature activation+1.03e+00

Pos logit contributions
lee+0.178
atted+0.178
 impressed+0.167
omo+0.156
 glad+0.154
Neg logit contributions
Ready-0.195
Left-0.173
alis-0.159
sc-0.154
 bust-0.151
Token,
Token ID11
Feature activation+8.50e+00

Pos logit contributions
atted+0.028
lee+0.027
 impressed+0.025
 smiling+0.023
 glad+0.023
Neg logit contributions
Ready-0.055
Left-0.049
alis-0.048
sc-0.045
 summit-0.045
Token he
Token ID339
Feature activation-1.01e+00

Pos logit contributions
lee+0.278
atted+0.275
 impressed+0.249
omo+0.233
 smiling+0.225
Neg logit contributions
Ready-0.417
Left-0.376
alis-0.347
sc-0.341
ready-0.333
Token saw
Token ID2497
Feature activation+1.21e+00

Pos logit contributions
Ready+0.043
Left+0.038
alis+0.035
sc+0.034
 bust+0.033
Neg logit contributions
lee-0.039
atted-0.039
 impressed-0.036
omo-0.034
 smiling-0.034
Token a
Token ID257
Feature activation-1.66e+00

Pos logit contributions
lee+0.053
atted+0.053
 impressed+0.049
omo+0.047
 smiling+0.046
Neg logit contributions
Ready-0.045
Left-0.039
alis-0.035
sc-0.034
 bust-0.033
Token big
Token ID1263
Feature activation+6.16e-01

Pos logit contributions
Ready+0.068
Left+0.061
alis+0.056
sc+0.055
 bust+0.053
Neg logit contributions
lee-0.065
atted-0.064
 impressed-0.061
omo-0.058
 smiling-0.057
Token rock
Token ID3881
Feature activation-2.08e+00

Pos logit contributions
atted+0.029
lee+0.028
 impressed+0.026
omo+0.025
 glad+0.024
Neg logit contributions
Ready-0.021
Left-0.018
alis-0.017
 bust-0.016
sc-0.016
Token.
Token ID13
Feature activation-5.82e-01

Pos logit contributions
Ready+0.103
Left+0.094
alis+0.086
 bust+0.083
sc+0.083
Neg logit contributions
atted-0.066
lee-0.065
 impressed-0.059
 smiling-0.056
 mad-0.056
Token to
Token ID284
Feature activation-2.78e+00

Pos logit contributions
lee+0.049
atted+0.048
 impressed+0.045
omo+0.043
 glad+0.041
Neg logit contributions
Ready-0.054
Left-0.048
alis-0.044
sc-0.043
 bust-0.042
Token play
Token ID711
Feature activation-1.84e+00

Pos logit contributions
Ready+0.092
Left+0.081
sc+0.071
alis+0.071
 bust+0.065
Neg logit contributions
lee-0.132
atted-0.129
 impressed-0.123
 smiling-0.120
 mad-0.119
Token both
Token ID1111
Feature activation-2.19e+00

Pos logit contributions
Ready+0.097
Left+0.087
alis+0.084
 bust+0.082
 summit+0.082
Neg logit contributions
atted-0.047
 impressed-0.047
lee-0.047
 smiling-0.043
 mad-0.042
Token games
Token ID1830
Feature activation-2.64e+00

Pos logit contributions
Ready+0.104
Left+0.094
alis+0.087
sc+0.083
 bust+0.083
Neg logit contributions
atted-0.074
lee-0.074
 impressed-0.068
omo-0.064
 smiling-0.063
Token.
Token ID13
Feature activation-7.68e-01

Pos logit contributions
Ready+0.132
Left+0.119
sc+0.112
alis+0.111
ready+0.106
Neg logit contributions
lee-0.082
atted-0.081
 impressed-0.072
omo-0.069
 mad-0.065
Token First
Token ID3274
Feature activation+1.28e+00

Pos logit contributions
Ready+0.032
Left+0.029
alis+0.027
 bust+0.026
sc+0.026
Neg logit contributions
lee-0.029
atted-0.029
 impressed-0.026
omo-0.025
 glad-0.025
Token,
Token ID11
Feature activation+7.91e+00

Pos logit contributions
lee+0.037
atted+0.036
 impressed+0.035
omo+0.031
 glad+0.030
Neg logit contributions
Ready-0.064
Left-0.058
sc-0.054
ready-0.053
alis-0.053
Token they
Token ID484
Feature activation-3.11e+00

Pos logit contributions
lee+0.224
atted+0.221
 impressed+0.206
 smiling+0.191
omo+0.187
Neg logit contributions
Ready-0.402
Left-0.367
alis-0.350
sc-0.341
 bust-0.328
Token played
Token ID2826
Feature activation+1.83e+00

Pos logit contributions
Ready+0.132
Left+0.118
alis+0.108
sc+0.104
ready+0.102
Neg logit contributions
lee-0.121
atted-0.118
 impressed-0.111
 smiling-0.103
omo-0.103
Token hide
Token ID7808
Feature activation+3.44e+00

Pos logit contributions
atted+0.066
lee+0.065
 impressed+0.065
 smiling+0.060
 mad+0.059
Neg logit contributions
Ready-0.078
Left-0.068
alis-0.066
 bust-0.063
 summit-0.062
Token and
Token ID290
Feature activation+6.29e+00

Pos logit contributions
atted+0.078
lee+0.076
 impressed+0.067
omo+0.066
 glad+0.061
Neg logit contributions
Ready-0.196
Left-0.183
sc-0.178
alis-0.169
 bust-0.167
Token many
Token ID867
Feature activation-2.51e+00

Pos logit contributions
Ready+0.035
Left+0.031
alis+0.028
sc+0.028
 bust+0.027
Neg logit contributions
lee-0.037
atted-0.037
 impressed-0.035
omo-0.034
 mad-0.032
Token rooms
Token ID9519
Feature activation-2.50e+00

Pos logit contributions
Ready+0.082
Left+0.072
sc+0.065
 south+0.062
 bust+0.061
Neg logit contributions
atted-0.112
lee-0.110
omo-0.105
 impressed-0.103
 glad-0.100
Token and
Token ID290
Feature activation+5.62e+00

Pos logit contributions
Ready+0.114
Left+0.102
sc+0.098
 south+0.095
alis+0.095
Neg logit contributions
atted-0.081
lee-0.080
omo-0.074
 impressed-0.073
 mad-0.069
Token windows
Token ID9168
Feature activation-3.05e+00

Pos logit contributions
lee+0.227
atted+0.226
 impressed+0.211
omo+0.199
 smiling+0.198
Neg logit contributions
Ready-0.226
Left-0.201
alis-0.186
sc-0.179
 bust-0.171
Token and
Token ID290
Feature activation+5.73e+00

Pos logit contributions
Ready+0.121
Left+0.111
 south+0.104
alis+0.103
sc+0.102
Neg logit contributions
lee-0.108
atted-0.106
 impressed-0.102
omo-0.098
 glad-0.094
Token stairs
Token ID16046
Feature activation-2.45e+00

Pos logit contributions
lee+0.227
atted+0.223
 impressed+0.212
 smiling+0.200
omo+0.196
Neg logit contributions
Ready-0.233
Left-0.208
alis-0.195
sc-0.185
 summit-0.178
Token.
Token ID13
Feature activation-9.37e-01

Pos logit contributions
Ready+0.113
Left+0.102
alis+0.094
sc+0.094
 bust+0.090
Neg logit contributions
lee-0.084
atted-0.083
 impressed-0.076
omo-0.073
 glad-0.070
Token A
Token ID317
Feature activation-1.35e+00

Pos logit contributions
Ready+0.046
Left+0.041
alis+0.038
sc+0.038
 bust+0.036
Neg logit contributions
lee-0.031
atted-0.030
 impressed-0.028
omo-0.026
 smiling-0.025
Token friendly
Token ID8030
Feature activation+3.71e+00

Pos logit contributions
Ready+0.053
Left+0.047
alis+0.044
sc+0.042
ready+0.040
Neg logit contributions
lee-0.055
atted-0.055
 impressed-0.053
omo-0.049
 smiling-0.049
Token man
Token ID582
Feature activation+2.70e+00

Pos logit contributions
atted+0.157
lee+0.157
 impressed+0.145
omo+0.139
 mad+0.135
Neg logit contributions
Ready-0.142
Left-0.124
alis-0.113
sc-0.110
 bust-0.108
Token with
Token ID351
Feature activation-1.48e-01

Pos logit contributions
lee+0.103
atted+0.098
omo+0.091
 impressed+0.091
 mad+0.084
Neg logit contributions
Ready-0.117
Left-0.103
sc-0.096
 bust-0.091
alis-0.091
Token tree
Token ID5509
Feature activation-4.97e+00

Pos logit contributions
sc+0.193
Left+0.178
Ready+0.175
works+0.173
alis+0.161
Neg logit contributions
 mad-0.215
 dad-0.214
 glad-0.210
 smiling-0.210
 understanding-0.209
Token,
Token ID11
Feature activation+7.27e+00

Pos logit contributions
Ready+0.343
Left+0.321
alis+0.303
sc+0.300
 bust+0.295
Neg logit contributions
atted-0.060
lee-0.058
 impressed-0.044
 smiling-0.040
 mad-0.038
Token she
Token ID673
Feature activation-3.10e+00

Pos logit contributions
atted+0.174
lee+0.172
 impressed+0.152
omo+0.141
 smiling+0.140
Neg logit contributions
Ready-0.410
Left-0.376
alis-0.361
sc-0.355
 bust-0.342
Token sees
Token ID7224
Feature activation-2.65e-01

Pos logit contributions
Ready+0.111
Left+0.097
alis+0.087
sc+0.086
ready+0.082
Neg logit contributions
atted-0.140
lee-0.139
 impressed-0.129
 smiling-0.124
omo-0.123
Token a
Token ID257
Feature activation-3.04e+00

Pos logit contributions
Ready+0.011
Left+0.009
alis+0.008
sc+0.008
 bust+0.008
Neg logit contributions
lee-0.011
atted-0.011
 impressed-0.010
omo-0.010
 smiling-0.009
Token problem
Token ID1917
Feature activation-2.12e+00

Pos logit contributions
Ready+0.127
Left+0.115
alis+0.107
sc+0.107
 bust+0.100
Neg logit contributions
lee-0.113
 impressed-0.111
atted-0.109
 smiling-0.106
 mad-0.104
Token.
Token ID13
Feature activation-8.67e-01

Pos logit contributions
Ready+0.098
Left+0.087
sc+0.081
alis+0.080
ready+0.077
Neg logit contributions
lee-0.074
atted-0.073
 impressed-0.068
omo-0.064
 glad-0.062
Token The
Token ID383
Feature activation-3.04e+00

Pos logit contributions
Ready+0.034
Left+0.030
sc+0.028
alis+0.028
 bust+0.026
Neg logit contributions
lee-0.036
atted-0.035
 impressed-0.032
omo-0.031
 glad-0.031
Token arrow
Token ID15452
Feature activation-1.56e-01

Pos logit contributions
Ready+0.149
Left+0.142
sc+0.135
alis+0.131
fire+0.127
Neg logit contributions
lee-0.087
 impressed-0.082
 smiling-0.079
 understanding-0.079
atted-0.079
Token is
Token ID318
Feature activation-5.26e-01

Pos logit contributions
Ready+0.005
Left+0.004
alis+0.004
sc+0.004
 bust+0.004
Neg logit contributions
lee-0.008
atted-0.008
 impressed-0.007
omo-0.007
 smiling-0.007
Token stuck
Token ID7819
Feature activation+5.49e-01

Pos logit contributions
Ready+0.023
Left+0.021
alis+0.019
 south+0.019
sc+0.018
Neg logit contributions
lee-0.019
atted-0.019
 impressed-0.017
omo-0.016
 smiling-0.015
Token't
Token ID470
Feature activation-1.27e+00

Pos logit contributions
Ready+0.058
Left+0.050
alis+0.047
sc+0.044
 south+0.043
Neg logit contributions
lee-0.062
atted-0.059
 impressed-0.056
 mad-0.055
omo-0.054
Token belong
Token ID5594
Feature activation-4.51e+00

Pos logit contributions
Ready+0.040
Left+0.033
alis+0.030
sc+0.030
Three+0.029
Neg logit contributions
lee-0.061
 mad-0.060
atted-0.060
 understanding-0.059
 impressed-0.059
Token to
Token ID284
Feature activation-5.21e+00

Pos logit contributions
Ready+0.204
Left+0.182
alis+0.168
sc+0.166
 bust+0.160
Neg logit contributions
lee-0.161
atted-0.160
 impressed-0.146
omo-0.139
 smiling-0.135
Token her
Token ID607
Feature activation-1.05e+00

Pos logit contributions
Ready+0.252
Left+0.226
alis+0.211
sc+0.208
 bust+0.201
Neg logit contributions
lee-0.173
atted-0.170
 impressed-0.155
omo-0.146
 smiling-0.145
Token.
Token ID13
Feature activation-8.28e-01

Pos logit contributions
Ready+0.049
Left+0.044
alis+0.041
sc+0.040
 bust+0.039
Neg logit contributions
lee-0.035
atted-0.035
 impressed-0.032
omo-0.030
 smiling-0.029
Token She
Token ID1375
Feature activation-1.69e+00

Pos logit contributions
Ready+0.031
Left+0.026
alis+0.024
sc+0.023
Three+0.022
Neg logit contributions
atted-0.036
lee-0.036
 impressed-0.034
 smiling-0.032
 mad-0.032
Token said
Token ID531
Feature activation+5.53e+00

Pos logit contributions
Ready+0.074
Left+0.066
 bust+0.064
alis+0.064
sc+0.063
Neg logit contributions
lee-0.053
atted-0.051
 impressed-0.048
omo-0.046
ummies-0.046
Token she
Token ID673
Feature activation-1.52e+00

Pos logit contributions
omo+0.224
lee+0.216
atted+0.216
 impressed+0.195
asured+0.179
Neg logit contributions
Ready-0.193
Left-0.173
br-0.157
 bust-0.151
sc-0.149
Token would
Token ID561
Feature activation-1.42e+00

Pos logit contributions
Ready+0.053
Left+0.045
alis+0.041
sc+0.041
 bust+0.039
Neg logit contributions
lee-0.068
atted-0.068
 impressed-0.064
omo-0.062
 smiling-0.060
Token not
Token ID407
Feature activation+7.09e-01

Pos logit contributions
Ready+0.048
Left+0.042
alis+0.037
sc+0.036
 bust+0.035
Neg logit contributions
lee-0.067
atted-0.066
 impressed-0.062
omo-0.060
 smiling-0.058
Token give
Token ID1577
Feature activation+2.24e+00

Pos logit contributions
lee+0.034
atted+0.034
 impressed+0.032
omo+0.031
 smiling+0.031
Neg logit contributions
Ready-0.023
Left-0.020
alis-0.017
sc-0.017
 bust-0.016
Token vinegar
Token ID26600
Feature activation-5.67e-01

Pos logit contributions
Ready+0.081
Left+0.070
alis+0.064
sc+0.064
ready+0.061
Neg logit contributions
lee-0.085
atted-0.084
 impressed-0.077
omo-0.073
 glad-0.071
Token was
Token ID373
Feature activation+2.16e+00

Pos logit contributions
Ready+0.020
sc+0.017
Left+0.017
alis+0.016
 am+0.016
Neg logit contributions
lee-0.024
atted-0.024
 impressed-0.022
omo-0.022
 glad-0.022
Token very
Token ID845
Feature activation+4.60e+00

Pos logit contributions
lee+0.087
atted+0.086
omo+0.072
 impressed+0.069
ica+0.066
Neg logit contributions
Ready-0.081
Left-0.073
sc-0.070
alis-0.069
 fart-0.068
Token sour
Token ID11348
Feature activation+4.13e+00

Pos logit contributions
atted+0.194
lee+0.193
pa+0.161
ica+0.160
omo+0.160
Neg logit contributions
Ready-0.152
Left-0.133
sc-0.133
 fart-0.125
 am-0.125
Token and
Token ID290
Feature activation+6.15e+00

Pos logit contributions
atted+0.138
lee+0.136
 impressed+0.126
 glad+0.118
 pleased+0.114
Neg logit contributions
Ready-0.175
sc-0.166
Left-0.157
 fart-0.156
br-0.155
Token made
Token ID925
Feature activation-2.09e+00

Pos logit contributions
atted+0.237
lee+0.234
 impressed+0.206
omo+0.194
 glad+0.189
Neg logit contributions
Ready-0.246
Left-0.212
sc-0.206
alis-0.197
 bust-0.194
Token a
Token ID257
Feature activation-1.56e+00

Pos logit contributions
Ready+0.108
Left+0.098
alis+0.092
sc+0.091
 bust+0.088
Neg logit contributions
lee-0.061
atted-0.060
 impressed-0.054
omo-0.051
 smiling-0.049
Token big
Token ID1263
Feature activation+5.17e-01

Pos logit contributions
Ready+0.068
Left+0.061
alis+0.056
sc+0.055
 bust+0.053
Neg logit contributions
lee-0.058
atted-0.058
 impressed-0.052
omo-0.050
 smiling-0.048
Token mess
Token ID2085
Feature activation-9.93e-01

Pos logit contributions
lee+0.021
atted+0.021
 impressed+0.017
 glad+0.016
omo+0.016
Neg logit contributions
Ready-0.021
Left-0.018
sc-0.017
alis-0.017
 fart-0.017
Token on
Token ID319
Feature activation-5.42e+00

Pos logit contributions
Ready+0.042
Left+0.038
sc+0.037
alis+0.035
br+0.033
Neg logit contributions
atted-0.036
lee-0.036
 impressed-0.033
omo-0.032
 glad-0.031
Token the
Token ID262
Feature activation-6.48e+00

Pos logit contributions
Ready+0.235
Left+0.210
alis+0.195
sc+0.190
 summit+0.185
Neg logit contributions
atted-0.204
lee-0.200
 impressed-0.186
omo-0.173
 glad-0.170
Token depend
Token ID4745
Feature activation+3.85e+00

Pos logit contributions
atted+0.090
lee+0.088
omo+0.078
 impressed+0.075
 mad+0.067
Neg logit contributions
Ready-0.143
Left-0.129
alis-0.123
 bust-0.118
sc-0.116
Tokenable
Token ID540
Feature activation+4.79e+00

Pos logit contributions
atted+0.146
lee+0.144
 impressed+0.134
 mad+0.126
omo+0.126
Neg logit contributions
Ready-0.166
Left-0.148
alis-0.137
sc-0.131
 summit-0.129
Token!
Token ID0
Feature activation-6.21e-01

Pos logit contributions
atted+0.190
lee+0.188
 impressed+0.171
omo+0.164
 mad+0.159
Neg logit contributions
Ready-0.195
Left-0.175
sc-0.159
alis-0.158
 bust-0.151
Token And
Token ID843
Feature activation+7.70e+00

Pos logit contributions
Ready+0.024
Left+0.021
alis+0.020
sc+0.020
 summit+0.019
Neg logit contributions
lee-0.024
atted-0.024
 impressed-0.022
 glad-0.022
omo-0.022
Token I
Token ID314
Feature activation-4.45e+00

Pos logit contributions
lee+0.305
atted+0.302
 impressed+0.291
 glad+0.277
 smiling+0.276
Neg logit contributions
Ready-0.308
Left-0.273
alis-0.255
sc-0.250
Three-0.240
Token can
Token ID460
Feature activation-3.15e+00

Pos logit contributions
Ready+0.133
Left+0.114
alis+0.100
ready+0.096
sc+0.094
Neg logit contributions
lee-0.220
atted-0.219
 impressed-0.213
 glad-0.205
omo-0.204
Token go
Token ID467
Feature activation+8.13e-01

Pos logit contributions
Ready+0.111
Left+0.095
sc+0.089
alis+0.084
ready+0.083
Neg logit contributions
lee-0.145
atted-0.138
 impressed-0.135
 smiling-0.133
 understanding-0.129
Token on
Token ID319
Feature activation-4.56e+00

Pos logit contributions
lee+0.027
atted+0.026
 impressed+0.024
 smiling+0.024
 glad+0.023
Neg logit contributions
Ready-0.039
Left-0.035
alis-0.032
ready-0.031
sc-0.031
Token adventures
Token ID17545
Feature activation-5.82e-01

Pos logit contributions
Ready+0.197
Left+0.175
alis+0.162
sc+0.159
 bust+0.153
Neg logit contributions
lee-0.173
atted-0.169
 impressed-0.158
 smiling-0.149
omo-0.147
Token whenever
Token ID8797
Feature activation-3.20e+00

Pos logit contributions
Ready+0.029
Left+0.026
alis+0.025
sc+0.024
ready+0.024
Neg logit contributions
lee-0.017
atted-0.017
 impressed-0.016
 smiling-0.015
omo-0.014
Token I
Token ID314
Feature activation-6.91e+00

Pos logit contributions
Ready+0.143
Left+0.129
alis+0.129
sc+0.128
tr+0.125
Neg logit contributions
lee-0.104
 impressed-0.097
atted-0.096
 smiling-0.095
 glad-0.093
Token his
Token ID465
Feature activation+7.21e-01

Pos logit contributions
lee+0.038
atted+0.038
 impressed+0.037
omo+0.036
 pleased+0.035
Neg logit contributions
Ready-0.034
Left-0.029
ready-0.025
 Ready-0.025
Three-0.025
Token frown
Token ID22002
Feature activation+4.47e+00

Pos logit contributions
lee+0.023
atted+0.022
omo+0.019
 impressed+0.018
anted+0.017
Neg logit contributions
Ready-0.031
 source-0.029
 same-0.029
 hunt-0.027
 rest-0.027
Token and
Token ID290
Feature activation+6.46e+00

Pos logit contributions
lee+0.128
atted+0.124
 impressed+0.114
omo+0.107
 glad+0.102
Neg logit contributions
Ready-0.226
Left-0.208
sc-0.197
alis-0.196
 bust-0.187
Token asked
Token ID1965
Feature activation+2.03e+00

Pos logit contributions
omo+0.248
atted+0.231
ummies+0.228
lee+0.226
ummy+0.218
Neg logit contributions
Ready-0.214
 make-0.186
 bust-0.186
 lead-0.186
 will-0.180
Token him
Token ID683
Feature activation+1.29e+00

Pos logit contributions
atted+0.067
lee+0.066
 impressed+0.064
omo+0.062
 pleased+0.058
Neg logit contributions
Ready-0.096
Left-0.085
 Ready-0.077
sc-0.077
ready-0.076
Token what
Token ID644
Feature activation-9.80e+00

Pos logit contributions
lee+0.047
atted+0.046
omo+0.045
 impressed+0.041
 mad+0.037
Neg logit contributions
Ready-0.053
Left-0.048
 Ready-0.043
 anywhere-0.043
 am-0.042
Token was
Token ID373
Feature activation-7.15e-01

Pos logit contributions
Ready+0.391
Left+0.340
sc+0.303
 am+0.294
alis+0.293
Neg logit contributions
atted-0.413
lee-0.412
 impressed-0.365
omo-0.356
 glad-0.342
Token wrong
Token ID2642
Feature activation-1.47e+00

Pos logit contributions
Ready+0.022
Left+0.018
alis+0.016
sc+0.016
 bust+0.015
Neg logit contributions
atted-0.036
lee-0.036
 impressed-0.034
omo-0.033
 smiling-0.032
Token.
Token ID13
Feature activation-1.02e+00

Pos logit contributions
Ready+0.036
Left+0.032
 am+0.032
sc+0.029
 Where+0.028
Neg logit contributions
atted-0.074
lee-0.072
 impressed-0.069
 glad-0.066
 pleased-0.064
Token Tim
Token ID5045
Feature activation+4.74e+00

Pos logit contributions
Ready+0.042
Left+0.036
Three+0.033
alis+0.033
sc+0.033
Neg logit contributions
atted-0.039
lee-0.037
 impressed-0.037
 glad-0.034
omo-0.034
Token told
Token ID1297
Feature activation+4.36e+00

Pos logit contributions
atted+0.166
lee+0.164
 impressed+0.151
 glad+0.150
ummies+0.149
Neg logit contributions
Ready-0.177
 will-0.166
Left-0.161
 hunt-0.156
 bust-0.154
Token sunshine
Token ID34488
Feature activation-1.77e+00

Pos logit contributions
lee+0.007
atted+0.007
 smiling+0.007
 impressed+0.006
 gigg+0.006
Neg logit contributions
Ready-0.009
Left-0.008
ready-0.007
sc-0.007
 bust-0.007
Token,
Token ID11
Feature activation+7.44e+00

Pos logit contributions
Ready+0.092
Left+0.083
alis+0.078
sc+0.077
 bust+0.075
Neg logit contributions
lee-0.052
atted-0.051
 impressed-0.046
omo-0.043
 smiling-0.041
Token excited
Token ID6568
Feature activation+7.07e+00

Pos logit contributions
lee+0.251
atted+0.251
omo+0.227
 impressed+0.204
 mad+0.197
Neg logit contributions
Ready-0.351
Left-0.314
alis-0.298
 south-0.292
sc-0.288
Token to
Token ID284
Feature activation-2.98e+00

Pos logit contributions
atted+0.260
lee+0.258
 impressed+0.244
omo+0.239
 glad+0.223
Neg logit contributions
Ready-0.302
Left-0.277
alis-0.251
sc-0.245
 bust-0.239
Token see
Token ID766
Feature activation-7.29e-01

Pos logit contributions
Ready+0.115
Left+0.097
sc+0.097
ready+0.088
alis+0.085
Neg logit contributions
lee-0.133
 smiling-0.124
atted-0.124
 impressed-0.123
 glad-0.121
Token what
Token ID644
Feature activation-9.97e+00

Pos logit contributions
Ready+0.036
Left+0.033
alis+0.031
sc+0.030
ready+0.029
Neg logit contributions
lee-0.023
atted-0.023
 impressed-0.021
 smiling-0.020
 glad-0.020
Token adventures
Token ID17545
Feature activation-1.86e+00

Pos logit contributions
Ready+0.476
Left+0.424
alis+0.402
sc+0.392
 summit+0.378
Neg logit contributions
lee-0.333
atted-0.327
 impressed-0.309
 smiling-0.286
omo-0.280
Token awaited
Token ID39576
Feature activation-4.88e+00

Pos logit contributions
Ready+0.091
Left+0.081
alis+0.077
Three+0.074
 summit+0.073
Neg logit contributions
lee-0.061
atted-0.060
 impressed-0.055
 smiling-0.053
 glad-0.050
Token her
Token ID607
Feature activation-2.36e+00

Pos logit contributions
Ready+0.294
Left+0.265
alis+0.257
ready+0.246
Three+0.246
Neg logit contributions
lee-0.107
atted-0.102
 impressed-0.087
 smiling-0.084
 mad-0.077
Token.
Token ID13
Feature activation-1.38e+00

Pos logit contributions
Ready+0.122
Left+0.108
sc+0.100
alis+0.100
Three+0.098
Neg logit contributions
lee-0.073
atted-0.071
 impressed-0.066
 smiling-0.062
 glad-0.060
Token<|endoftext|>
Token ID50256
Feature activation-7.85e+00

Pos logit contributions
Ready+0.061
Left+0.054
alis+0.051
sc+0.050
ready+0.048
Neg logit contributions
lee-0.051
atted-0.051
 impressed-0.046
 glad-0.043
omo-0.043
Token.
Token ID13
Feature activation-1.20e+00

Pos logit contributions
Ready+0.276
Left+0.249
alis+0.231
sc+0.226
 bust+0.221
Neg logit contributions
lee-0.189
atted-0.188
 impressed-0.172
omo-0.161
 smiling-0.160
Token He
Token ID679
Feature activation-2.07e+00

Pos logit contributions
Ready+0.042
Left+0.035
alis+0.031
sc+0.031
ready+0.030
Neg logit contributions
atted-0.056
lee-0.056
 impressed-0.052
omo-0.050
 smiling-0.049
Token wanted
Token ID2227
Feature activation-3.04e-01

Pos logit contributions
Ready+0.074
Left+0.060
Find+0.058
 bust+0.058
Three+0.057
Neg logit contributions
atted-0.087
 glad-0.081
lee-0.081
 mad-0.079
 impressed-0.078
Token to
Token ID284
Feature activation-3.95e+00

Pos logit contributions
Ready+0.012
Left+0.011
alis+0.010
sc+0.010
ready+0.010
Neg logit contributions
atted-0.012
lee-0.012
omo-0.011
 impressed-0.011
 mad-0.010
Token know
Token ID760
Feature activation+1.55e+00

Pos logit contributions
Ready+0.139
Left+0.123
alis+0.109
sc+0.108
 bust+0.100
Neg logit contributions
lee-0.182
atted-0.176
 impressed-0.169
 understanding-0.162
 smiling-0.161
Token what
Token ID644
Feature activation-1.01e+01

Pos logit contributions
lee+0.055
atted+0.055
omo+0.049
 impressed+0.046
 mad+0.045
Neg logit contributions
Ready-0.070
Left-0.063
sc-0.057
 south-0.057
alis-0.056
Token was
Token ID373
Feature activation-8.29e-01

Pos logit contributions
Ready+0.501
Left+0.454
alis+0.432
sc+0.415
 summit+0.407
Neg logit contributions
lee-0.309
atted-0.303
 impressed-0.285
 smiling-0.264
 understanding-0.256
Token inside
Token ID2641
Feature activation-4.63e+00

Pos logit contributions
Ready+0.036
Left+0.031
alis+0.029
sc+0.029
ready+0.027
Neg logit contributions
atted-0.032
lee-0.032
 impressed-0.029
omo-0.028
 smiling-0.027
Token it
Token ID340
Feature activation-8.21e+00

Pos logit contributions
Ready+0.189
Left+0.165
sc+0.155
 south+0.153
 summit+0.152
Neg logit contributions
atted-0.177
lee-0.171
omo-0.160
 impressed-0.158
 mad-0.142
Token,
Token ID11
Feature activation+6.82e+00

Pos logit contributions
Ready+0.460
Left+0.422
alis+0.397
sc+0.384
 bust+0.381
Neg logit contributions
lee-0.207
atted-0.200
 impressed-0.183
 smiling-0.167
 mad-0.162
Token so
Token ID523
Feature activation+2.04e+00

Pos logit contributions
atted+0.235
lee+0.232
omo+0.202
 impressed+0.201
 smiling+0.186
Neg logit contributions
Ready-0.323
Left-0.287
sc-0.267
alis-0.267
 south-0.258
Tokenenny
Token ID11870
Feature activation+6.60e+00

Pos logit contributions
atted+0.273
 impressed+0.267
 smiling+0.261
 glad+0.261
lee+0.258
Neg logit contributions
Ready-0.337
Left-0.293
sc-0.286
alis-0.273
Three-0.271
Token asked
Token ID1965
Feature activation+3.38e+00

Pos logit contributions
atted+0.247
 glad+0.230
omo+0.220
ummies+0.219
lee+0.215
Neg logit contributions
Ready-0.225
 bust-0.205
 hunt-0.198
Left-0.197
tr-0.193
Token Jack
Token ID3619
Feature activation+5.31e+00

Pos logit contributions
atted+0.114
omo+0.108
lee+0.102
 impressed+0.101
 coughing+0.092
Neg logit contributions
Ready-0.153
Left-0.135
 Ready-0.124
 Where-0.122
sc-0.120
Token,
Token ID11
Feature activation+9.05e+00

Pos logit contributions
lee+0.162
atted+0.158
omo+0.149
 impressed+0.135
 mad+0.122
Neg logit contributions
Ready-0.248
Left-0.226
alis-0.206
sc-0.206
 am-0.206
Token "
Token ID366
Feature activation-2.17e+00

Pos logit contributions
atted+0.374
lee+0.369
omo+0.334
 impressed+0.320
 mad+0.300
Neg logit contributions
Ready-0.368
Left-0.322
sc-0.280
alis-0.279
Three-0.273
TokenWhat
Token ID2061
Feature activation-9.52e+00

Pos logit contributions
Ready+0.061
Left+0.053
alis+0.050
sc+0.045
 bust+0.044
Neg logit contributions
lee-0.108
atted-0.106
 impressed-0.104
omo-0.099
 smiling-0.099
Token is
Token ID318
Feature activation-1.45e+00

Pos logit contributions
Ready+0.328
Left+0.281
alis+0.262
sc+0.249
 bust+0.238
Neg logit contributions
lee-0.435
atted-0.434
 impressed-0.418
 smiling-0.396
omo-0.395
Token that
Token ID326
Feature activation-5.24e+00

Pos logit contributions
Ready+0.068
Left+0.061
alis+0.056
sc+0.055
 bust+0.054
Neg logit contributions
lee-0.050
atted-0.050
 impressed-0.046
omo-0.043
 smiling-0.042
Token wreck
Token ID15228
Feature activation-4.13e-01

Pos logit contributions
Ready+0.248
Left+0.224
alis+0.212
sc+0.209
Skip+0.200
Neg logit contributions
 impressed-0.168
lee-0.167
atted-0.165
 mad-0.159
 smiling-0.154
Token?".
Token ID43634
Feature activation+9.81e-01

Pos logit contributions
Ready+0.021
Left+0.019
alis+0.017
sc+0.017
Three+0.017
Neg logit contributions
atted-0.013
lee-0.013
 impressed-0.012
 mad-0.011
 smiling-0.011
Token
Token ID198
Feature activation-2.71e+00

Pos logit contributions
atted+0.028
lee+0.025
 impressed+0.024
omo+0.023
 mad+0.021
Neg logit contributions
Ready-0.054
Left-0.048
alis-0.044
Three-0.044
sc-0.044
Token now
Token ID783
Feature activation+2.26e+00

Pos logit contributions
lee+0.143
atted+0.142
 impressed+0.130
omo+0.123
 smiling+0.119
Neg logit contributions
Ready-0.187
Left-0.168
alis-0.156
sc-0.154
 bust-0.148
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
lee+0.086
atted+0.086
 impressed+0.078
omo+0.076
 smiling+0.071
Neg logit contributions
Ready-0.097
Left-0.086
alis-0.079
sc-0.079
ready-0.075
Token You
Token ID921
Feature activation-2.24e+00

Pos logit contributions
Ready+0.042
Left+0.037
alis+0.034
sc+0.033
 summit+0.032
Neg logit contributions
lee-0.048
atted-0.048
 impressed-0.044
 glad-0.043
 smiling-0.042
Token must
Token ID1276
Feature activation-2.45e+00

Pos logit contributions
Ready+0.079
Left+0.068
Whe+0.062
alis+0.061
sc+0.061
Neg logit contributions
atted-0.096
lee-0.095
 impressed-0.093
 mad-0.093
 glad-0.089
Token do
Token ID466
Feature activation-2.81e+00

Pos logit contributions
Ready+0.097
Left+0.086
sc+0.081
alis+0.075
ready+0.075
Neg logit contributions
lee-0.100
atted-0.096
 impressed-0.093
 mad-0.092
 understanding-0.092
Token what
Token ID644
Feature activation-9.49e+00

Pos logit contributions
Ready+0.128
Left+0.114
alis+0.106
sc+0.106
 bust+0.101
Neg logit contributions
lee-0.101
atted-0.099
 impressed-0.094
 smiling-0.087
 mad-0.086
Token I
Token ID314
Feature activation-7.52e+00

Pos logit contributions
Ready+0.374
Left+0.328
alis+0.300
sc+0.293
 bust+0.282
Neg logit contributions
lee-0.395
atted-0.393
 impressed-0.365
omo-0.348
 smiling-0.341
Token say
Token ID910
Feature activation+1.47e+00

Pos logit contributions
Ready+0.297
Left+0.278
alis+0.258
sc+0.244
 bust+0.241
Neg logit contributions
lee-0.287
atted-0.287
 impressed-0.278
 mad-0.276
 smiling-0.267
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
lee+0.057
atted+0.057
 impressed+0.052
omo+0.051
 mad+0.048
Neg logit contributions
Ready-0.061
Left-0.054
alis-0.049
sc-0.049
ready-0.047
Token You
Token ID921
Feature activation-2.50e+00

Pos logit contributions
Ready+0.051
Left+0.044
alis+0.040
sc+0.039
 bust+0.037
Neg logit contributions
lee-0.064
atted-0.064
 impressed-0.060
omo-0.057
 smiling-0.057
Token are
Token ID389
Feature activation-9.40e-01

Pos logit contributions
Ready+0.090
Left+0.077
Whe+0.071
alis+0.071
sc+0.070
Neg logit contributions
atted-0.105
lee-0.104
 impressed-0.101
 mad-0.101
 gigg-0.097