TOP ACTIVATIONS
MAX = 30.262

grandma 's house for safe keeping . When
the animal out of the bog . The animal thanked Rose
had become trapped in the bog . Rose thought and thought
they had reached an imp asse , the strong man bow
. The k idd o understood the message ,
that she and Rain could agree . <|endoftext|> One day ,
hard - and the k idd o soon began to do
Once there was a k idd o who loved to guess
I 'm sorry , Your Majesty . I won 't do
one day , the k idd o â s
The two friends couldn 't agree . " You 're wrong
But the wife didn 't agree . She always thought that
The little girl didn 't agree . She wanted to go
. Tim my did not agree with his mom and he
The people could not agree on what to do ,
use a special sign to agree to be friends forever .
that she made her mum agree with her . From then
. " I agree ," Ben said . He
. The villagers started to agree with each other and the
the king , " Your Majesty , it has been too

MIN ACTIVATIONS
MIN = -37.391

. He pulls and twists the hose . He sees a
works ! We can turn the screw with this screw driver
. We have to save the world from bad guys ."
to fight . They pull the book from each other .
to pick good things from the refrigerator ." S
runs to them and grabs the ball . He says ,
and pulls . She opens the barrel . Tim comes out
happy . They forgot about the balloon . They
. They let go of the tire . It rolls fast
Let 's take turns wearing the sweater ," L ila said
not jump as high as the others . One
okay to not always win the game . <|endoftext|> Once upon
time to go home as the woods could be dangerous .
and dots . They mixed the colors and made new ones
sorry , but he lost the book . He says he
, they would go to the open barn and take a
: " Give me the cup !" Jack wanted
lick and nib ble of the sweet treat . Rachel was
They take turns to pull the string and watch the rocket
while , pretending to fly the airplane and having lots of

INTERVAL 13.349 - 30.262
CONTAINS 5.737%

something . It was a flame ! He thought it was
. He brings his favorite car , a red one with
decided to test out its tail again . This time it
crazy things ! There were bats , balls , and silly
saw the blood and the onion juice . He cried too

INTERVAL -3.564 - 13.349
CONTAINS 63.889%

all so scared , but they knew they had to work
mad if we go ," Tom said . Sam
to be careful and he should never try to do something
yellow ball and shouted , " Look ! What is that
felt a warm breeze around it . It was the wind

INTERVAL -20.478 - -3.564
CONTAINS 26.276%

she could run , and how loud she could scream .
princess could not resist playing with it . The original light
and said , " What a nice dinosaur ."
with his family and played with his baby sister . Tim
His mum came to him and said softly ,

INTERVAL -37.391 - -20.478
CONTAINS 4.099%

Whenever the elderly man watched the sunset from that day on
up to the top of the tank . He told the
. She followed Tom to the table . Tom
She loved playing outside in the mud and dirt . One
bikes . They run to the box and grab a bike
Token grandma
Token ID49890
Feature activation+1.16e+01

Pos logit contributions
 your+0.328
 my+0.318
 new+0.279
 our+0.278
 same+0.273
Neg logit contributions
oped-0.523
owing-0.509
oled-0.494
oling-0.485
aring-0.476
Token's
Token ID338
Feature activation-1.30e+01

Pos logit contributions
oped+0.325
owing+0.308
oled+0.303
umbled+0.302
amb+0.299
Neg logit contributions
 your-0.267
 my-0.258
 our-0.228
 new-0.225
 the-0.224
Token house
Token ID2156
Feature activation+1.77e+01

Pos logit contributions
 your+0.249
 my+0.238
 new+0.224
 big+0.217
 same+0.216
Neg logit contributions
oped-0.431
owing-0.409
oled-0.402
oling-0.399
unch-0.393
Token for
Token ID329
Feature activation-8.94e+00

Pos logit contributions
oped+0.508
owing+0.486
oled+0.472
oling+0.468
amb+0.468
Neg logit contributions
 your-0.390
 my-0.376
 our-0.329
 new-0.329
 same-0.325
Token safe
Token ID3338
Feature activation+7.15e+00

Pos logit contributions
 your+0.120
 my+0.114
 our+0.091
 same+0.087
 new+0.086
Neg logit contributions
oped-0.333
owing-0.327
oled-0.315
oling-0.312
aring-0.311
Tokenkeeping
Token ID19934
Feature activation+3.03e+01

Pos logit contributions
oped+0.157
owing+0.145
oled+0.140
oling+0.139
unch+0.139
Neg logit contributions
 your-0.214
 my-0.207
 our-0.190
 the-0.188
 new-0.186
Token.
Token ID13
Feature activation+8.80e+00

Pos logit contributions
oped+0.863
ipt+0.823
eled+0.816
idd+0.802
anged+0.801
Neg logit contributions
 your-0.684
 my-0.629
 the-0.587
 our-0.565
 big-0.564
Token
Token ID220
Feature activation+1.32e+01

Pos logit contributions
owing+0.256
oped+0.249
oled+0.232
edly+0.232
oling+0.231
Neg logit contributions
 your-0.208
 my-0.203
 the-0.178
 new-0.175
 our-0.174
Token
Token ID198
Feature activation+3.20e+00

Pos logit contributions
owing+0.422
edly+0.416
oped+0.408
eled+0.403
anged+0.398
Neg logit contributions
 your-0.262
 my-0.242
 the-0.215
 new-0.213
 our-0.209
Token
Token ID198
Feature activation+3.36e+00

Pos logit contributions
owing+0.098
oped+0.093
anged+0.091
ement+0.089
edly+0.088
Neg logit contributions
 your-0.070
 my-0.067
 big-0.060
 the-0.060
 new-0.058
TokenWhen
Token ID2215
Feature activation+3.51e+00

Pos logit contributions
oped+0.090
owing+0.087
oled+0.083
oling+0.082
aring+0.081
Neg logit contributions
 your-0.081
 my-0.079
 our-0.070
 same-0.069
 new-0.068
Token the
Token ID262
Feature activation-2.10e+01

Pos logit contributions
oped+0.457
owing+0.449
oled+0.431
oling+0.427
aring+0.427
Neg logit contributions
 your-0.193
 my-0.183
 our-0.150
 same-0.144
 new-0.143
Token animal
Token ID5044
Feature activation+1.35e+01

Pos logit contributions
 your+0.444
 my+0.435
 our+0.380
 same+0.379
 new+0.373
Neg logit contributions
oped-0.632
owing-0.616
oled-0.591
amb-0.579
oling-0.577
Token out
Token ID503
Feature activation-1.53e+00

Pos logit contributions
oped+0.391
owing+0.382
oled+0.365
oling+0.359
aring+0.358
Neg logit contributions
 your-0.288
 my-0.278
 our-0.243
 same-0.238
 new-0.236
Token of
Token ID286
Feature activation-1.32e+01

Pos logit contributions
 your+0.036
 my+0.035
 our+0.031
 same+0.031
 new+0.031
Neg logit contributions
oped-0.041
owing-0.040
oled-0.038
oling-0.037
aring-0.037
Token the
Token ID262
Feature activation-2.09e+01

Pos logit contributions
 your+0.108
 my+0.097
 same+0.079
 our+0.067
 new+0.066
Neg logit contributions
oped-0.503
owing-0.483
eled-0.482
idd-0.475
oled-0.474
Token bog
Token ID22922
Feature activation+3.00e+01

Pos logit contributions
 your+0.457
 my+0.436
 our+0.387
 same+0.370
 new+0.368
Neg logit contributions
oped-0.579
owing-0.570
oling-0.537
oled-0.534
aring-0.534
Token.
Token ID13
Feature activation+9.94e+00

Pos logit contributions
oped+0.906
oled+0.858
eled+0.848
ement+0.841
unch+0.828
Neg logit contributions
 your-0.584
 the-0.550
 my-0.546
 big-0.524
 our-0.510
Token The
Token ID383
Feature activation-1.02e+01

Pos logit contributions
owing+0.292
oped+0.284
eled+0.269
anged+0.267
aring+0.265
Neg logit contributions
 your-0.218
 my-0.211
 the-0.182
 new-0.179
 our-0.178
Token animal
Token ID5044
Feature activation+1.36e+01

Pos logit contributions
 your+0.199
 my+0.198
 same+0.178
 new+0.176
 big+0.175
Neg logit contributions
oped-0.330
owing-0.319
oled-0.307
uts-0.303
amb-0.301
Token thanked
Token ID26280
Feature activation+7.75e+00

Pos logit contributions
oped+0.387
owing+0.387
amb+0.369
oled+0.367
oling+0.363
Neg logit contributions
 your-0.290
 my-0.284
 big-0.257
 new-0.254
 the-0.251
Token Rose
Token ID8049
Feature activation+1.09e+01

Pos logit contributions
oped+0.279
owing+0.273
oled+0.267
oling+0.261
aring+0.260
Neg logit contributions
 your-0.104
 my-0.099
 our-0.081
 same-0.079
 new-0.075
Token had
Token ID550
Feature activation-1.12e+00

Pos logit contributions
 your+0.090
 my+0.087
 our+0.078
 same+0.076
 new+0.075
Neg logit contributions
oped-0.102
owing-0.098
oled-0.094
oling-0.092
aring-0.092
Token become
Token ID1716
Feature activation-4.98e+00

Pos logit contributions
 your+0.022
 my+0.020
 our+0.018
 same+0.017
 new+0.017
Neg logit contributions
oped-0.033
owing-0.032
oled-0.031
uts-0.031
umbled-0.030
Token trapped
Token ID13640
Feature activation+9.42e+00

Pos logit contributions
 your+0.073
 my+0.069
 our+0.057
 same+0.056
 new+0.053
Neg logit contributions
oped-0.174
owing-0.172
oled-0.165
oling-0.163
idd-0.162
Token in
Token ID287
Feature activation-1.34e+01

Pos logit contributions
oped+0.246
owing+0.240
oled+0.228
oling+0.224
aring+0.223
Neg logit contributions
 your-0.228
 my-0.222
 our-0.198
 same-0.194
 new-0.192
Token the
Token ID262
Feature activation-2.17e+01

Pos logit contributions
 your+0.107
 my+0.096
 same+0.066
 our+0.064
 new+0.060
Neg logit contributions
oped-0.543
owing-0.533
oled-0.519
idd-0.512
oling-0.512
Token bog
Token ID22922
Feature activation+2.98e+01

Pos logit contributions
 your+0.432
 my+0.416
 our+0.361
 same+0.350
 new+0.347
Neg logit contributions
oped-0.663
owing-0.649
oled-0.620
oling-0.613
aring-0.610
Token.
Token ID13
Feature activation+9.20e+00

Pos logit contributions
oped+0.885
oled+0.816
eled+0.815
ement+0.799
unch+0.790
Neg logit contributions
 your-0.627
 my-0.596
 the-0.565
 big-0.546
 same-0.539
Token Rose
Token ID8049
Feature activation+1.07e+01

Pos logit contributions
owing+0.271
oped+0.266
anged+0.249
eled+0.249
idd+0.247
Neg logit contributions
 your-0.206
 my-0.203
 new-0.171
 the-0.170
 our-0.170
Token thought
Token ID1807
Feature activation+1.60e+01

Pos logit contributions
owing+0.324
oped+0.314
unch+0.311
anged+0.304
oot+0.302
Neg logit contributions
 your-0.212
 my-0.211
 big-0.190
 the-0.189
 our-0.176
Token and
Token ID290
Feature activation-3.34e+00

Pos logit contributions
oped+0.400
owing+0.394
oled+0.380
oot+0.374
aring+0.371
Neg logit contributions
 my-0.357
 your-0.353
 same-0.327
 our-0.322
 new-0.288
Token thought
Token ID1807
Feature activation+1.59e+01

Pos logit contributions
 your+0.082
 my+0.080
 the+0.076
 new+0.068
 big+0.068
Neg logit contributions
owing-0.092
oped-0.091
unch-0.086
oling-0.086
aring-0.085
Token they
Token ID484
Feature activation-7.78e-01

Pos logit contributions
oped+0.396
owing+0.377
oled+0.371
aring+0.365
oot+0.361
Neg logit contributions
 your-0.328
 my-0.327
 same-0.292
 our-0.282
 new-0.261
Token had
Token ID550
Feature activation-2.15e+00

Pos logit contributions
 your+0.018
 my+0.018
 big+0.017
 the+0.016
 same+0.016
Neg logit contributions
owing-0.020
oped-0.020
unch-0.019
amb-0.019
aring-0.019
Token reached
Token ID4251
Feature activation+2.12e+00

Pos logit contributions
 your+0.047
 my+0.046
 our+0.040
 same+0.039
 new+0.039
Neg logit contributions
oped-0.058
owing-0.057
oled-0.054
anged-0.054
aring-0.053
Token an
Token ID281
Feature activation-1.47e+01

Pos logit contributions
owing+0.072
ks+0.070
anged+0.070
oped+0.070
ocular+0.067
Neg logit contributions
 my-0.019
 your-0.019
 same-0.015
 sunny-0.014
 fake-0.012
Token imp
Token ID848
Feature activation+1.23e+01

Pos logit contributions
 your+0.265
 my+0.246
 our+0.218
 new+0.197
 same+0.196
Neg logit contributions
owing-0.449
oped-0.426
aring-0.425
anged-0.424
eled-0.421
Tokenasse
Token ID21612
Feature activation+2.97e+01

Pos logit contributions
oped+0.233
owing+0.223
oled+0.208
oling+0.202
anged+0.201
Neg logit contributions
 your-0.390
 my-0.383
 our-0.348
 same-0.348
 new-0.344
Token,
Token ID11
Feature activation+3.10e-01

Pos logit contributions
eled+0.606
edly+0.598
ipt+0.580
unch+0.570
ement+0.569
Neg logit contributions
 your-0.811
 my-0.774
 the-0.759
 our-0.702
 big-0.699
Token the
Token ID262
Feature activation-2.19e+01

Pos logit contributions
oped+0.011
owing+0.011
oled+0.010
oling+0.010
aring+0.010
Neg logit contributions
 your-0.005
 my-0.005
 our-0.004
 new-0.004
 same-0.004
Token strong
Token ID1913
Feature activation+4.00e+00

Pos logit contributions
 your+0.425
 my+0.406
 our+0.353
 same+0.332
 new+0.329
Neg logit contributions
oped-0.674
owing-0.658
oled-0.635
oling-0.625
aring-0.625
Token man
Token ID582
Feature activation+1.78e+01

Pos logit contributions
oped+0.112
owing+0.109
oled+0.105
anged+0.104
aring+0.104
Neg logit contributions
 your-0.087
 my-0.083
 our-0.075
 same-0.070
 new-0.069
Token bow
Token ID9563
Feature activation+1.93e+01

Pos logit contributions
unch+0.494
amb+0.491
owing+0.491
oped+0.485
ipt+0.484
Neg logit contributions
 your-0.362
 my-0.355
 the-0.350
 big-0.332
 new-0.313
Token.
Token ID13
Feature activation+9.41e+00

Pos logit contributions
oped+0.400
owing+0.393
oled+0.373
oling+0.364
aring+0.363
Neg logit contributions
 your-0.324
 my-0.321
 same-0.287
 our-0.277
 big-0.267
Token
Token ID198
Feature activation+3.67e+00

Pos logit contributions
owing+0.280
oped+0.271
eled+0.252
oot+0.251
anged+0.250
Neg logit contributions
 your-0.210
 my-0.203
 the-0.183
 our-0.175
 new-0.172
Token
Token ID198
Feature activation+3.81e+00

Pos logit contributions
owing+0.126
ked+0.119
anged+0.118
ocular+0.116
oped+0.115
Neg logit contributions
 your-0.068
 my-0.062
 the-0.060
 big-0.060
 new-0.057
TokenThe
Token ID464
Feature activation-1.19e+01

Pos logit contributions
owing+0.116
oped+0.113
anged+0.109
ocular+0.106
oled+0.106
Neg logit contributions
 your-0.079
 my-0.076
 our-0.066
 big-0.065
 new-0.063
Token k
Token ID479
Feature activation+9.30e+00

Pos logit contributions
 your+0.221
 my+0.217
 new+0.188
 same+0.188
 big+0.188
Neg logit contributions
oped-0.390
owing-0.384
oled-0.363
oling-0.360
amb-0.358
Tokenidd
Token ID1638
Feature activation+2.91e+01

Pos logit contributions
owing+0.111
edly+0.110
oled+0.107
uts+0.100
istent+0.100
Neg logit contributions
 your-0.333
 my-0.330
 our-0.294
 new-0.290
 the-0.289
Tokeno
Token ID78
Feature activation+1.36e+01

Pos logit contributions
ement+0.408
oling+0.406
oled+0.400
unch+0.396
oped+0.395
Neg logit contributions
 your-0.928
 my-0.919
 same-0.862
 the-0.858
 big-0.847
Token understood
Token ID7247
Feature activation+8.47e+00

Pos logit contributions
owing+0.392
oped+0.388
unch+0.376
oled+0.376
oling+0.372
Neg logit contributions
 your-0.277
 my-0.276
 the-0.244
 big-0.243
 same-0.237
Token the
Token ID262
Feature activation-2.05e+01

Pos logit contributions
oped+0.232
owing+0.230
oled+0.217
aring+0.215
oling+0.213
Neg logit contributions
 your-0.187
 my-0.183
 same-0.162
 our-0.160
 new-0.155
Token message
Token ID3275
Feature activation+2.16e+01

Pos logit contributions
 your+0.373
 my+0.359
 same+0.306
 our+0.304
 new+0.303
Neg logit contributions
oped-0.671
owing-0.654
oled-0.627
oling-0.620
anged-0.617
Token,
Token ID11
Feature activation+1.59e+00

Pos logit contributions
oped+0.602
owing+0.592
oled+0.560
aring+0.553
oling+0.549
Neg logit contributions
 your-0.479
 my-0.465
 our-0.410
 same-0.398
 new-0.390
Token that
Token ID326
Feature activation-2.08e+00

Pos logit contributions
oped+0.254
owing+0.247
oled+0.238
oling+0.236
idd+0.233
Neg logit contributions
 your-0.142
 my-0.137
 our-0.115
 new-0.113
 the-0.111
Token she
Token ID673
Feature activation+2.32e+00

Pos logit contributions
 your+0.038
 my+0.037
 our+0.031
 same+0.031
 new+0.030
Neg logit contributions
oped-0.067
owing-0.066
oled-0.063
oling-0.062
aring-0.062
Token and
Token ID290
Feature activation-1.48e+00

Pos logit contributions
oped+0.063
owing+0.062
oled+0.059
oling+0.058
aring+0.058
Neg logit contributions
 your-0.054
 my-0.053
 our-0.046
 same-0.045
 new-0.045
Token Rain
Token ID10301
Feature activation+1.93e+01

Pos logit contributions
 your+0.024
 my+0.023
 our+0.020
 same+0.019
 new+0.019
Neg logit contributions
oped-0.050
owing-0.049
oled-0.047
oling-0.047
aring-0.047
Token could
Token ID714
Feature activation+4.72e+00

Pos logit contributions
oped+0.495
owing+0.490
unch+0.485
eled+0.473
idd+0.471
Neg logit contributions
 your-0.445
 my-0.430
 same-0.410
 the-0.401
 new-0.399
Token agree
Token ID4236
Feature activation+2.88e+01

Pos logit contributions
oped+0.150
owing+0.147
ocular+0.138
oled+0.137
amb+0.137
Neg logit contributions
 your-0.080
 my-0.078
 our-0.066
 new-0.061
 same-0.061
Token.
Token ID13
Feature activation+1.08e+01

Pos logit contributions
oped+0.881
owing+0.855
oled+0.825
oling+0.814
anged+0.810
Neg logit contributions
 your-0.596
 my-0.570
 our-0.495
 new-0.484
 same-0.476
Token<|endoftext|>
Token ID50256
Feature activation+1.25e+01

Pos logit contributions
owing+0.326
oped+0.311
anged+0.299
eled+0.296
ked+0.293
Neg logit contributions
 your-0.238
 my-0.230
 the-0.206
 new-0.193
 big-0.186
TokenOne
Token ID3198
Feature activation+5.74e+00

Pos logit contributions
owing+0.428
aring+0.414
anged+0.412
olded+0.403
oot+0.399
Neg logit contributions
 your-0.215
 the-0.208
 my-0.203
 big-0.191
 new-0.180
Token day
Token ID1110
Feature activation+1.17e+01

Pos logit contributions
owing+0.191
oped+0.190
aring+0.178
anged+0.177
unch+0.177
Neg logit contributions
 your-0.092
 my-0.088
 our-0.076
 same-0.069
 new-0.066
Token,
Token ID11
Feature activation+1.45e+00

Pos logit contributions
oped+0.344
owing+0.330
oled+0.321
oling+0.314
anged+0.311
Neg logit contributions
 your-0.243
 my-0.237
 our-0.209
 same-0.205
 new-0.201
Token hard
Token ID1327
Feature activation+4.27e+00

Pos logit contributions
oped+0.336
owing+0.328
oled+0.313
oling+0.308
aring+0.307
Neg logit contributions
 your-0.246
 my-0.238
 our-0.208
 same-0.204
 new-0.202
Token -
Token ID532
Feature activation+2.65e+00

Pos logit contributions
oped+0.113
owing+0.110
oled+0.105
oling+0.103
anged+0.102
Neg logit contributions
 your-0.102
 my-0.100
 our-0.089
 same-0.086
 new-0.085
Token and
Token ID290
Feature activation-2.68e+00

Pos logit contributions
oped+0.077
owing+0.075
oled+0.072
oling+0.071
aring+0.070
Neg logit contributions
 your-0.057
 my-0.055
 our-0.048
 same-0.047
 new-0.047
Token the
Token ID262
Feature activation-2.12e+01

Pos logit contributions
 your+0.057
 my+0.055
 our+0.048
 same+0.048
 new+0.046
Neg logit contributions
oped-0.075
owing-0.074
oled-0.070
anged-0.070
aring-0.069
Token k
Token ID479
Feature activation+8.64e+00

Pos logit contributions
 your+0.385
 my+0.371
 our+0.315
 same+0.314
 new+0.310
Neg logit contributions
oped-0.692
owing-0.678
oled-0.648
oling-0.641
amb-0.638
Tokenidd
Token ID1638
Feature activation+2.83e+01

Pos logit contributions
edly+0.109
oled+0.103
owing+0.100
rums+0.098
ously+0.096
Neg logit contributions
 your-0.306
 my-0.300
 our-0.273
 same-0.269
 big-0.269
Tokeno
Token ID78
Feature activation+1.31e+01

Pos logit contributions
unch+0.361
ement+0.358
oled+0.355
oling+0.355
oped+0.351
Neg logit contributions
 your-0.952
 my-0.932
 same-0.902
 big-0.874
 the-0.869
Token soon
Token ID2582
Feature activation+8.42e+00

Pos logit contributions
owing+0.343
oped+0.343
unch+0.331
amb+0.331
oled+0.329
Neg logit contributions
 your-0.297
 my-0.290
 same-0.258
 big-0.258
 the-0.255
Token began
Token ID2540
Feature activation+4.97e+00

Pos logit contributions
oped+0.225
owing+0.218
oled+0.208
oling+0.204
anged+0.203
Neg logit contributions
 your-0.200
 my-0.194
 our-0.173
 same-0.169
 new-0.167
Token to
Token ID284
Feature activation-1.19e+01

Pos logit contributions
oped+0.158
owing+0.155
oled+0.148
aring+0.146
anged+0.146
Neg logit contributions
 your-0.091
 my-0.088
 our-0.076
 same-0.073
 new-0.071
Token do
Token ID466
Feature activation+2.00e+00

Pos logit contributions
 your+0.192
 my+0.185
 our+0.158
 new+0.145
 same+0.144
Neg logit contributions
oped-0.400
owing-0.395
oled-0.378
oling-0.372
aring-0.371
TokenOnce
Token ID7454
Feature activation+3.94e+00

Pos logit contributions
owing+0.357
aring+0.347
anged+0.346
olded+0.335
oped+0.332
Neg logit contributions
 your-0.206
 the-0.198
 my-0.197
 big-0.185
 new-0.175
Token there
Token ID612
Feature activation+2.69e+00

Pos logit contributions
oped+0.126
owing+0.123
oled+0.118
aring+0.116
anged+0.116
Neg logit contributions
 your-0.071
 my-0.069
 our-0.059
 same-0.057
 new-0.055
Token was
Token ID373
Feature activation-4.97e+00

Pos logit contributions
oped+0.079
owing+0.077
oled+0.073
oling+0.072
aring+0.072
Neg logit contributions
 your-0.058
 my-0.056
 our-0.049
 same-0.048
 new-0.047
Token a
Token ID257
Feature activation-1.33e+01

Pos logit contributions
 your+0.054
 my+0.053
 our+0.039
 same+0.039
 new+0.036
Neg logit contributions
oped-0.181
owing-0.179
amb-0.177
unch-0.177
aw-0.175
Token k
Token ID479
Feature activation+8.30e+00

Pos logit contributions
 your+0.157
 my+0.148
 our+0.113
 new+0.111
 big+0.111
Neg logit contributions
oped-0.518
owing-0.510
oled-0.490
anged-0.486
oling-0.483
Tokenidd
Token ID1638
Feature activation+2.83e+01

Pos logit contributions
edly+0.123
oled+0.117
ussed+0.116
owing+0.113
anged+0.112
Neg logit contributions
 your-0.298
 my-0.291
 big-0.268
 the-0.260
 our-0.260
Tokeno
Token ID78
Feature activation+1.23e+01

Pos logit contributions
ement+0.461
oped+0.453
oled+0.432
oling+0.429
eled+0.411
Neg logit contributions
 your-0.938
 my-0.908
 big-0.851
 the-0.840
 same-0.837
Token who
Token ID508
Feature activation+2.64e+00

Pos logit contributions
oped+0.340
oled+0.323
ement+0.316
oling+0.308
uts+0.305
Neg logit contributions
 your-0.308
 my-0.288
 the-0.272
 big-0.265
 our-0.259
Token loved
Token ID6151
Feature activation+3.92e+00

Pos logit contributions
oped+0.075
owing+0.074
oled+0.070
oling+0.069
aring+0.069
Neg logit contributions
 your-0.059
 my-0.057
 our-0.050
 same-0.050
 new-0.049
Token to
Token ID284
Feature activation-1.25e+01

Pos logit contributions
owing+0.119
oped+0.118
amb+0.112
anged+0.111
unch+0.111
Neg logit contributions
 your-0.070
 my-0.069
 our-0.058
 same-0.058
 new-0.054
Token guess
Token ID4724
Feature activation+1.65e+01

Pos logit contributions
 your+0.230
 my+0.229
 our+0.203
 same+0.190
 new+0.181
Neg logit contributions
oped-0.372
owing-0.369
unch-0.353
amb-0.346
uts-0.339
TokenI
Token ID40
Feature activation+3.78e+00

Pos logit contributions
owing+0.118
oped+0.116
anged+0.110
oled+0.109
oling+0.107
Neg logit contributions
 your-0.109
 my-0.107
 same-0.094
 our-0.092
 the-0.091
Token'm
Token ID1101
Feature activation-2.55e+00

Pos logit contributions
oped+0.110
owing+0.108
oled+0.104
oling+0.104
edly+0.103
Neg logit contributions
 your-0.082
 my-0.078
 our-0.069
 big-0.067
 same-0.066
Token sorry
Token ID7926
Feature activation+1.53e+01

Pos logit contributions
 your+0.066
 my+0.064
 same+0.060
 our+0.058
 new+0.058
Neg logit contributions
oped-0.057
owing-0.057
oled-0.053
idd-0.053
oling-0.053
Token,
Token ID11
Feature activation+8.31e-01

Pos logit contributions
oped+0.460
owing+0.449
oled+0.429
oling+0.423
aring+0.421
Neg logit contributions
 your-0.316
 my-0.305
 our-0.265
 same-0.259
 new-0.257
Token Your
Token ID3406
Feature activation-8.81e+00

Pos logit contributions
oped+0.024
owing+0.023
oled+0.022
aring+0.022
oling+0.022
Neg logit contributions
 your-0.017
 my-0.016
 our-0.015
 same-0.015
 new-0.014
Token Majesty
Token ID25788
Feature activation+2.83e+01

Pos logit contributions
 your+0.187
 my+0.181
 our+0.159
 new+0.157
 big+0.156
Neg logit contributions
oped-0.267
owing-0.259
oled-0.249
oling-0.245
anged-0.244
Token.
Token ID13
Feature activation+9.40e+00

Pos logit contributions
oped+0.850
eled+0.806
anged+0.795
amb+0.788
ipt+0.778
Neg logit contributions
 your-0.633
 my-0.617
 the-0.536
 new-0.528
 our-0.526
Token I
Token ID314
Feature activation+4.08e+00

Pos logit contributions
oped+0.301
owing+0.299
oled+0.282
anged+0.281
eled+0.279
Neg logit contributions
 your-0.187
 my-0.184
 our-0.152
 the-0.140
 same-0.139
Token won
Token ID1839
Feature activation+1.26e+01

Pos logit contributions
oped+0.114
owing+0.113
oled+0.108
oling+0.108
edly+0.106
Neg logit contributions
 your-0.091
 my-0.087
 our-0.077
 big-0.076
 same-0.075
Token't
Token ID470
Feature activation-1.78e-01

Pos logit contributions
oped+0.353
owing+0.344
oled+0.330
oling+0.325
aring+0.323
Neg logit contributions
 your-0.282
 my-0.272
 our-0.240
 same-0.237
 new-0.235
Token do
Token ID466
Feature activation+1.46e+00

Pos logit contributions
 your+0.003
 my+0.003
 our+0.002
 same+0.002
 new+0.002
Neg logit contributions
oped-0.006
owing-0.006
oled-0.006
oling-0.006
aring-0.006
Token one
Token ID530
Feature activation-1.28e-01

Pos logit contributions
oped+0.180
owing+0.171
anged+0.167
oled+0.165
idd+0.163
Neg logit contributions
 your-0.100
 my-0.098
 same-0.084
 our-0.081
 new-0.080
Token day
Token ID1110
Feature activation+9.99e+00

Pos logit contributions
 your+0.002
 my+0.002
 our+0.002
 same+0.002
 new+0.002
Neg logit contributions
oped-0.004
owing-0.004
oled-0.004
oling-0.004
amb-0.004
Token,
Token ID11
Feature activation+1.34e-01

Pos logit contributions
oped+0.304
owing+0.292
oled+0.284
anged+0.278
oling+0.277
Neg logit contributions
 your-0.198
 my-0.193
 our-0.165
 same-0.165
 new-0.158
Token the
Token ID262
Feature activation-2.18e+01

Pos logit contributions
oped+0.005
owing+0.004
oled+0.004
oling+0.004
anged+0.004
Neg logit contributions
 your-0.002
 my-0.002
 same-0.002
 our-0.002
 new-0.002
Token k
Token ID479
Feature activation+8.30e+00

Pos logit contributions
 your+0.399
 my+0.396
 big+0.352
 same+0.351
 new+0.350
Neg logit contributions
oped-0.726
owing-0.718
oled-0.677
aring-0.671
anged-0.671
Tokenidd
Token ID1638
Feature activation+2.81e+01

Pos logit contributions
edly+0.109
owing+0.106
oled+0.104
ously+0.104
rums+0.103
Neg logit contributions
 your-0.285
 my-0.283
 our-0.254
 big-0.253
 new-0.250
Tokeno
Token ID78
Feature activation+1.26e+01

Pos logit contributions
ement+0.384
oling+0.344
unch+0.342
oped+0.338
oled+0.333
Neg logit contributions
 your-0.935
 my-0.922
 same-0.887
 big-0.868
 the-0.859
Tokenâ
Token ID22940
Feature activation+5.90e+00

Pos logit contributions
owing+0.349
oped+0.342
amb+0.331
unch+0.330
oled+0.327
Neg logit contributions
 your-0.271
 my-0.266
 big-0.240
 same-0.234
 the-0.234
Token
Token ID26391
Feature activation+4.09e+00

Pos logit contributions
oped+0.152
owing+0.147
oled+0.141
oling+0.138
aring+0.136
Neg logit contributions
 your-0.147
 my-0.144
 our-0.127
 same-0.127
 new-0.122
Token
Token ID8151
Feature activation+2.13e+01

Pos logit contributions
eled+0.081
edly+0.078
owing+0.076
amb+0.074
ement+0.073
Neg logit contributions
 your-0.120
 my-0.115
 big-0.112
 the-0.110
 our-0.108
Tokens
Token ID82
Feature activation-7.15e+00

Pos logit contributions
edly+0.446
owing+0.429
amb+0.422
eled+0.412
anged+0.411
Neg logit contributions
 your-0.599
 my-0.575
 the-0.548
 big-0.544
 new-0.530
TokenThe
Token ID464
Feature activation-1.23e+01

Pos logit contributions
oped+0.096
owing+0.096
anged+0.089
oled+0.089
oling+0.087
Neg logit contributions
 your-0.096
 my-0.094
 our-0.084
 big-0.082
 same-0.081
Token two
Token ID734
Feature activation+1.80e+00

Pos logit contributions
 your+0.213
 my+0.206
 same+0.175
 our+0.174
 new+0.173
Neg logit contributions
oped-0.420
owing-0.411
oled-0.394
oling-0.389
anged-0.388
Token friends
Token ID2460
Feature activation+1.59e+01

Pos logit contributions
oped+0.051
owing+0.050
oled+0.048
oling+0.047
amb+0.047
Neg logit contributions
 your-0.040
 my-0.039
 our-0.034
 new-0.034
 same-0.034
Token couldn
Token ID3521
Feature activation+5.80e+00

Pos logit contributions
owing+0.422
oped+0.422
unch+0.421
uts+0.417
oling+0.417
Neg logit contributions
 your-0.353
 my-0.336
 the-0.333
 big-0.312
 our-0.306
Token't
Token ID470
Feature activation+4.52e-01

Pos logit contributions
oped+0.158
owing+0.153
oled+0.146
oling+0.144
aring+0.143
Neg logit contributions
 your-0.134
 my-0.130
 our-0.115
 same-0.114
 new-0.112
Token agree
Token ID4236
Feature activation+2.77e+01

Pos logit contributions
oped+0.014
owing+0.013
oled+0.013
idd+0.013
umbled+0.013
Neg logit contributions
 your-0.009
 my-0.009
 our-0.008
 big-0.008
 same-0.008
Token.
Token ID13
Feature activation+9.74e+00

Pos logit contributions
oped+0.744
owing+0.736
oled+0.692
aring+0.684
oling+0.680
Neg logit contributions
 your-0.640
 my-0.625
 our-0.549
 same-0.547
 new-0.533
Token "
Token ID366
Feature activation+4.60e+00

Pos logit contributions
oped+0.284
owing+0.279
unch+0.264
idd+0.261
oot+0.261
Neg logit contributions
 your-0.218
 my-0.213
 our-0.192
 same-0.189
 the-0.186
TokenYou
Token ID1639
Feature activation+8.25e+00

Pos logit contributions
owing+0.129
oped+0.123
oot+0.118
unch+0.117
anged+0.117
Neg logit contributions
 your-0.107
 my-0.104
 our-0.094
 same-0.093
 the-0.090
Token're
Token ID821
Feature activation-1.58e+00

Pos logit contributions
oped+0.222
owing+0.216
oled+0.206
oling+0.204
anged+0.202
Neg logit contributions
 your-0.197
 my-0.192
 our-0.171
 same-0.167
 big-0.165
Token wrong
Token ID2642
Feature activation+5.06e+00

Pos logit contributions
 your+0.031
 my+0.030
 same+0.027
 new+0.027
 big+0.026
Neg logit contributions
owing-0.042
aring-0.040
idd-0.039
oped-0.039
oling-0.039
Token But
Token ID887
Feature activation+7.10e+00

Pos logit contributions
owing+0.287
oped+0.281
oled+0.262
anged+0.261
edly+0.258
Neg logit contributions
 your-0.195
 my-0.188
 the-0.169
 new-0.168
 our-0.166
Token the
Token ID262
Feature activation-2.13e+01

Pos logit contributions
oped+0.204
owing+0.204
anged+0.197
eled+0.195
amb+0.194
Neg logit contributions
 your-0.125
 my-0.123
 same-0.111
 big-0.110
 new-0.109
Token wife
Token ID3656
Feature activation+1.65e+01

Pos logit contributions
 your+0.598
 my+0.584
 our+0.528
 same+0.475
 new+0.468
Neg logit contributions
owing-0.417
aw-0.398
eled-0.397
ocular-0.395
edly-0.393
Token didn
Token ID1422
Feature activation+7.81e+00

Pos logit contributions
oped+0.501
owing+0.488
oled+0.474
oling+0.470
unch+0.465
Neg logit contributions
 your-0.333
 my-0.318
 the-0.278
 big-0.277
 same-0.275
Token't
Token ID470
Feature activation+3.30e-01

Pos logit contributions
oped+0.165
uts+0.160
oled+0.154
unch+0.153
oling+0.149
Neg logit contributions
 your-0.215
 my-0.209
 our-0.193
 same-0.191
 new-0.190
Token agree
Token ID4236
Feature activation+2.76e+01

Pos logit contributions
owing+0.009
oped+0.009
aring+0.009
oled+0.009
oling+0.009
Neg logit contributions
 your-0.007
 my-0.007
 our-0.006
 new-0.006
 same-0.006
Token.
Token ID13
Feature activation+9.22e+00

Pos logit contributions
oped+0.782
owing+0.774
oled+0.732
oling+0.721
aring+0.720
Neg logit contributions
 your-0.594
 my-0.579
 our-0.510
 same-0.503
 new-0.490
Token She
Token ID1375
Feature activation+3.47e+00

Pos logit contributions
oped+0.315
owing+0.313
oot+0.293
anged+0.291
eled+0.290
Neg logit contributions
 your-0.170
 my-0.164
 the-0.151
 new-0.147
 same-0.143
Token always
Token ID1464
Feature activation+1.38e+00

Pos logit contributions
owing+0.098
oped+0.098
oled+0.094
aring+0.093
oling+0.092
Neg logit contributions
 your-0.075
 my-0.073
 big-0.066
 the-0.065
 same-0.064
Token thought
Token ID1807
Feature activation+1.57e+01

Pos logit contributions
oped+0.036
owing+0.035
oled+0.033
oling+0.033
amb+0.033
Neg logit contributions
 your-0.035
 my-0.033
 our-0.030
 same-0.029
 new-0.029
Token that
Token ID326
Feature activation-3.92e+00

Pos logit contributions
uts+0.404
owing+0.404
ement+0.397
oled+0.396
unch+0.395
Neg logit contributions
 my-0.297
 your-0.295
 same-0.285
 our-0.264
 common-0.234
TokenThe
Token ID464
Feature activation-1.25e+01

Pos logit contributions
oped+0.078
owing+0.073
oled+0.073
aring+0.072
oling+0.071
Neg logit contributions
 your-0.089
 my-0.087
 our-0.078
 same-0.077
 new-0.076
Token little
Token ID1310
Feature activation+9.82e-01

Pos logit contributions
 your+0.125
 my+0.117
 new+0.084
 same+0.084
 big+0.083
Neg logit contributions
oped-0.516
owing-0.507
oled-0.489
oling-0.486
anged-0.483
Token girl
Token ID2576
Feature activation+1.21e+01

Pos logit contributions
oped+0.027
owing+0.027
amb+0.025
anged+0.025
oled+0.025
Neg logit contributions
 your-0.021
 my-0.021
 our-0.019
 same-0.017
 new-0.017
Token didn
Token ID1422
Feature activation+7.64e+00

Pos logit contributions
oped+0.355
owing+0.348
oled+0.346
oling+0.343
unch+0.338
Neg logit contributions
 your-0.249
 my-0.238
 the-0.217
 big-0.214
 same-0.209
Token't
Token ID470
Feature activation+2.65e-01

Pos logit contributions
oped+0.175
uts+0.169
oled+0.163
owing+0.162
unch+0.162
Neg logit contributions
 your-0.198
 my-0.193
 same-0.177
 our-0.174
 new-0.172
Token agree
Token ID4236
Feature activation+2.75e+01

Pos logit contributions
oped+0.007
owing+0.007
oled+0.007
oling+0.007
anged+0.007
Neg logit contributions
 your-0.006
 my-0.006
 our-0.005
 same-0.005
 new-0.005
Token.
Token ID13
Feature activation+9.21e+00

Pos logit contributions
oped+0.753
owing+0.693
oled+0.683
amb+0.674
oling+0.671
Neg logit contributions
 your-0.691
 my-0.661
 the-0.593
 our-0.589
 new-0.587
Token She
Token ID1375
Feature activation+3.38e+00

Pos logit contributions
oped+0.273
owing+0.259
oled+0.251
oling+0.248
idd+0.247
Neg logit contributions
 your-0.204
 my-0.199
 same-0.178
 new-0.172
 big-0.170
Token wanted
Token ID2227
Feature activation+1.07e+01

Pos logit contributions
owing+0.096
oped+0.095
oled+0.094
unch+0.093
oling+0.092
Neg logit contributions
 your-0.072
 my-0.070
 big-0.067
 the-0.065
 same-0.063
Token to
Token ID284
Feature activation-1.24e+01

Pos logit contributions
ocular+0.236
owing+0.236
anged+0.224
uts+0.223
ents+0.220
Neg logit contributions
 my-0.220
 your-0.217
 same-0.204
 our-0.197
 task-0.185
Token go
Token ID467
Feature activation+3.79e+00

Pos logit contributions
 your+0.208
 my+0.201
 new+0.171
 our+0.170
 same+0.169
Neg logit contributions
owing-0.380
oped-0.376
amb-0.366
ocular-0.355
oot-0.354
Token.
Token ID13
Feature activation+9.24e+00

Pos logit contributions
oped+0.280
owing+0.264
oled+0.257
oling+0.253
amb+0.250
Neg logit contributions
 your-0.269
 my-0.261
 our-0.230
 big-0.227
 same-0.227
Token Tim
Token ID5045
Feature activation+6.88e+00

Pos logit contributions
owing+0.258
oped+0.258
oled+0.239
aring+0.237
anged+0.236
Neg logit contributions
 your-0.215
 my-0.208
 our-0.182
 new-0.181
 the-0.180
Tokenmy
Token ID1820
Feature activation+9.65e+00

Pos logit contributions
oped+0.172
owing+0.165
oled+0.160
oling+0.158
aring+0.155
Neg logit contributions
 your-0.179
 my-0.175
 same-0.155
 our-0.154
 new-0.151
Token did
Token ID750
Feature activation+4.62e+00

Pos logit contributions
oped+0.239
owing+0.232
oled+0.219
aring+0.216
anged+0.216
Neg logit contributions
 your-0.247
 my-0.240
 our-0.216
 same-0.211
 new-0.209
Token not
Token ID407
Feature activation-3.99e-01

Pos logit contributions
owing+0.124
oled+0.123
unch+0.122
oped+0.122
aring+0.121
Neg logit contributions
 my-0.081
 same-0.078
 your-0.077
 big-0.070
 our-0.069
Token agree
Token ID4236
Feature activation+2.75e+01

Pos logit contributions
 your+0.009
 my+0.009
 our+0.008
 new+0.007
 same+0.007
Neg logit contributions
oped-0.011
owing-0.011
oled-0.011
aring-0.010
oling-0.010
Token with
Token ID351
Feature activation-4.66e+00

Pos logit contributions
oped+0.771
owing+0.767
oled+0.729
aring+0.716
oling+0.714
Neg logit contributions
 your-0.583
 my-0.568
 our-0.508
 same-0.500
 new-0.482
Token his
Token ID465
Feature activation-1.58e+01

Pos logit contributions
 your+0.053
 my+0.049
 same+0.042
 our+0.041
 big+0.035
Neg logit contributions
owing-0.165
oped-0.165
oled-0.159
eled-0.159
anged-0.159
Token mom
Token ID1995
Feature activation+1.19e+01

Pos logit contributions
 your+0.320
 my+0.310
 new+0.274
 big+0.269
 same+0.267
Neg logit contributions
oped-0.498
owing-0.479
oled-0.461
oling-0.456
amb-0.452
Token and
Token ID290
Feature activation-3.13e+00

Pos logit contributions
oped+0.359
idd+0.336
amb+0.334
ipt+0.328
owing+0.327
Neg logit contributions
 your-0.257
 my-0.245
 the-0.225
 new-0.217
 same-0.215
Token he
Token ID339
Feature activation+1.08e+00

Pos logit contributions
 your+0.076
 my+0.075
 same+0.069
 our+0.068
 new+0.067
Neg logit contributions
oped-0.072
owing-0.071
anged-0.070
olded-0.068
oled-0.068
Token
Token ID198
Feature activation+3.40e+00

Pos logit contributions
owing+0.116
anged+0.110
oped+0.108
ked+0.108
edly+0.106
Neg logit contributions
 your-0.059
 my-0.054
 big-0.053
 the-0.053
 new-0.051
TokenThe
Token ID464
Feature activation-1.23e+01

Pos logit contributions
oped+0.112
owing+0.112
oled+0.106
anged+0.105
amb+0.104
Neg logit contributions
 your-0.061
 my-0.059
 our-0.050
 big-0.048
 same-0.048
Token people
Token ID661
Feature activation+1.05e+01

Pos logit contributions
 your+0.247
 my+0.236
 our+0.203
 same+0.187
 new+0.179
Neg logit contributions
owing-0.358
oped-0.356
aring-0.342
oled-0.340
idd-0.336
Token could
Token ID714
Feature activation+3.09e+00

Pos logit contributions
oped+0.314
uts+0.305
unch+0.304
owing+0.302
oling+0.301
Neg logit contributions
 your-0.210
 the-0.194
 my-0.193
 big-0.181
 our-0.173
Token not
Token ID407
Feature activation-1.17e-01

Pos logit contributions
oped+0.098
owing+0.097
oled+0.092
aring+0.091
amb+0.091
Neg logit contributions
 your-0.055
 my-0.054
 our-0.045
 same-0.044
 new-0.044
Token agree
Token ID4236
Feature activation+2.74e+01

Pos logit contributions
 your+0.002
 my+0.002
 our+0.002
 same+0.002
 new+0.002
Neg logit contributions
oped-0.004
owing-0.003
oled-0.003
oling-0.003
aring-0.003
Token on
Token ID319
Feature activation-9.48e+00

Pos logit contributions
oped+0.777
owing+0.757
oled+0.722
oling+0.711
aring+0.708
Neg logit contributions
 your-0.612
 my-0.592
 our-0.521
 same-0.510
 new-0.507
Token what
Token ID644
Feature activation-1.29e+00

Pos logit contributions
 your+0.183
 my+0.176
 our+0.151
 same+0.148
 new+0.146
Neg logit contributions
oped-0.296
owing-0.290
oled-0.278
oling-0.274
aring-0.273
Token to
Token ID284
Feature activation-1.21e+01

Pos logit contributions
 my+0.025
 your+0.025
 same+0.022
 our+0.021
 new+0.019
Neg logit contributions
oped-0.037
owing-0.036
aring-0.035
uts-0.035
oled-0.034
Token do
Token ID466
Feature activation+1.83e+00

Pos logit contributions
 your+0.162
 my+0.154
 our+0.123
 same+0.118
 new+0.116
Neg logit contributions
oped-0.448
owing-0.443
oled-0.425
aring-0.419
oling-0.419
Token,
Token ID11
Feature activation+8.24e-01

Pos logit contributions
oped+0.037
owing+0.037
oled+0.034
aring+0.034
uts+0.033
Neg logit contributions
 your-0.053
 my-0.052
 our-0.047
 same-0.047
 new-0.046
Token use
Token ID779
Feature activation+3.26e+00

Pos logit contributions
owing+0.111
oped+0.109
oling+0.107
oled+0.107
unch+0.106
Neg logit contributions
 your-0.085
 my-0.081
 the-0.073
 big-0.073
 same-0.073
Token a
Token ID257
Feature activation-1.27e+01

Pos logit contributions
oped+0.121
owing+0.119
anged+0.114
oled+0.114
aring+0.113
Neg logit contributions
 your-0.037
 my-0.035
 same-0.027
 new-0.025
 our-0.025
Token special
Token ID2041
Feature activation+1.67e+00

Pos logit contributions
 your+0.218
 my+0.211
 our+0.173
 same+0.168
 the+0.156
Neg logit contributions
oped-0.419
owing-0.408
oled-0.391
oling-0.386
aring-0.385
Token sign
Token ID1051
Feature activation+1.64e+01

Pos logit contributions
oped+0.048
owing+0.048
anged+0.044
aring+0.044
idd+0.044
Neg logit contributions
 your-0.033
 my-0.032
 our-0.028
 same-0.026
 the-0.025
Token to
Token ID284
Feature activation-1.23e+01

Pos logit contributions
oped+0.492
owing+0.481
oled+0.461
oling+0.454
anged+0.451
Neg logit contributions
 your-0.336
 my-0.324
 our-0.282
 same-0.275
 new-0.273
Token agree
Token ID4236
Feature activation+2.74e+01

Pos logit contributions
 your+0.210
 my+0.202
 our+0.170
 same+0.167
 new+0.164
Neg logit contributions
oped-0.406
owing-0.400
oled-0.381
aring-0.377
oling-0.377
Token to
Token ID284
Feature activation-1.23e+01

Pos logit contributions
oped+0.860
oled+0.806
owing+0.803
oling+0.794
eled+0.784
Neg logit contributions
 your-0.600
 my-0.568
 our-0.504
 the-0.486
 new-0.460
Token be
Token ID307
Feature activation-4.57e+00

Pos logit contributions
 your+0.194
 my+0.186
 same+0.155
 our+0.154
 new+0.152
Neg logit contributions
oped-0.407
owing-0.404
oled-0.383
aring-0.383
amb-0.378
Token friends
Token ID2460
Feature activation+1.53e+01

Pos logit contributions
 your+0.074
 my+0.071
 same+0.061
 our+0.059
 new+0.057
Neg logit contributions
owing-0.146
oped-0.146
aring-0.138
idd-0.137
oled-0.136
Token forever
Token ID8097
Feature activation+9.69e+00

Pos logit contributions
oped+0.451
owing+0.420
oled+0.420
anged+0.419
oling+0.412
Neg logit contributions
 your-0.361
 my-0.348
 our-0.306
 the-0.295
 new-0.293
Token.
Token ID13
Feature activation+9.17e+00

Pos logit contributions
oped+0.232
owing+0.223
oled+0.213
oling+0.208
anged+0.207
Neg logit contributions
 your-0.263
 my-0.256
 our-0.231
 same-0.225
 new-0.225
Token that
Token ID326
Feature activation-3.54e+00

Pos logit contributions
oped+0.174
owing+0.165
oled+0.160
oling+0.158
idd+0.157
Neg logit contributions
 your-0.130
 my-0.126
 new-0.112
 our-0.110
 the-0.110
Token she
Token ID673
Feature activation+9.26e-01

Pos logit contributions
 your+0.067
 my+0.066
 our+0.057
 same+0.057
 new+0.053
Neg logit contributions
oped-0.103
owing-0.101
oled-0.096
uts-0.094
aring-0.093
Token made
Token ID925
Feature activation-1.15e+00

Pos logit contributions
oped+0.024
owing+0.023
oled+0.022
oling+0.022
aring+0.022
Neg logit contributions
 your-0.023
 my-0.022
 our-0.020
 same-0.019
 new-0.019
Token her
Token ID607
Feature activation-1.37e+01

Pos logit contributions
 your+0.014
 my+0.014
 our+0.011
 same+0.011
 big+0.010
Neg logit contributions
owing-0.041
oped-0.041
oled-0.039
aring-0.039
uts-0.039
Token mum
Token ID25682
Feature activation+1.46e+01

Pos logit contributions
 your+0.270
 my+0.260
 our+0.226
 same+0.217
 new+0.211
Neg logit contributions
oped-0.415
owing-0.413
oled-0.387
anged-0.384
aring-0.384
Token agree
Token ID4236
Feature activation+2.74e+01

Pos logit contributions
oped+0.441
owing+0.430
oled+0.412
oling+0.407
aring+0.405
Neg logit contributions
 your-0.295
 my-0.285
 our-0.247
 same-0.241
 new-0.240
Token with
Token ID351
Feature activation-4.41e+00

Pos logit contributions
oped+0.737
owing+0.694
oled+0.676
anged+0.674
oling+0.672
Neg logit contributions
 your-0.680
 my-0.650
 the-0.584
 our-0.577
 new-0.572
Token her
Token ID607
Feature activation-1.37e+01

Pos logit contributions
 your+0.059
 my+0.056
 our+0.044
 same+0.043
 new+0.043
Neg logit contributions
oped-0.166
owing-0.162
oled-0.157
oling-0.155
aring-0.155
Token.
Token ID13
Feature activation+9.21e+00

Pos logit contributions
 your+0.314
 my+0.304
 new+0.285
 big+0.275
 the+0.269
Neg logit contributions
oped-0.403
owing-0.372
oled-0.368
idd-0.367
oling-0.365
Token From
Token ID3574
Feature activation-5.96e-02

Pos logit contributions
owing+0.292
oped+0.282
anged+0.271
oling+0.266
ked+0.265
Neg logit contributions
 your-0.196
 my-0.187
 the-0.171
 our-0.160
 new-0.155
Token then
Token ID788
Feature activation+7.81e+00

Pos logit contributions
 your+0.001
 my+0.001
 our+0.001
 same+0.001
 new+0.001
Neg logit contributions
oped-0.002
owing-0.001
oled-0.001
amb-0.001
oling-0.001
Token.
Token ID13
Feature activation+9.29e+00

Pos logit contributions
oped+0.411
idd+0.384
oled+0.374
owing+0.374
anged+0.372
Neg logit contributions
 your-0.255
 my-0.241
 the-0.226
 big-0.223
 new-0.220
Token
Token ID198
Feature activation+3.46e+00

Pos logit contributions
owing+0.282
oped+0.277
eled+0.262
anged+0.260
aring+0.255
Neg logit contributions
 your-0.204
 my-0.193
 new-0.171
 the-0.171
 big-0.169
Token
Token ID198
Feature activation+3.54e+00

Pos logit contributions
owing+0.118
oped+0.113
anged+0.108
edly+0.107
ked+0.106
Neg logit contributions
 your-0.073
 my-0.067
 the-0.062
 new-0.060
 big-0.060
Token"
Token ID1
Feature activation+5.21e+00

Pos logit contributions
oped+0.090
owing+0.089
oled+0.083
oling+0.082
anged+0.082
Neg logit contributions
 your-0.091
 my-0.088
 our-0.079
 same-0.077
 new-0.076
TokenI
Token ID40
Feature activation+3.83e+00

Pos logit contributions
oped+0.134
owing+0.133
oled+0.124
anged+0.122
aring+0.122
Neg logit contributions
 your-0.131
 my-0.127
 our-0.113
 same-0.112
 new-0.111
Token agree
Token ID4236
Feature activation+2.73e+01

Pos logit contributions
oped+0.112
owing+0.110
oled+0.105
oling+0.103
aring+0.103
Neg logit contributions
 your-0.082
 my-0.079
 our-0.069
 same-0.068
 new-0.067
Token,"
Token ID553
Feature activation+1.04e+01

Pos logit contributions
oped+0.789
owing+0.732
oled+0.720
umbled+0.709
eled+0.707
Neg logit contributions
 your-0.680
 my-0.660
 our-0.585
 the-0.565
 new-0.545
Token Ben
Token ID3932
Feature activation+8.59e+00

Pos logit contributions
oped+0.306
owing+0.297
oled+0.286
anged+0.282
oling+0.281
Neg logit contributions
 your-0.213
 my-0.207
 our-0.181
 same-0.179
 new-0.175
Token said
Token ID531
Feature activation+1.15e+01

Pos logit contributions
oped+0.219
owing+0.216
oled+0.197
umbled+0.196
anged+0.196
Neg logit contributions
 your-0.222
 my-0.221
 the-0.199
 big-0.196
 new-0.193
Token.
Token ID13
Feature activation+9.40e+00

Pos logit contributions
oped+0.335
idd+0.304
oled+0.304
eled+0.302
owing+0.302
Neg logit contributions
 your-0.275
 my-0.259
 the-0.246
 new-0.243
 big-0.235
Token He
Token ID679
Feature activation+4.00e+00

Pos logit contributions
owing+0.312
oped+0.301
anged+0.283
eled+0.279
amb+0.278
Neg logit contributions
 your-0.189
 my-0.185
 big-0.169
 new-0.168
 the-0.167
Token.
Token ID13
Feature activation+8.89e+00

Pos logit contributions
oped+0.103
owing+0.095
oled+0.095
idd+0.094
unch+0.093
Neg logit contributions
 your-0.098
 my-0.094
 our-0.086
 new-0.084
 the-0.083
Token The
Token ID383
Feature activation-1.12e+01

Pos logit contributions
owing+0.266
oped+0.260
anged+0.240
eled+0.240
oot+0.239
Neg logit contributions
 your-0.195
 my-0.187
 the-0.169
 our-0.164
 new-0.162
Token villagers
Token ID25263
Feature activation+1.69e+01

Pos logit contributions
 your+0.224
 my+0.217
 same+0.192
 new+0.191
 big+0.189
Neg logit contributions
oped-0.348
owing-0.338
oled-0.323
oling-0.319
anged-0.318
Token started
Token ID2067
Feature activation+4.02e+00

Pos logit contributions
oped+0.420
owing+0.413
oled+0.391
oling+0.390
aring+0.386
Neg logit contributions
 your-0.429
 my-0.414
 our-0.375
 big-0.372
 the-0.371
Token to
Token ID284
Feature activation-1.25e+01

Pos logit contributions
oped+0.126
owing+0.125
oled+0.119
anged+0.118
aring+0.117
Neg logit contributions
 your-0.072
 my-0.071
 our-0.059
 same-0.059
 new-0.056
Token agree
Token ID4236
Feature activation+2.71e+01

Pos logit contributions
 your+0.241
 my+0.234
 our+0.201
 same+0.195
 new+0.194
Neg logit contributions
oped-0.385
owing-0.379
oled-0.360
oling-0.355
aring-0.355
Token with
Token ID351
Feature activation-4.88e+00

Pos logit contributions
oped+0.795
owing+0.776
oled+0.741
oling+0.731
aring+0.727
Neg logit contributions
 your-0.575
 my-0.555
 our-0.486
 same-0.474
 new-0.472
Token each
Token ID1123
Feature activation-8.41e+00

Pos logit contributions
 your+0.067
 my+0.064
 our+0.051
 same+0.049
 new+0.048
Neg logit contributions
oped-0.178
owing-0.175
oled-0.169
oling-0.167
aring-0.166
Token other
Token ID584
Feature activation-1.54e+00

Pos logit contributions
 your+0.119
 my+0.116
 our+0.092
 same+0.085
 new+0.075
Neg logit contributions
owing-0.287
oped-0.282
oled-0.269
eled-0.268
aring-0.267
Token and
Token ID290
Feature activation-3.26e+00

Pos logit contributions
 your+0.032
 my+0.031
 our+0.027
 new+0.027
 same+0.026
Neg logit contributions
oped-0.047
owing-0.045
oled-0.043
amb-0.043
oling-0.043
Token the
Token ID262
Feature activation-2.19e+01

Pos logit contributions
 your+0.072
 my+0.070
 our+0.062
 new+0.060
 same+0.060
Neg logit contributions
oped-0.094
owing-0.091
oled-0.087
oling-0.087
amb-0.086
Token the
Token ID262
Feature activation-2.26e+01

Pos logit contributions
 your+0.232
 my+0.229
 new+0.194
 same+0.188
 big+0.188
Neg logit contributions
owing-0.379
oped-0.367
anged-0.353
ocular-0.350
eled-0.348
Token king
Token ID5822
Feature activation+1.62e+01

Pos logit contributions
 your+0.511
 my+0.491
 our+0.432
 new+0.403
 same+0.402
Neg logit contributions
owing-0.608
oped-0.604
aring-0.574
oled-0.569
ocular-0.563
Token,
Token ID11
Feature activation-1.63e-01

Pos logit contributions
oped+0.495
owing+0.477
oled+0.464
oling+0.462
amb+0.460
Neg logit contributions
 your-0.327
 my-0.314
 our-0.272
 new-0.268
 the-0.266
Token "
Token ID366
Feature activation+3.38e+00

Pos logit contributions
 your+0.003
 my+0.003
 the+0.003
 our+0.003
 new+0.003
Neg logit contributions
oped-0.005
owing-0.005
amb-0.005
anged-0.005
oled-0.005
TokenYour
Token ID7120
Feature activation-1.04e+01

Pos logit contributions
owing+0.083
oped+0.083
oled+0.078
anged+0.077
aring+0.076
Neg logit contributions
 your-0.087
 my-0.085
 our-0.075
 same-0.075
 the-0.073
Token Majesty
Token ID25788
Feature activation+2.70e+01

Pos logit contributions
 your+0.214
 my+0.208
 our+0.179
 same+0.173
 new+0.171
Neg logit contributions
oped-0.303
owing-0.301
oled-0.283
aring-0.283
anged-0.280
Token,
Token ID11
Feature activation-1.64e-01

Pos logit contributions
oped+0.841
owing+0.793
amb+0.790
anged+0.790
eled+0.785
Neg logit contributions
 your-0.557
 my-0.539
 our-0.455
 the-0.450
 new-0.443
Token it
Token ID340
Feature activation-3.82e-01

Pos logit contributions
 your+0.003
 my+0.003
 same+0.003
 new+0.003
 our+0.003
Neg logit contributions
owing-0.004
aring-0.004
oped-0.004
ocular-0.004
oled-0.004
Token has
Token ID468
Feature activation-3.13e+00

Pos logit contributions
 your+0.009
 my+0.009
 our+0.008
 new+0.008
 same+0.008
Neg logit contributions
oped-0.010
owing-0.010
aring-0.009
oled-0.009
oling-0.009
Token been
Token ID587
Feature activation-4.26e+00

Pos logit contributions
 your+0.055
 my+0.052
 same+0.045
 sunny+0.045
 our+0.045
Neg logit contributions
oped-0.084
owing-0.084
olded-0.082
ocular-0.082
aring-0.082
Token too
Token ID1165
Feature activation+2.77e+00

Pos logit contributions
 your+0.081
 my+0.077
 same+0.072
 our+0.067
 new+0.067
Neg logit contributions
owing-0.117
oped-0.116
idd-0.112
olded-0.110
aring-0.108
Token.
Token ID13
Feature activation-2.50e+00

Pos logit contributions
oped+0.189
owing+0.183
amb+0.180
oled+0.173
anged+0.172
Neg logit contributions
 your-0.185
 my-0.180
 big-0.163
 our-0.162
 the-0.161
Token He
Token ID679
Feature activation-7.04e+00

Pos logit contributions
 your+0.056
 my+0.055
 the+0.046
 our+0.046
 big+0.042
Neg logit contributions
owing-0.078
oped-0.073
anged-0.070
eled-0.069
oled-0.069
Token pulls
Token ID16194
Feature activation-7.60e-01

Pos logit contributions
 your+0.173
 my+0.168
 our+0.150
 same+0.147
 new+0.146
Neg logit contributions
oped-0.182
owing-0.178
oled-0.168
oling-0.166
aring-0.165
Token and
Token ID290
Feature activation-1.48e+01

Pos logit contributions
 your+0.010
 my+0.009
 our+0.007
 same+0.007
 new+0.007
Neg logit contributions
oped-0.029
owing-0.029
oled-0.028
oling-0.027
aring-0.027
Token twists
Token ID30953
Feature activation-1.84e+00

Pos logit contributions
 your+0.377
 my+0.367
 our+0.329
 same+0.324
 new+0.323
Neg logit contributions
oped-0.369
owing-0.356
oled-0.339
oling-0.334
anged-0.333
Token the
Token ID262
Feature activation-3.27e+01

Pos logit contributions
 your+0.041
 my+0.040
 our+0.035
 new+0.034
 big+0.034
Neg logit contributions
oped-0.053
owing-0.052
amb-0.049
oled-0.049
aring-0.049
Token hose
Token ID31489
Feature activation+9.07e+00

Pos logit contributions
 your+0.613
 my+0.591
 our+0.505
 same+0.500
 new+0.494
Neg logit contributions
oped-1.038
owing-1.014
oled-0.974
oling-0.961
amb-0.955
Token.
Token ID13
Feature activation-1.40e+00

Pos logit contributions
oped+0.276
oled+0.260
owing+0.260
unch+0.260
idd+0.258
Neg logit contributions
 your-0.188
 my-0.183
 the-0.168
 big-0.168
 same-0.167
Token He
Token ID679
Feature activation-4.89e+00

Pos logit contributions
 your+0.031
 my+0.029
 the+0.026
 big+0.025
 new+0.025
Neg logit contributions
owing-0.045
oped-0.043
eled-0.041
anged-0.040
aring-0.040
Token sees
Token ID7224
Feature activation-7.46e+00

Pos logit contributions
 your+0.113
 my+0.109
 our+0.097
 new+0.094
 same+0.094
Neg logit contributions
oped-0.132
owing-0.126
oled-0.121
anged-0.120
oling-0.120
Token a
Token ID257
Feature activation-2.07e+01

Pos logit contributions
 your+0.084
 my+0.079
 our+0.059
 new+0.057
 big+0.057
Neg logit contributions
oped-0.298
owing-0.294
oled-0.282
oling-0.280
aring-0.280
Token works
Token ID2499
Feature activation-3.84e-01

Pos logit contributions
 your+0.041
 my+0.040
 our+0.036
 same+0.035
 the+0.035
Neg logit contributions
owing-0.042
oped-0.042
oled-0.039
aring-0.039
anged-0.039
Token!
Token ID0
Feature activation-6.55e+00

Pos logit contributions
 your+0.009
 my+0.009
 our+0.008
 same+0.008
 new+0.008
Neg logit contributions
oped-0.010
owing-0.009
aring-0.009
oled-0.009
oling-0.009
Token We
Token ID775
Feature activation-9.80e+00

Pos logit contributions
 your+0.156
 my+0.151
 the+0.127
 our+0.127
 same+0.116
Neg logit contributions
owing-0.195
oped-0.185
anged-0.174
eled-0.174
oling-0.173
Token can
Token ID460
Feature activation-6.82e+00

Pos logit contributions
 your+0.174
 my+0.162
 same+0.143
 our+0.139
 big+0.138
Neg logit contributions
oped-0.323
owing-0.321
edly-0.311
ipt-0.310
oling-0.309
Token turn
Token ID1210
Feature activation+1.57e+00

Pos logit contributions
 your+0.094
 my+0.089
 our+0.071
 same+0.069
 new+0.067
Neg logit contributions
oped-0.253
owing-0.249
oled-0.240
oling-0.237
anged-0.236
Token the
Token ID262
Feature activation-3.24e+01

Pos logit contributions
oped+0.047
owing+0.046
oled+0.044
anged+0.043
oling+0.043
Neg logit contributions
 your-0.030
 my-0.029
 same-0.025
 our-0.024
 new-0.024
Token screw
Token ID9580
Feature activation+6.10e+00

Pos logit contributions
 your+0.611
 my+0.586
 our+0.502
 new+0.475
 same+0.474
Neg logit contributions
oped-0.997
owing-0.984
oled-0.933
ocular-0.924
oling-0.923
Token with
Token ID351
Feature activation-1.41e+01

Pos logit contributions
oped+0.164
owing+0.160
oled+0.150
aring+0.149
oling+0.148
Neg logit contributions
 your-0.140
 my-0.136
 our-0.120
 new-0.118
 same-0.117
Token this
Token ID428
Feature activation-1.96e+01

Pos logit contributions
 your+0.149
 my+0.140
 same+0.107
 new+0.104
 our+0.101
Neg logit contributions
oped-0.523
owing-0.514
anged-0.495
idd-0.494
oled-0.494
Token screw
Token ID9580
Feature activation+8.20e+00

Pos logit contributions
 your+0.391
 my+0.375
 our+0.328
 same+0.315
 new+0.312
Neg logit contributions
oped-0.582
owing-0.571
oled-0.540
oling-0.535
aring-0.534
Tokendriver
Token ID26230
Feature activation+8.62e+00

Pos logit contributions
oped+0.197
owing+0.192
oled+0.181
oling+0.178
aring+0.177
Neg logit contributions
 your-0.216
 my-0.210
 our-0.189
 same-0.186
 new-0.185
Token.
Token ID13
Feature activation-2.50e+00

Pos logit contributions
 my+0.139
 your+0.138
 same+0.127
 new+0.123
 big+0.118
Neg logit contributions
owing-0.274
oped-0.264
olded-0.263
aring-0.262
anged-0.258
Token We
Token ID775
Feature activation-1.05e+01

Pos logit contributions
 your+0.056
 my+0.055
 the+0.046
 our+0.046
 big+0.042
Neg logit contributions
owing-0.078
oped-0.073
anged-0.070
eled-0.069
oled-0.069
Token have
Token ID423
Feature activation-1.44e+01

Pos logit contributions
 your+0.199
 my+0.186
 same+0.167
 the+0.167
 big+0.165
Neg logit contributions
owing-0.332
oped-0.328
ipt-0.319
edly-0.318
oling-0.318
Token to
Token ID284
Feature activation-2.46e+01

Pos logit contributions
 your+0.225
 my+0.219
 same+0.182
 new+0.178
 our+0.176
Neg logit contributions
oped-0.450
owing-0.443
idd-0.430
anged-0.428
aw-0.428
Token save
Token ID3613
Feature activation-6.10e+00

Pos logit contributions
 your+0.395
 my+0.385
 new+0.328
 same+0.320
 our+0.316
Neg logit contributions
oped-0.785
owing-0.782
aring-0.744
oled-0.738
amb-0.731
Token the
Token ID262
Feature activation-3.23e+01

Pos logit contributions
 your+0.069
 my+0.065
 our+0.048
 same+0.048
 new+0.046
Neg logit contributions
oped-0.235
owing-0.233
oled-0.223
aring-0.221
oling-0.221
Token world
Token ID995
Feature activation+3.28e+00

Pos logit contributions
 your+0.620
 my+0.597
 our+0.511
 same+0.481
 new+0.472
Neg logit contributions
oped-0.977
owing-0.967
oled-0.920
aring-0.910
idd-0.908
Token from
Token ID422
Feature activation-2.19e+01

Pos logit contributions
owing+0.083
oped+0.081
aring+0.078
uts+0.077
ocular+0.075
Neg logit contributions
 your-0.074
 my-0.073
 same-0.066
 new-0.064
 our-0.063
Token bad
Token ID2089
Feature activation-6.42e+00

Pos logit contributions
 your+0.216
 my+0.204
 same+0.153
 new+0.144
 our+0.141
Neg logit contributions
oped-0.830
owing-0.829
idd-0.793
anged-0.788
oled-0.787
Token guys
Token ID3730
Feature activation+9.10e+00

Pos logit contributions
 your+0.124
 my+0.121
 our+0.103
 same+0.100
 new+0.099
Neg logit contributions
oped-0.196
owing-0.195
oled-0.184
anged-0.182
aring-0.182
Token."
Token ID526
Feature activation+3.19e+00

Pos logit contributions
oped+0.236
owing+0.227
oled+0.217
anged+0.214
oling+0.214
Neg logit contributions
 your-0.227
 my-0.220
 our-0.197
 same-0.191
 new-0.190
Token to
Token ID284
Feature activation-2.78e+01

Pos logit contributions
oped+0.074
owing+0.073
eled+0.068
anged+0.068
oled+0.066
Neg logit contributions
 your-0.067
 my-0.066
 our-0.057
 the-0.053
 same-0.052
Token fight
Token ID1907
Feature activation+2.59e+00

Pos logit contributions
 your+0.382
 my+0.375
 new+0.332
 same+0.327
 our+0.307
Neg logit contributions
oped-0.851
owing-0.850
anged-0.798
uts-0.796
amb-0.794
Token.
Token ID13
Feature activation-3.65e+00

Pos logit contributions
oped+0.063
owing+0.061
oled+0.058
aring+0.057
oling+0.057
Neg logit contributions
 your-0.065
 my-0.064
 our-0.057
 same-0.057
 new-0.056
Token They
Token ID1119
Feature activation-7.33e+00

Pos logit contributions
 your+0.079
 my+0.077
 the+0.064
 our+0.064
 big+0.058
Neg logit contributions
owing-0.118
oped-0.112
anged-0.106
eled-0.106
oot-0.105
Token pull
Token ID2834
Feature activation+6.47e-01

Pos logit contributions
 your+0.150
 my+0.145
 our+0.126
 same+0.124
 big+0.122
Neg logit contributions
oped-0.220
owing-0.216
oled-0.206
oling-0.204
aring-0.203
Token the
Token ID262
Feature activation-3.22e+01

Pos logit contributions
oped+0.022
owing+0.021
oled+0.020
oling+0.020
aring+0.020
Neg logit contributions
 your-0.011
 my-0.011
 our-0.009
 same-0.009
 new-0.009
Token book
Token ID1492
Feature activation+7.24e+00

Pos logit contributions
 your+0.670
 my+0.644
 our+0.556
 same+0.521
 new+0.517
Neg logit contributions
oped-0.922
owing-0.906
oled-0.868
ocular-0.857
oling-0.856
Token from
Token ID422
Feature activation-2.10e+01

Pos logit contributions
oped+0.206
owing+0.201
oled+0.192
oling+0.189
aring+0.188
Neg logit contributions
 your-0.159
 my-0.154
 our-0.136
 same-0.133
 new-0.132
Token each
Token ID1123
Feature activation-1.70e+01

Pos logit contributions
 your+0.266
 my+0.252
 our+0.194
 same+0.190
 new+0.186
Neg logit contributions
oped-0.774
owing-0.764
oled-0.735
anged-0.730
oling-0.727
Token other
Token ID584
Feature activation-9.02e+00

Pos logit contributions
 your+0.198
 my+0.185
 our+0.143
 same+0.134
 new+0.131
Neg logit contributions
oped-0.656
owing-0.645
oled-0.623
anged-0.614
oling-0.614
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
 your+0.209
 my+0.201
 our+0.180
 the+0.178
 big+0.178
Neg logit contributions
oped-0.259
owing-0.241
amb-0.240
unch-0.238
idd-0.237
Token to
Token ID284
Feature activation-2.85e+01

Pos logit contributions
 your+0.380
 my+0.375
 same+0.332
 our+0.331
 new+0.308
Neg logit contributions
owing-0.538
oped-0.531
uts-0.514
aring-0.498
ocular-0.497
Token pick
Token ID2298
Feature activation-9.96e+00

Pos logit contributions
 your+0.423
 my+0.418
 new+0.360
 our+0.351
 same+0.349
Neg logit contributions
owing-0.886
oped-0.871
unch-0.840
ban-0.835
uts-0.831
Token good
Token ID922
Feature activation-1.48e+01

Pos logit contributions
 your+0.156
 my+0.149
 our+0.124
 same+0.120
 new+0.117
Neg logit contributions
oped-0.341
owing-0.336
oled-0.322
oling-0.318
aring-0.317
Token things
Token ID1243
Feature activation-4.01e+00

Pos logit contributions
 your+0.223
 my+0.212
 our+0.173
 same+0.168
 new+0.166
Neg logit contributions
oped-0.534
owing-0.520
oled-0.504
oling-0.500
aring-0.495
Token from
Token ID422
Feature activation-2.42e+01

Pos logit contributions
 your+0.106
 my+0.104
 same+0.095
 our+0.094
 big+0.092
Neg logit contributions
owing-0.089
oped-0.088
uts-0.083
aring-0.082
amb-0.081
Token the
Token ID262
Feature activation-3.21e+01

Pos logit contributions
 your+0.378
 my+0.363
 our+0.300
 same+0.293
 new+0.287
Neg logit contributions
oped-0.835
owing-0.822
oled-0.788
oling-0.779
aring-0.777
Token refrigerator
Token ID30500
Feature activation+9.77e+00

Pos logit contributions
 your+0.602
 my+0.579
 our+0.496
 same+0.492
 new+0.486
Neg logit contributions
oped-1.028
owing-1.002
oled-0.962
oling-0.949
anged-0.945
Token."
Token ID526
Feature activation+2.03e+00

Pos logit contributions
oped+0.253
owing+0.239
oled+0.234
oling+0.227
anged+0.227
Neg logit contributions
 your-0.250
 my-0.243
 our-0.217
 same-0.214
 big-0.213
Token
Token ID198
Feature activation-4.79e+00

Pos logit contributions
owing+0.062
oped+0.060
oled+0.057
oling+0.057
ocular+0.056
Neg logit contributions
 your-0.047
 my-0.044
 the-0.041
 our-0.038
 new-0.036
Token
Token ID198
Feature activation-3.87e+00

Pos logit contributions
 your+0.100
 my+0.094
 the+0.086
 big+0.083
 new+0.081
Neg logit contributions
owing-0.160
oped-0.152
anged-0.149
ked-0.148
ocular-0.145
TokenS
Token ID50
Feature activation+1.16e+00

Pos logit contributions
 your+0.088
 my+0.085
 our+0.074
 big+0.070
 the+0.069
Neg logit contributions
owing-0.115
oped-0.110
anged-0.106
oled-0.104
ocular-0.103
Token runs
Token ID4539
Feature activation-9.26e+00

Pos logit contributions
 your+0.077
 my+0.073
 our+0.068
 the+0.065
 big+0.065
Neg logit contributions
owing-0.090
oped-0.088
oled-0.083
ement-0.081
anged-0.081
Token to
Token ID284
Feature activation-2.80e+01

Pos logit contributions
 your+0.183
 my+0.176
 our+0.152
 same+0.148
 new+0.146
Neg logit contributions
oped-0.290
owing-0.284
oled-0.271
oling-0.268
anged-0.266
Token them
Token ID606
Feature activation-1.17e+01

Pos logit contributions
 your+0.312
 my+0.307
 same+0.253
 new+0.230
 our+0.229
Neg logit contributions
oped-0.942
owing-0.922
oot-0.887
oled-0.886
anged-0.886
Token and
Token ID290
Feature activation-1.47e+01

Pos logit contributions
 your+0.266
 my+0.254
 the+0.232
 our+0.224
 new+0.222
Neg logit contributions
oped-0.351
oled-0.327
idd-0.327
anged-0.321
oling-0.319
Token grabs
Token ID22378
Feature activation-6.44e+00

Pos logit contributions
 your+0.366
 my+0.359
 same+0.341
 sunny+0.337
 new+0.331
Neg logit contributions
oped-0.326
olded-0.302
anged-0.297
owing-0.297
ocular-0.287
Token the
Token ID262
Feature activation-3.21e+01

Pos logit contributions
 your+0.103
 my+0.099
 our+0.082
 same+0.080
 new+0.079
Neg logit contributions
oped-0.222
owing-0.218
oled-0.210
oling-0.207
aring-0.207
Token ball
Token ID2613
Feature activation+8.08e+00

Pos logit contributions
 your+0.655
 my+0.633
 our+0.551
 same+0.515
 new+0.514
Neg logit contributions
oped-0.892
owing-0.877
ocular-0.845
idd-0.841
oled-0.836
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
oped+0.210
owing+0.203
oled+0.195
oling+0.191
anged+0.190
Neg logit contributions
 your-0.203
 my-0.197
 our-0.177
 same-0.171
 big-0.171
Token He
Token ID679
Feature activation-4.65e+00

Pos logit contributions
 your+0.034
 my+0.032
 our+0.027
 the+0.027
 new+0.026
Neg logit contributions
owing-0.047
oped-0.045
eled-0.042
anged-0.042
owed-0.041
Token says
Token ID1139
Feature activation+3.70e+00

Pos logit contributions
 your+0.113
 my+0.108
 sunny+0.107
 same+0.099
 our+0.099
Neg logit contributions
oped-0.111
aw-0.104
olded-0.102
anged-0.099
idd-0.098
Token,
Token ID11
Feature activation-7.79e+00

Pos logit contributions
oped+0.113
owing+0.110
oled+0.105
oling+0.104
aring+0.104
Neg logit contributions
 your-0.075
 my-0.072
 our-0.062
 same-0.061
 new-0.060
Token and
Token ID290
Feature activation-1.49e+01

Pos logit contributions
 your+0.154
 my+0.142
 our+0.102
 same+0.095
 new+0.093
Neg logit contributions
oped-0.648
owing-0.638
oled-0.617
oling-0.610
aring-0.610
Token pulls
Token ID16194
Feature activation-3.64e+00

Pos logit contributions
 your+0.310
 my+0.302
 our+0.264
 same+0.259
 new+0.256
Neg logit contributions
oped-0.426
owing-0.415
oled-0.395
anged-0.392
aring-0.387
Token.
Token ID13
Feature activation-4.50e+00

Pos logit contributions
 your+0.054
 my+0.051
 our+0.042
 same+0.040
 the+0.040
Neg logit contributions
oped-0.134
owing-0.131
oled-0.126
aring-0.125
oling-0.125
Token She
Token ID1375
Feature activation-9.01e+00

Pos logit contributions
 your+0.101
 my+0.095
 the+0.083
 our+0.081
 big+0.078
Neg logit contributions
owing-0.141
oped-0.134
eled-0.129
anged-0.126
aring-0.124
Token opens
Token ID9808
Feature activation-1.18e+01

Pos logit contributions
 your+0.217
 my+0.211
 our+0.189
 same+0.185
 new+0.184
Neg logit contributions
oped-0.235
owing-0.223
oled-0.216
oling-0.212
anged-0.212
Token the
Token ID262
Feature activation-3.21e+01

Pos logit contributions
 your+0.104
 my+0.097
 our+0.067
 same+0.065
 new+0.060
Neg logit contributions
oped-0.480
owing-0.470
oled-0.457
oling-0.451
anged-0.451
Token barrel
Token ID9036
Feature activation+9.43e+00

Pos logit contributions
 your+0.678
 my+0.652
 our+0.577
 same+0.534
 new+0.530
Neg logit contributions
oped-0.876
owing-0.860
ocular-0.834
oled-0.815
oling-0.810
Token.
Token ID13
Feature activation-1.38e+00

Pos logit contributions
oped+0.319
owing+0.310
anged+0.303
oled+0.301
idd+0.300
Neg logit contributions
 your-0.160
 my-0.156
 the-0.139
 big-0.135
 new-0.130
Token Tim
Token ID5045
Feature activation-1.26e+00

Pos logit contributions
 your+0.030
 my+0.028
 the+0.025
 big+0.023
 new+0.023
Neg logit contributions
owing-0.045
oped-0.043
eled-0.041
anged-0.041
aring-0.040
Token comes
Token ID2058
Feature activation-3.73e+00

Pos logit contributions
 your+0.025
 my+0.024
 our+0.021
 same+0.020
 new+0.020
Neg logit contributions
oped-0.039
owing-0.038
oled-0.036
oling-0.036
aring-0.036
Token out
Token ID503
Feature activation-1.01e+01

Pos logit contributions
 your+0.064
 my+0.061
 big+0.053
 the+0.053
 new+0.052
Neg logit contributions
oped-0.131
amb-0.125
oled-0.125
ement-0.124
owing-0.123
Token happy
Token ID3772
Feature activation-7.30e+00

Pos logit contributions
oped+0.069
owing+0.068
oled+0.064
oling+0.063
eled+0.063
Neg logit contributions
 your-0.053
 my-0.053
 big-0.046
 the-0.046
 new-0.046
Token.
Token ID13
Feature activation-1.91e+00

Pos logit contributions
 your+0.173
 my+0.167
 our+0.148
 new+0.145
 same+0.144
Neg logit contributions
oped-0.203
owing-0.195
oled-0.188
oling-0.186
anged-0.183
Token They
Token ID1119
Feature activation-7.76e+00

Pos logit contributions
 your+0.044
 my+0.042
 our+0.036
 the+0.035
 new+0.033
Neg logit contributions
owing-0.059
oped-0.057
anged-0.054
oled-0.053
oling-0.053
Token forgot
Token ID16453
Feature activation-5.04e+00

Pos logit contributions
 your+0.187
 my+0.182
 our+0.162
 same+0.159
 new+0.157
Neg logit contributions
oped-0.204
owing-0.200
oled-0.189
oling-0.186
aring-0.186
Token about
Token ID546
Feature activation-1.52e+01

Pos logit contributions
 your+0.109
 my+0.107
 same+0.095
 our+0.093
 big+0.090
Neg logit contributions
oped-0.135
owing-0.135
oled-0.128
aring-0.128
uts-0.125
Token the
Token ID262
Feature activation-3.20e+01

Pos logit contributions
 your+0.134
 my+0.128
 same+0.093
 our+0.082
 big+0.078
Neg logit contributions
owing-0.596
oped-0.592
oled-0.568
anged-0.566
aring-0.562
Token balloon
Token ID21190
Feature activation+6.82e+00

Pos logit contributions
 your+0.560
 my+0.537
 our+0.455
 same+0.426
 new+0.416
Neg logit contributions
oped-1.033
owing-1.021
oled-0.975
aring-0.961
oling-0.960
Token.
Token ID13
Feature activation-7.80e-01

Pos logit contributions
oped+0.190
owing+0.181
oled+0.179
amb+0.174
oling+0.174
Neg logit contributions
 your-0.157
 my-0.152
 our-0.136
 new-0.135
 the-0.134
Token
Token ID198
Feature activation-4.74e+00

Pos logit contributions
 your+0.016
 my+0.015
 our+0.013
 the+0.012
 new+0.011
Neg logit contributions
owing-0.028
oped-0.026
anged-0.025
eled-0.025
owed-0.024
Token
Token ID198
Feature activation-3.64e+00

Pos logit contributions
 your+0.100
 my+0.092
 big+0.086
 the+0.086
 new+0.084
Neg logit contributions
owing-0.160
oped-0.153
anged-0.147
ked-0.145
edly-0.143
TokenThey
Token ID2990
Feature activation-5.45e-01

Pos logit contributions
 your+0.083
 my+0.078
 our+0.070
 big+0.065
 the+0.064
Neg logit contributions
owing-0.110
oped-0.106
anged-0.101
oled-0.100
ocular-0.099
Token.
Token ID13
Feature activation-2.50e+00

Pos logit contributions
 your+0.337
 my+0.335
 our+0.281
 same+0.271
 new+0.267
Neg logit contributions
oped-0.587
owing-0.574
anged-0.549
amb-0.544
uts-0.532
Token They
Token ID1119
Feature activation-8.69e+00

Pos logit contributions
 your+0.056
 my+0.055
 the+0.046
 our+0.046
 big+0.042
Neg logit contributions
owing-0.078
oped-0.073
anged-0.070
eled-0.069
oled-0.069
Token let
Token ID1309
Feature activation-7.95e+00

Pos logit contributions
 your+0.197
 my+0.190
 our+0.168
 same+0.165
 new+0.163
Neg logit contributions
oped-0.241
owing-0.236
oled-0.225
oling-0.222
aring-0.221
Token go
Token ID467
Feature activation-9.65e+00

Pos logit contributions
 your+0.137
 my+0.131
 our+0.110
 same+0.107
 new+0.106
Neg logit contributions
oped-0.268
owing-0.262
oled-0.252
oling-0.249
aring-0.248
Token of
Token ID286
Feature activation-2.56e+01

Pos logit contributions
 your+0.198
 my+0.189
 our+0.163
 new+0.158
 the+0.157
Neg logit contributions
oped-0.298
oled-0.291
oling-0.288
owing-0.287
edly-0.281
Token the
Token ID262
Feature activation-3.20e+01

Pos logit contributions
 your+0.197
 my+0.182
 same+0.149
 new+0.114
 big+0.108
Neg logit contributions
oped-0.989
owing-0.979
idd-0.957
oled-0.946
anged-0.944
Token tire
Token ID15867
Feature activation+8.42e+00

Pos logit contributions
 your+0.652
 my+0.627
 our+0.544
 same+0.520
 new+0.513
Neg logit contributions
oped-0.937
owing-0.917
oled-0.874
idd-0.868
oling-0.865
Token.
Token ID13
Feature activation-7.16e-01

Pos logit contributions
oped+0.235
owing+0.229
oled+0.219
oling+0.215
aring+0.214
Neg logit contributions
 your-0.190
 my-0.184
 our-0.162
 same-0.159
 new-0.158
Token It
Token ID632
Feature activation-3.98e+00

Pos logit contributions
 your+0.015
 my+0.015
 our+0.013
 the+0.012
 new+0.012
Neg logit contributions
owing-0.023
oped-0.022
eled-0.021
oled-0.021
oot-0.020
Token rolls
Token ID14088
Feature activation+3.83e+00

Pos logit contributions
 your+0.080
 my+0.076
 our+0.068
 new+0.063
 sunny+0.063
Neg logit contributions
oped-0.116
owing-0.106
ocular-0.105
anged-0.104
idd-0.103
Token fast
Token ID3049
Feature activation-2.10e+00

Pos logit contributions
oped+0.103
owing+0.096
oled+0.094
ocular+0.093
oling+0.092
Neg logit contributions
 your-0.085
 my-0.082
 new-0.073
 same-0.073
 our-0.072
TokenLet
Token ID5756
Feature activation-1.20e+01

Pos logit contributions
 your+0.163
 my+0.157
 our+0.141
 new+0.136
 the+0.136
Neg logit contributions
oped-0.164
owing-0.154
amb-0.150
oled-0.149
eled-0.148
Token's
Token ID338
Feature activation-2.70e+01

Pos logit contributions
 your+0.264
 my+0.257
 new+0.230
 our+0.228
 big+0.222
Neg logit contributions
oped-0.315
owing-0.307
aring-0.288
amb-0.287
oled-0.286
Token take
Token ID1011
Feature activation-1.38e+01

Pos logit contributions
 your+0.419
 my+0.400
 our+0.331
 new+0.327
 same+0.326
Neg logit contributions
oped-0.906
owing-0.891
amb-0.845
oled-0.843
aring-0.843
Token turns
Token ID4962
Feature activation-3.94e+00

Pos logit contributions
 your+0.175
 my+0.167
 same+0.132
 our+0.131
 new+0.129
Neg logit contributions
oped-0.505
owing-0.493
oled-0.476
amb-0.471
idd-0.470
Token wearing
Token ID5762
Feature activation-9.82e+00

Pos logit contributions
 your+0.082
 my+0.079
 our+0.069
 new+0.067
 same+0.067
Neg logit contributions
oped-0.118
owing-0.115
oled-0.110
amb-0.109
oling-0.109
Token the
Token ID262
Feature activation-3.20e+01

Pos logit contributions
 your+0.136
 my+0.129
 same+0.112
 new+0.106
 our+0.104
Neg logit contributions
oped-0.333
owing-0.321
oled-0.312
idd-0.311
amb-0.308
Token sweater
Token ID35685
Feature activation+1.21e+01

Pos logit contributions
 your+0.593
 my+0.570
 our+0.500
 same+0.448
 new+0.446
Neg logit contributions
oped-0.939
owing-0.925
idd-0.891
ocular-0.880
aw-0.878
Token,"
Token ID553
Feature activation+1.02e+00

Pos logit contributions
oped+0.331
owing+0.323
oled+0.308
anged+0.306
oling+0.303
Neg logit contributions
 your-0.284
 my-0.276
 our-0.243
 same-0.240
 big-0.236
Token L
Token ID406
Feature activation+1.28e-01

Pos logit contributions
oped+0.030
owing+0.030
oled+0.028
oling+0.028
aring+0.028
Neg logit contributions
 your-0.022
 my-0.021
 our-0.019
 new-0.018
 same-0.018
Tokenila
Token ID10102
Feature activation-7.69e-01

Pos logit contributions
oped+0.004
ocular+0.004
owing+0.004
edly+0.003
eled+0.003
Neg logit contributions
 your-0.003
 my-0.003
 the-0.002
 big-0.002
 same-0.002
Token said
Token ID531
Feature activation+4.65e+00

Pos logit contributions
 your+0.021
 my+0.020
 the+0.018
 same+0.018
 big+0.018
Neg logit contributions
oped-0.019
owing-0.018
oled-0.017
oling-0.017
idd-0.017
Token not
Token ID407
Feature activation-1.59e+01

Pos logit contributions
 your+0.053
 my+0.051
 our+0.046
 same+0.045
 new+0.045
Neg logit contributions
oped-0.052
owing-0.051
oled-0.048
oling-0.047
aring-0.047
Token jump
Token ID4391
Feature activation-2.52e+00

Pos logit contributions
 your+0.317
 my+0.310
 our+0.267
 same+0.264
 new+0.258
Neg logit contributions
owing-0.464
oped-0.458
aring-0.438
oled-0.431
anged-0.426
Token as
Token ID355
Feature activation-1.49e+01

Pos logit contributions
 your+0.063
 my+0.062
 our+0.055
 same+0.054
 new+0.054
Neg logit contributions
oped-0.061
owing-0.059
oled-0.056
oling-0.055
aring-0.055
Token high
Token ID1029
Feature activation-1.28e+01

Pos logit contributions
 your+0.248
 my+0.241
 our+0.203
 same+0.198
 new+0.191
Neg logit contributions
oped-0.483
owing-0.472
oled-0.452
aring-0.448
oling-0.447
Token as
Token ID355
Feature activation-1.19e+01

Pos logit contributions
 your+0.321
 my+0.313
 our+0.281
 same+0.276
 new+0.276
Neg logit contributions
oped-0.312
owing-0.305
oled-0.287
anged-0.285
amb-0.284
Token the
Token ID262
Feature activation-3.19e+01

Pos logit contributions
 your+0.223
 my+0.215
 our+0.184
 same+0.180
 new+0.178
Neg logit contributions
oped-0.376
owing-0.368
oled-0.352
oling-0.348
aring-0.346
Token others
Token ID1854
Feature activation-1.58e-01

Pos logit contributions
 your+0.608
 my+0.588
 same+0.506
 big+0.504
 new+0.504
Neg logit contributions
oped-1.016
owing-0.991
oled-0.950
oling-0.935
aring-0.934
Token.
Token ID13
Feature activation-7.48e-01

Pos logit contributions
 your+0.004
 my+0.003
 the+0.003
 our+0.003
 big+0.003
Neg logit contributions
oped-0.004
owing-0.004
amb-0.004
oled-0.004
eled-0.004
Token
Token ID198
Feature activation-4.67e+00

Pos logit contributions
 your+0.016
 my+0.016
 the+0.013
 our+0.013
 same+0.012
Neg logit contributions
owing-0.025
oped-0.024
anged-0.023
eled-0.022
oled-0.022
Token
Token ID198
Feature activation-3.59e+00

Pos logit contributions
 your+0.091
 my+0.084
 big+0.078
 the+0.077
 new+0.075
Neg logit contributions
owing-0.164
ked-0.155
oped-0.154
anged-0.151
oling-0.147
TokenOne
Token ID3198
Feature activation-1.45e+00

Pos logit contributions
 your+0.074
 my+0.070
 our+0.060
 big+0.057
 the+0.055
Neg logit contributions
owing-0.115
oped-0.110
anged-0.107
ocular-0.105
oled-0.104
Token okay
Token ID8788
Feature activation+3.45e-01

Pos logit contributions
 your+0.116
 my+0.110
 same+0.101
 our+0.098
 big+0.091
Neg logit contributions
owing-0.159
oped-0.158
uts-0.153
ocular-0.152
oot-0.150
Token to
Token ID284
Feature activation-2.56e+01

Pos logit contributions
oped+0.011
oled+0.010
owing+0.010
idd+0.010
oling+0.009
Neg logit contributions
 your-0.008
 my-0.008
 our-0.007
 the-0.006
 same-0.006
Token not
Token ID407
Feature activation-1.26e+01

Pos logit contributions
 your+0.405
 my+0.385
 our+0.319
 same+0.306
 new+0.299
Neg logit contributions
oped-0.909
owing-0.883
oled-0.858
oling-0.845
anged-0.839
Token always
Token ID1464
Feature activation-1.18e+01

Pos logit contributions
 your+0.214
 my+0.206
 our+0.173
 same+0.169
 new+0.167
Neg logit contributions
oped-0.416
owing-0.411
oled-0.392
aring-0.389
oling-0.388
Token win
Token ID1592
Feature activation+2.77e+00

Pos logit contributions
 your+0.198
 my+0.193
 same+0.168
 new+0.166
 our+0.165
Neg logit contributions
owing-0.362
oped-0.344
aring-0.342
oled-0.324
anged-0.324
Token the
Token ID262
Feature activation-3.18e+01

Pos logit contributions
oped+0.076
owing+0.075
oled+0.071
aring+0.071
oling+0.070
Neg logit contributions
 your-0.060
 my-0.058
 our-0.051
 same-0.051
 new-0.050
Token game
Token ID983
Feature activation+7.66e+00

Pos logit contributions
 your+0.529
 my+0.508
 our+0.430
 same+0.379
 new+0.376
Neg logit contributions
oped-1.028
owing-1.023
aring-0.968
oled-0.964
idd-0.963
Token.
Token ID13
Feature activation-4.16e-01

Pos logit contributions
oped+0.193
owing+0.187
oled+0.178
oling+0.175
amb+0.174
Neg logit contributions
 your-0.198
 my-0.192
 our-0.172
 same-0.169
 new-0.169
Token<|endoftext|>
Token ID50256
Feature activation+1.51e+00

Pos logit contributions
 your+0.009
 my+0.009
 our+0.007
 the+0.007
 new+0.006
Neg logit contributions
owing-0.014
oped-0.013
anged-0.013
ked-0.012
eled-0.012
TokenOnce
Token ID7454
Feature activation-5.31e+00

Pos logit contributions
owing+0.047
anged+0.046
aring+0.046
oped+0.045
olded+0.044
Neg logit contributions
 your-0.031
 my-0.030
 the-0.029
 big-0.027
 new-0.026
Token upon
Token ID2402
Feature activation-1.67e+01

Pos logit contributions
 your+0.094
 my+0.090
 our+0.076
 same+0.074
 new+0.072
Neg logit contributions
oped-0.173
owing-0.170
oled-0.162
oling-0.160
aring-0.160
Token time
Token ID640
Feature activation-1.03e+01

Pos logit contributions
 your+0.254
 my+0.248
 our+0.225
 new+0.220
 same+0.220
Neg logit contributions
oped-0.187
owing-0.183
oled-0.171
oling-0.168
aring-0.167
Token to
Token ID284
Feature activation-2.68e+01

Pos logit contributions
 your+0.222
 my+0.215
 our+0.189
 same+0.185
 new+0.183
Neg logit contributions
oped-0.295
owing-0.288
oled-0.275
oling-0.271
aring-0.269
Token go
Token ID467
Feature activation-1.01e+01

Pos logit contributions
 your+0.398
 my+0.391
 new+0.353
 same+0.340
 our+0.317
Neg logit contributions
oped-0.830
owing-0.811
anged-0.773
eled-0.768
oled-0.759
Token home
Token ID1363
Feature activation-1.61e+00

Pos logit contributions
 your+0.224
 my+0.223
 same+0.202
 our+0.197
 fake+0.188
Neg logit contributions
owing-0.260
oped-0.258
amb-0.238
oot-0.237
anged-0.235
Token as
Token ID355
Feature activation-1.17e+01

Pos logit contributions
 your+0.043
 my+0.042
 same+0.038
 our+0.038
 new+0.037
Neg logit contributions
owing-0.037
oped-0.036
oled-0.033
uts-0.033
oling-0.033
Token the
Token ID262
Feature activation-3.18e+01

Pos logit contributions
 your+0.212
 my+0.208
 same+0.180
 our+0.178
 new+0.168
Neg logit contributions
oped-0.356
owing-0.348
idd-0.329
oled-0.329
oling-0.326
Token woods
Token ID16479
Feature activation+5.61e+00

Pos logit contributions
 your+0.588
 my+0.574
 big+0.519
 same+0.514
 new+0.512
Neg logit contributions
oped-1.046
owing-1.017
oled-0.978
oling-0.967
aring-0.962
Token could
Token ID714
Feature activation-5.85e+00

Pos logit contributions
oped+0.154
owing+0.151
oled+0.144
oling+0.142
amb+0.141
Neg logit contributions
 your-0.128
 my-0.124
 our-0.110
 same-0.108
 new-0.107
Token be
Token ID307
Feature activation-1.28e+01

Pos logit contributions
 your+0.131
 my+0.126
 our+0.111
 same+0.109
 new+0.108
Neg logit contributions
oped-0.165
owing-0.161
oled-0.153
oling-0.151
aring-0.150
Token dangerous
Token ID4923
Feature activation-2.23e+00

Pos logit contributions
 your+0.275
 my+0.269
 our+0.236
 same+0.230
 new+0.217
Neg logit contributions
oped-0.358
owing-0.357
oled-0.328
anged-0.324
aw-0.321
Token.
Token ID13
Feature activation+1.57e+00

Pos logit contributions
 your+0.055
 my+0.053
 our+0.047
 same+0.047
 new+0.046
Neg logit contributions
oped-0.059
owing-0.056
oled-0.054
oling-0.053
anged-0.053
Token and
Token ID290
Feature activation-1.49e+01

Pos logit contributions
oped+0.141
owing+0.133
oled+0.130
amb+0.129
oling+0.128
Neg logit contributions
 your-0.110
 my-0.106
 our-0.094
 same-0.092
 new-0.092
Token dots
Token ID22969
Feature activation+1.25e-02

Pos logit contributions
 your+0.310
 my+0.302
 our+0.264
 same+0.259
 new+0.256
Neg logit contributions
oped-0.426
owing-0.415
oled-0.395
anged-0.392
aring-0.387
Token.
Token ID13
Feature activation-3.68e+00

Pos logit contributions
oped+0.000
owing+0.000
oled+0.000
oling+0.000
aring+0.000
Neg logit contributions
 your-0.000
 my-0.000
 our-0.000
 same-0.000
 new-0.000
Token They
Token ID1119
Feature activation-7.85e+00

Pos logit contributions
 your+0.084
 my+0.080
 our+0.068
 the+0.067
 big+0.063
Neg logit contributions
owing-0.116
oped-0.111
anged-0.104
oled-0.103
eled-0.102
Token mixed
Token ID7668
Feature activation-4.98e+00

Pos logit contributions
 your+0.163
 my+0.159
 our+0.138
 new+0.135
 same+0.133
Neg logit contributions
oped-0.230
owing-0.222
oled-0.214
oling-0.209
anged-0.209
Token the
Token ID262
Feature activation-3.18e+01

Pos logit contributions
 your+0.092
 my+0.090
 our+0.075
 same+0.074
 new+0.071
Neg logit contributions
oped-0.139
owing-0.137
aw-0.136
ocular-0.136
ement-0.135
Token colors
Token ID7577
Feature activation+3.45e+00

Pos logit contributions
 your+0.579
 my+0.557
 our+0.478
 the+0.399
 new+0.395
Neg logit contributions
owing-0.920
ocular-0.917
oped-0.904
aw-0.891
ement-0.885
Token and
Token ID290
Feature activation-1.22e+01

Pos logit contributions
oped+0.086
owing+0.085
ocular+0.081
uts+0.081
umbled+0.079
Neg logit contributions
 your-0.082
 my-0.080
 our-0.071
 same-0.070
 new-0.068
Token made
Token ID925
Feature activation-9.91e+00

Pos logit contributions
 your+0.228
 my+0.222
 same+0.187
 our+0.185
 new+0.178
Neg logit contributions
oped-0.353
anged-0.340
owing-0.336
ocular-0.333
oled-0.329
Token new
Token ID649
Feature activation-1.08e+01

Pos logit contributions
 your+0.130
 my+0.123
 our+0.097
 same+0.093
 new+0.092
Neg logit contributions
oped-0.371
owing-0.365
oled-0.352
oling-0.348
aring-0.347
Token ones
Token ID3392
Feature activation+3.56e+00

Pos logit contributions
 your+0.182
 my+0.175
 new+0.151
 our+0.148
 same+0.146
Neg logit contributions
oped-0.380
owing-0.363
oled-0.360
oling-0.353
aring-0.347
Token sorry
Token ID7926
Feature activation-1.70e-01

Pos logit contributions
 your+0.440
 my+0.425
 our+0.370
 same+0.353
 those+0.346
Neg logit contributions
ocular-0.530
owing-0.512
oped-0.505
edly-0.478
anged-0.474
Token,
Token ID11
Feature activation-1.51e+01

Pos logit contributions
 your+0.004
 my+0.004
 our+0.004
 same+0.003
 new+0.003
Neg logit contributions
oped-0.005
owing-0.004
oled-0.004
idd-0.004
oling-0.004
Token but
Token ID475
Feature activation-7.49e+00

Pos logit contributions
 your+0.289
 my+0.277
 same+0.253
 our+0.241
 new+0.239
Neg logit contributions
oped-0.421
owing-0.416
oled-0.407
aring-0.404
oling-0.398
Token he
Token ID339
Feature activation-9.64e+00

Pos logit contributions
 your+0.148
 my+0.143
 same+0.126
 our+0.124
 new+0.123
Neg logit contributions
oped-0.218
owing-0.215
oled-0.203
aring-0.202
oling-0.201
Token lost
Token ID2626
Feature activation-5.32e+00

Pos logit contributions
 your+0.211
 my+0.204
 our+0.178
 same+0.175
 big+0.175
Neg logit contributions
oped-0.279
owing-0.274
oled-0.263
oling-0.260
amb-0.258
Token the
Token ID262
Feature activation-3.18e+01

Pos logit contributions
 your+0.072
 my+0.068
 our+0.055
 same+0.055
 new+0.053
Neg logit contributions
oped-0.191
owing-0.188
oled-0.181
oling-0.178
anged-0.178
Token book
Token ID1492
Feature activation+6.85e+00

Pos logit contributions
 your+0.598
 my+0.574
 our+0.495
 same+0.467
 new+0.462
Neg logit contributions
oped-0.983
owing-0.970
oled-0.925
oling-0.912
aring-0.906
Token.
Token ID13
Feature activation-5.58e-01

Pos logit contributions
oped+0.168
owing+0.163
oled+0.154
oling+0.152
anged+0.151
Neg logit contributions
 your-0.178
 my-0.173
 our-0.155
 same-0.153
 new-0.152
Token He
Token ID679
Feature activation-4.00e+00

Pos logit contributions
 your+0.012
 my+0.012
 our+0.010
 the+0.010
 big+0.009
Neg logit contributions
owing-0.018
oped-0.017
anged-0.016
eled-0.016
oot-0.016
Token says
Token ID1139
Feature activation+3.67e+00

Pos logit contributions
 your+0.096
 my+0.093
 our+0.083
 new+0.082
 same+0.081
Neg logit contributions
oped-0.104
owing-0.098
oled-0.095
anged-0.094
oling-0.093
Token he
Token ID339
Feature activation-5.84e+00

Pos logit contributions
oped+0.111
owing+0.108
oled+0.104
oling+0.102
aring+0.102
Neg logit contributions
 your-0.075
 my-0.072
 our-0.063
 same-0.062
 new-0.061
Token,
Token ID11
Feature activation-1.75e+01

Pos logit contributions
 your+0.225
 my+0.220
 same+0.192
 our+0.188
 new+0.181
Neg logit contributions
oped-0.329
owing-0.327
uts-0.320
aring-0.309
oled-0.308
Token they
Token ID484
Feature activation-1.45e+01

Pos logit contributions
 your+0.364
 my+0.354
 our+0.311
 same+0.310
 new+0.295
Neg logit contributions
oped-0.495
owing-0.483
oled-0.468
oling-0.457
aring-0.455
Token would
Token ID561
Feature activation-1.27e+01

Pos logit contributions
 your+0.323
 my+0.312
 our+0.275
 same+0.271
 new+0.266
Neg logit contributions
oped-0.413
owing-0.405
oled-0.385
oling-0.380
aring-0.379
Token go
Token ID467
Feature activation-9.35e+00

Pos logit contributions
 your+0.197
 my+0.188
 our+0.156
 same+0.151
 new+0.149
Neg logit contributions
oped-0.443
owing-0.435
oled-0.418
oling-0.413
aring-0.412
Token to
Token ID284
Feature activation-2.42e+01

Pos logit contributions
 your+0.175
 my+0.173
 same+0.148
 our+0.145
 new+0.139
Neg logit contributions
oped-0.280
owing-0.278
amb-0.258
idd-0.254
oled-0.254
Token the
Token ID262
Feature activation-3.17e+01

Pos logit contributions
 your+0.331
 my+0.321
 same+0.261
 our+0.252
 new+0.243
Neg logit contributions
oped-0.816
owing-0.815
oled-0.769
aring-0.766
anged-0.765
Token open
Token ID1280
Feature activation-4.99e+00

Pos logit contributions
 your+0.561
 my+0.537
 our+0.456
 same+0.424
 new+0.420
Neg logit contributions
oped-1.005
owing-0.985
oled-0.943
oling-0.937
ocular-0.935
Token barn
Token ID25203
Feature activation+7.97e+00

Pos logit contributions
 your+0.091
 my+0.087
 our+0.076
 same+0.073
 new+0.071
Neg logit contributions
oped-0.150
owing-0.147
ocular-0.140
idd-0.140
aw-0.139
Token and
Token ID290
Feature activation-1.12e+01

Pos logit contributions
oped+0.229
owing+0.219
oled+0.214
oling+0.210
anged+0.208
Neg logit contributions
 your-0.178
 my-0.171
 our-0.151
 same-0.149
 new-0.148
Token take
Token ID1011
Feature activation-7.19e+00

Pos logit contributions
 your+0.185
 my+0.182
 same+0.157
 new+0.153
 our+0.148
Neg logit contributions
oped-0.340
owing-0.335
anged-0.321
ocular-0.318
oled-0.312
Token a
Token ID257
Feature activation-1.99e+01

Pos logit contributions
 your+0.114
 my+0.108
 our+0.090
 same+0.087
 new+0.086
Neg logit contributions
oped-0.252
owing-0.247
oled-0.238
oling-0.235
aring-0.234
Token:
Token ID25
Feature activation-1.46e+01

Pos logit contributions
oped+0.329
owing+0.321
oled+0.306
oling+0.302
aring+0.301
Neg logit contributions
 your-0.249
 my-0.241
 our-0.211
 same-0.207
 new-0.206
Token
Token ID198
Feature activation-6.47e+00

Pos logit contributions
 your+0.332
 my+0.316
 the+0.271
 our+0.270
 new+0.266
Neg logit contributions
oped-0.441
owing-0.437
anged-0.411
oled-0.409
edly-0.409
Token"
Token ID1
Feature activation-5.50e+00

Pos logit contributions
 your+0.136
 my+0.128
 big+0.109
 the+0.109
 our+0.108
Neg logit contributions
owing-0.220
oped-0.206
ked-0.206
anged-0.203
oled-0.202
TokenGive
Token ID23318
Feature activation+4.86e-02

Pos logit contributions
 your+0.137
 my+0.133
 our+0.117
 same+0.115
 new+0.112
Neg logit contributions
owing-0.149
oped-0.145
anged-0.136
oled-0.136
oling-0.132
Token me
Token ID502
Feature activation-9.65e+00

Pos logit contributions
oped+0.002
owing+0.002
oled+0.001
oling+0.001
aring+0.001
Neg logit contributions
 your-0.001
 my-0.001
 our-0.001
 same-0.001
 new-0.001
Token the
Token ID262
Feature activation-3.17e+01

Pos logit contributions
 your+0.082
 my+0.075
 same+0.072
 sunny+0.065
 new+0.063
Neg logit contributions
owing-0.361
oped-0.354
aring-0.350
oot-0.347
ocular-0.345
Token cup
Token ID6508
Feature activation+2.98e+00

Pos logit contributions
 your+0.657
 my+0.633
 our+0.554
 same+0.525
 new+0.524
Neg logit contributions
oped-0.914
owing-0.901
oled-0.853
aring-0.845
oling-0.841
Token!"
Token ID2474
Feature activation+1.05e+00

Pos logit contributions
oped+0.074
owing+0.072
oled+0.068
aring+0.067
amb+0.067
Neg logit contributions
 your-0.074
 my-0.072
 our-0.065
 same-0.064
 new-0.063
Token
Token ID198
Feature activation-4.60e+00

Pos logit contributions
oped+0.033
owing+0.033
oled+0.031
aring+0.031
oling+0.031
Neg logit contributions
 your-0.021
 my-0.020
 the-0.017
 our-0.017
 big-0.017
TokenJack
Token ID14295
Feature activation+3.41e+00

Pos logit contributions
 your+0.096
 my+0.090
 the+0.080
 big+0.078
 our+0.075
Neg logit contributions
owing-0.155
oped-0.147
anged-0.146
ked-0.143
oled-0.141
Token wanted
Token ID2227
Feature activation+3.67e+00

Pos logit contributions
oped+0.082
owing+0.081
unch+0.078
oled+0.077
idd+0.076
Neg logit contributions
 your-0.090
 my-0.088
 the-0.079
 same-0.078
 big-0.078
Token lick
Token ID36728
Feature activation-7.09e+00

Pos logit contributions
 your+0.160
 my+0.157
 same+0.146
 our+0.142
 new+0.137
Neg logit contributions
oped-0.183
owing-0.178
uts-0.167
oled-0.166
olded-0.166
Token and
Token ID290
Feature activation-1.82e+01

Pos logit contributions
 your+0.118
 my+0.114
 our+0.095
 same+0.093
 new+0.092
Neg logit contributions
oped-0.237
owing-0.233
oled-0.224
oling-0.221
aring-0.220
Token nib
Token ID33272
Feature activation-2.69e+00

Pos logit contributions
 your+0.419
 my+0.408
 our+0.360
 same+0.355
 new+0.351
Neg logit contributions
oped-0.489
owing-0.476
oled-0.453
anged-0.446
oling-0.445
Tokenble
Token ID903
Feature activation+2.34e+00

Pos logit contributions
 your+0.088
 my+0.086
 our+0.079
 same+0.078
 new+0.078
Neg logit contributions
oped-0.048
owing-0.046
oled-0.043
aring-0.042
oling-0.042
Token of
Token ID286
Feature activation-2.56e+01

Pos logit contributions
oped+0.066
owing+0.064
oled+0.062
aring+0.061
oling+0.060
Neg logit contributions
 your-0.054
 my-0.052
 our-0.045
 big-0.044
 new-0.044
Token the
Token ID262
Feature activation-3.17e+01

Pos logit contributions
 your+0.321
 my+0.304
 same+0.245
 our+0.244
 new+0.224
Neg logit contributions
oped-0.901
owing-0.887
anged-0.853
ocular-0.848
oled-0.847
Token sweet
Token ID6029
Feature activation-6.63e+00

Pos logit contributions
 your+0.595
 my+0.571
 our+0.492
 same+0.472
 new+0.468
Neg logit contributions
oped-0.990
owing-0.972
oled-0.927
oling-0.917
aring-0.912
Token treat
Token ID2190
Feature activation+1.30e+01

Pos logit contributions
 your+0.131
 my+0.126
 our+0.110
 same+0.105
 new+0.103
Neg logit contributions
oped-0.198
owing-0.196
oled-0.185
anged-0.183
amb-0.183
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
oped+0.357
owing+0.343
aring+0.337
oled+0.336
idd+0.328
Neg logit contributions
 your-0.307
 my-0.296
 the-0.269
 big-0.267
 new-0.266
Token Rachel
Token ID15984
Feature activation+2.29e+00

Pos logit contributions
owing+0.013
oped+0.013
anged+0.012
oot+0.012
aring+0.012
Neg logit contributions
 your-0.010
 my-0.010
 the-0.008
 our-0.008
 new-0.008
Token was
Token ID373
Feature activation-1.12e+01

Pos logit contributions
oped+0.059
owing+0.057
oled+0.055
oling+0.054
aring+0.053
Neg logit contributions
 your-0.056
 my-0.054
 our-0.048
 same-0.048
 new-0.047
Token They
Token ID1119
Feature activation-8.69e+00

Pos logit contributions
 your+0.056
 my+0.055
 the+0.046
 our+0.046
 big+0.042
Neg logit contributions
owing-0.078
oped-0.073
anged-0.070
eled-0.069
oled-0.069
Token take
Token ID1011
Feature activation-1.30e+01

Pos logit contributions
 your+0.197
 my+0.190
 our+0.168
 same+0.165
 new+0.163
Neg logit contributions
oped-0.241
owing-0.236
oled-0.225
oling-0.222
aring-0.221
Token turns
Token ID4962
Feature activation-3.78e+00

Pos logit contributions
 your+0.197
 my+0.187
 our+0.155
 same+0.148
 new+0.147
Neg logit contributions
oped-0.466
owing-0.458
oled-0.440
oling-0.437
aring-0.434
Token to
Token ID284
Feature activation-2.40e+01

Pos logit contributions
 your+0.068
 my+0.063
 the+0.057
 big+0.056
 our+0.056
Neg logit contributions
oped-0.125
amb-0.120
owing-0.120
eled-0.120
ement-0.118
Token pull
Token ID2834
Feature activation+1.46e+00

Pos logit contributions
 your+0.386
 my+0.375
 our+0.309
 same+0.299
 new+0.295
Neg logit contributions
oped-0.799
owing-0.787
oled-0.744
anged-0.739
aring-0.738
Token the
Token ID262
Feature activation-3.17e+01

Pos logit contributions
oped+0.054
owing+0.053
oled+0.051
oling+0.051
aring+0.051
Neg logit contributions
 your-0.021
 my-0.019
 our-0.016
 new-0.015
 same-0.015
Token string
Token ID4731
Feature activation+7.90e+00

Pos logit contributions
 your+0.614
 my+0.588
 our+0.507
 same+0.472
 new+0.470
Neg logit contributions
oped-0.954
owing-0.940
oled-0.896
oling-0.886
ocular-0.885
Token and
Token ID290
Feature activation-1.21e+01

Pos logit contributions
oped+0.206
owing+0.203
oled+0.191
oling+0.188
aring+0.188
Neg logit contributions
 your-0.188
 my-0.183
 our-0.162
 same-0.160
 new-0.158
Token watch
Token ID2342
Feature activation+4.44e+00

Pos logit contributions
 your+0.192
 my+0.186
 same+0.152
 our+0.151
 new+0.150
Neg logit contributions
oped-0.407
owing-0.393
anged-0.382
oled-0.381
oling-0.377
Token the
Token ID262
Feature activation-2.91e+01

Pos logit contributions
oped+0.183
owing+0.180
oled+0.174
amb+0.173
aring+0.172
Neg logit contributions
 your-0.047
 my-0.043
 our-0.033
 new-0.030
 the-0.030
Token rocket
Token ID10701
Feature activation+8.68e+00

Pos logit contributions
 your+0.549
 my+0.532
 same+0.464
 our+0.460
 big+0.458
Neg logit contributions
oped-0.938
owing-0.921
oled-0.875
aring-0.866
anged-0.865
Token while
Token ID981
Feature activation-1.40e+00

Pos logit contributions
 your+0.342
 my+0.325
 our+0.270
 same+0.248
 new+0.239
Neg logit contributions
oped-0.794
owing-0.777
oled-0.752
oling-0.743
aring-0.738
Token,
Token ID11
Feature activation-1.06e+01

Pos logit contributions
 your+0.028
 my+0.027
 our+0.024
 new+0.023
 same+0.023
Neg logit contributions
oped-0.043
owing-0.042
oled-0.040
oling-0.039
aring-0.039
Token pretending
Token ID23662
Feature activation+1.86e-01

Pos logit contributions
 your+0.183
 my+0.177
 same+0.153
 our+0.152
 new+0.144
Neg logit contributions
oped-0.340
owing-0.333
oled-0.321
oling-0.315
amb-0.312
Token to
Token ID284
Feature activation-2.47e+01

Pos logit contributions
oped+0.006
owing+0.006
oled+0.005
uts+0.005
aring+0.005
Neg logit contributions
 your-0.003
 my-0.003
 same-0.003
 our-0.003
 new-0.003
Token fly
Token ID6129
Feature activation+3.66e+00

Pos logit contributions
 your+0.373
 my+0.357
 our+0.304
 same+0.289
 new+0.285
Neg logit contributions
oped-0.785
owing-0.783
aring-0.747
ocular-0.739
oot-0.738
Token the
Token ID262
Feature activation-3.16e+01

Pos logit contributions
oped+0.103
owing+0.101
oled+0.095
aring+0.094
oling+0.093
Neg logit contributions
 your-0.077
 my-0.075
 our-0.066
 same-0.065
 new-0.063
Token airplane
Token ID19401
Feature activation+4.74e+00

Pos logit contributions
 your+0.595
 my+0.571
 our+0.493
 same+0.464
 new+0.464
Neg logit contributions
oped-0.980
owing-0.966
oled-0.919
oling-0.908
aring-0.907
Token and
Token ID290
Feature activation-1.19e+01

Pos logit contributions
oped+0.128
owing+0.124
oled+0.118
oling+0.117
aring+0.116
Neg logit contributions
 your-0.111
 my-0.108
 our-0.096
 same-0.094
 new-0.093
Token having
Token ID1719
Feature activation-8.56e+00

Pos logit contributions
 your+0.196
 my+0.190
 our+0.158
 same+0.156
 new+0.155
Neg logit contributions
oped-0.384
owing-0.375
oled-0.358
anged-0.357
ocular-0.355
Token lots
Token ID6041
Feature activation-3.57e+00

Pos logit contributions
 your+0.113
 my+0.106
 our+0.084
 same+0.081
 new+0.081
Neg logit contributions
oped-0.322
owing-0.317
oled-0.305
oling-0.302
aring-0.301
Token of
Token ID286
Feature activation-2.08e+01

Pos logit contributions
 your+0.076
 my+0.074
 new+0.065
 our+0.064
 big+0.064
Neg logit contributions
oped-0.106
owing-0.103
oled-0.099
oling-0.098
anged-0.097
Token something
Token ID1223
Feature activation-1.27e+00

Pos logit contributions
oped+0.033
owing+0.033
oled+0.032
anged+0.031
oling+0.031
Neg logit contributions
 your-0.008
 my-0.007
 our-0.005
 same-0.005
 new-0.004
Token.
Token ID13
Feature activation+8.09e+00

Pos logit contributions
 your+0.017
 my+0.016
 our+0.013
 same+0.012
 new+0.012
Neg logit contributions
oped-0.047
owing-0.046
oled-0.044
oling-0.044
aring-0.044
Token It
Token ID632
Feature activation+3.61e+00

Pos logit contributions
owing+0.254
oped+0.240
aring+0.229
anged+0.228
oot+0.227
Neg logit contributions
 your-0.169
 my-0.166
 the-0.155
 big-0.153
 new-0.147
Token was
Token ID373
Feature activation-5.27e+00

Pos logit contributions
oped+0.103
owing+0.099
oled+0.095
oling+0.093
anged+0.093
Neg logit contributions
 your-0.081
 my-0.078
 our-0.069
 same-0.067
 new-0.066
Token a
Token ID257
Feature activation-1.35e+01

Pos logit contributions
 your+0.082
 my+0.074
 our+0.068
 same+0.059
 those+0.054
Neg logit contributions
ocular-0.158
eled-0.149
aw-0.148
owing-0.148
oped-0.147
Token flame
Token ID16506
Feature activation+1.67e+01

Pos logit contributions
 your+0.171
 my+0.159
 our+0.126
 same+0.118
 new+0.107
Neg logit contributions
oped-0.499
owing-0.487
oled-0.474
oling-0.473
idd-0.468
Token!
Token ID0
Feature activation+7.01e+00

Pos logit contributions
oped+0.466
owing+0.448
oled+0.437
anged+0.427
amb+0.424
Neg logit contributions
 your-0.385
 my-0.374
 our-0.331
 big-0.329
 new-0.322
Token He
Token ID679
Feature activation+3.27e+00

Pos logit contributions
owing+0.237
oped+0.224
aring+0.214
anged+0.212
eled+0.211
Neg logit contributions
 your-0.133
 my-0.131
 the-0.121
 big-0.114
 new-0.108
Token thought
Token ID1807
Feature activation+1.49e+01

Pos logit contributions
owing+0.097
oped+0.094
oled+0.092
aring+0.091
oling+0.090
Neg logit contributions
 your-0.069
 my-0.068
 big-0.063
 the-0.061
 new-0.059
Token it
Token ID340
Feature activation+6.66e-02

Pos logit contributions
owing+0.300
oped+0.294
uts+0.281
unch+0.277
oot+0.271
Neg logit contributions
 my-0.384
 same-0.383
 your-0.375
 our-0.339
 common-0.320
Token was
Token ID373
Feature activation-5.25e+00

Pos logit contributions
oped+0.002
owing+0.002
aring+0.002
oled+0.002
unch+0.002
Neg logit contributions
 your-0.001
 my-0.001
 big-0.001
 new-0.001
 same-0.001
Token.
Token ID13
Feature activation+6.76e+00

Pos logit contributions
oped+0.403
oled+0.376
oling+0.373
umbled+0.373
unch+0.372
Neg logit contributions
 your-0.324
 my-0.302
 the-0.288
 big-0.271
 our-0.271
Token He
Token ID679
Feature activation+2.09e+00

Pos logit contributions
oped+0.180
owing+0.178
oled+0.165
aring+0.164
oling+0.163
Neg logit contributions
 your-0.166
 my-0.161
 our-0.142
 new-0.141
 same-0.140
Token brings
Token ID6774
Feature activation+3.81e+00

Pos logit contributions
oped+0.049
ks+0.046
aw+0.046
idd+0.046
anged+0.045
Neg logit contributions
 your-0.045
 my-0.045
 sunny-0.042
 our-0.041
 those-0.040
Token his
Token ID465
Feature activation-1.72e+01

Pos logit contributions
oped+0.144
owing+0.142
oled+0.136
anged+0.135
amb+0.135
Neg logit contributions
 your-0.046
 my-0.044
 our-0.034
 same-0.033
 new-0.032
Token favorite
Token ID4004
Feature activation-3.87e+00

Pos logit contributions
 your+0.330
 my+0.319
 our+0.268
 same+0.241
 those+0.240
Neg logit contributions
oped-0.485
owing-0.483
ocular-0.475
anged-0.474
idd-0.471
Token car
Token ID1097
Feature activation+1.40e+01

Pos logit contributions
 your+0.076
 my+0.072
 our+0.063
 same+0.060
 the+0.054
Neg logit contributions
oped-0.108
idd-0.104
owing-0.104
anged-0.101
ocular-0.100
Token,
Token ID11
Feature activation-9.59e-01

Pos logit contributions
oped+0.398
owing+0.390
oled+0.368
aring+0.365
anged+0.364
Neg logit contributions
 your-0.306
 my-0.297
 our-0.262
 same-0.256
 new-0.252
Token a
Token ID257
Feature activation-1.40e+01

Pos logit contributions
 your+0.020
 my+0.019
 same+0.019
 our+0.017
 new+0.016
Neg logit contributions
oped-0.024
ocular-0.024
owing-0.023
uts-0.023
oled-0.023
Token red
Token ID2266
Feature activation+1.26e+00

Pos logit contributions
 your+0.264
 my+0.253
 our+0.220
 same+0.207
 the+0.193
Neg logit contributions
oped-0.427
oled-0.399
idd-0.395
oling-0.392
owing-0.391
Token one
Token ID530
Feature activation-2.99e-01

Pos logit contributions
oped+0.032
owing+0.029
amb+0.029
idd+0.029
anged+0.029
Neg logit contributions
 your-0.030
 my-0.029
 our-0.026
 same-0.025
 new-0.025
Token with
Token ID351
Feature activation-5.66e+00

Pos logit contributions
 your+0.006
 my+0.006
 our+0.005
 same+0.005
 new+0.005
Neg logit contributions
oped-0.009
owing-0.008
oled-0.008
aring-0.008
anged-0.008
Token decided
Token ID3066
Feature activation+8.00e+00

Pos logit contributions
 your+0.021
 my+0.020
 our+0.019
 same+0.018
 new+0.018
Neg logit contributions
oped-0.020
owing-0.019
oled-0.018
uts-0.018
oling-0.018
Token to
Token ID284
Feature activation-1.40e+01

Pos logit contributions
oped+0.221
owing+0.217
aring+0.215
uts+0.214
oot+0.210
Neg logit contributions
 your-0.149
 my-0.148
 same-0.132
 our-0.129
 big-0.126
Token test
Token ID1332
Feature activation+1.27e+01

Pos logit contributions
 your+0.220
 my+0.211
 our+0.179
 new+0.174
 same+0.172
Neg logit contributions
oped-0.471
owing-0.462
amb-0.446
oled-0.440
aring-0.440
Token out
Token ID503
Feature activation-4.02e+00

Pos logit contributions
oped+0.418
owing+0.412
oled+0.394
oling+0.388
anged+0.388
Neg logit contributions
 your-0.209
 my-0.202
 our-0.169
 same-0.168
 big-0.161
Token its
Token ID663
Feature activation-1.55e+01

Pos logit contributions
 your+0.078
 my+0.075
 same+0.066
 our+0.065
 big+0.062
Neg logit contributions
oped-0.119
owing-0.118
aring-0.112
oled-0.111
oling-0.109
Token tail
Token ID7894
Feature activation+1.39e+01

Pos logit contributions
 your+0.298
 my+0.287
 our+0.247
 same+0.240
 new+0.238
Neg logit contributions
oped-0.485
owing-0.476
oled-0.454
oling-0.448
aring-0.448
Token again
Token ID757
Feature activation+5.44e+00

Pos logit contributions
oped+0.366
owing+0.352
oled+0.342
oling+0.337
anged+0.335
Neg logit contributions
 your-0.339
 my-0.329
 big-0.292
 new-0.292
 same-0.291
Token.
Token ID13
Feature activation+7.13e+00

Pos logit contributions
oped+0.116
owing+0.114
oled+0.104
aring+0.103
oling+0.103
Neg logit contributions
 your-0.155
 my-0.152
 our-0.138
 same-0.137
 new-0.135
Token This
Token ID770
Feature activation-6.53e+00

Pos logit contributions
owing+0.202
oped+0.199
anged+0.184
oled+0.182
oling+0.182
Neg logit contributions
 your-0.169
 my-0.163
 the-0.145
 new-0.142
 our-0.141
Token time
Token ID640
Feature activation+3.61e+00

Pos logit contributions
 your+0.122
 my+0.114
 our+0.102
 those+0.081
 same+0.080
Neg logit contributions
oped-0.198
eled-0.192
ement-0.190
aw-0.186
oled-0.184
Token it
Token ID340
Feature activation-1.49e+00

Pos logit contributions
oped+0.108
owing+0.104
oled+0.100
anged+0.098
oling+0.098
Neg logit contributions
 your-0.073
 my-0.071
 same-0.062
 our-0.062
 new-0.060
Token crazy
Token ID7165
Feature activation+5.57e-01

Pos logit contributions
 your+0.279
 my+0.266
 our+0.223
 same+0.211
 new+0.199
Neg logit contributions
oped-0.600
owing-0.591
oled-0.568
idd-0.563
anged-0.561
Token things
Token ID1243
Feature activation+5.27e+00

Pos logit contributions
oped+0.019
owing+0.019
oled+0.018
oling+0.018
amb+0.018
Neg logit contributions
 your-0.009
 my-0.009
 new-0.007
 our-0.007
 big-0.007
Token!
Token ID0
Feature activation+3.35e+00

Pos logit contributions
oped+0.147
owing+0.143
oled+0.136
oling+0.134
aring+0.134
Neg logit contributions
 your-0.119
 my-0.115
 our-0.102
 same-0.100
 new-0.099
Token There
Token ID1318
Feature activation+1.10e+00

Pos logit contributions
owing+0.106
oped+0.102
aring+0.096
anged+0.095
oling+0.095
Neg logit contributions
 your-0.069
 my-0.067
 the-0.059
 new-0.056
 our-0.056
Token were
Token ID547
Feature activation-5.32e+00

Pos logit contributions
oped+0.024
owing+0.024
oled+0.022
anged+0.021
umbled+0.021
Neg logit contributions
 your-0.031
 my-0.030
 our-0.027
 same-0.027
 new-0.026
Token bats
Token ID19553
Feature activation+1.41e+01

Pos logit contributions
 your+0.100
 my+0.095
 our+0.082
 same+0.078
 new+0.077
Neg logit contributions
oped-0.162
owing-0.158
oled-0.153
ocular-0.153
idd-0.150
Token,
Token ID11
Feature activation-2.91e+00

Pos logit contributions
oped+0.402
owing+0.391
oled+0.375
oling+0.368
aring+0.365
Neg logit contributions
 your-0.308
 my-0.299
 our-0.262
 same-0.256
 new-0.253
Token balls
Token ID11333
Feature activation+1.17e+01

Pos logit contributions
 your+0.059
 my+0.057
 our+0.049
 same+0.048
 new+0.047
Neg logit contributions
oped-0.085
owing-0.082
oled-0.080
ocular-0.079
oling-0.078
Token,
Token ID11
Feature activation-2.77e+00

Pos logit contributions
oped+0.349
owing+0.341
oled+0.326
oling+0.321
aring+0.320
Neg logit contributions
 your-0.243
 my-0.234
 our-0.204
 same-0.200
 new-0.198
Token and
Token ID290
Feature activation-6.38e+00

Pos logit contributions
 your+0.064
 my+0.061
 our+0.054
 same+0.054
 new+0.052
Neg logit contributions
oped-0.071
ocular-0.069
owing-0.068
oled-0.066
uts-0.064
Token silly
Token ID14397
Feature activation+2.24e+00

Pos logit contributions
 your+0.123
 my+0.118
 same+0.102
 our+0.102
 new+0.097
Neg logit contributions
oped-0.174
owing-0.169
ocular-0.169
oled-0.165
anged-0.164
Token saw
Token ID2497
Feature activation+9.32e-01

Pos logit contributions
owing+0.261
oped+0.260
amb+0.248
unch+0.244
aring+0.244
Neg logit contributions
 your-0.195
 my-0.189
 big-0.166
 the-0.164
 our-0.162
Token the
Token ID262
Feature activation-2.23e+01

Pos logit contributions
oped+0.033
owing+0.032
oled+0.031
anged+0.031
oling+0.030
Neg logit contributions
 your-0.014
 my-0.013
 our-0.011
 same-0.011
 new-0.010
Token blood
Token ID2910
Feature activation+1.07e+01

Pos logit contributions
 your+0.472
 my+0.450
 our+0.404
 new+0.347
 same+0.346
Neg logit contributions
owing-0.625
oped-0.613
oled-0.597
oling-0.594
umbled-0.589
Token and
Token ID290
Feature activation-3.97e+00

Pos logit contributions
oped+0.330
owing+0.326
amb+0.313
aring+0.310
anged+0.309
Neg logit contributions
 your-0.209
 my-0.200
 the-0.174
 big-0.173
 our-0.171
Token the
Token ID262
Feature activation-2.23e+01

Pos logit contributions
 your+0.079
 my+0.077
 our+0.068
 same+0.068
 new+0.064
Neg logit contributions
oped-0.112
anged-0.109
owing-0.106
oled-0.106
eled-0.105
Token onion
Token ID21670
Feature activation+1.56e+01

Pos logit contributions
 your+0.444
 my+0.426
 our+0.374
 same+0.339
 new+0.339
Neg logit contributions
oped-0.656
owing-0.654
oled-0.627
oling-0.620
idd-0.612
Token juice
Token ID13135
Feature activation+1.46e+01

Pos logit contributions
oped+0.443
amb+0.439
owing+0.428
aring+0.420
oot+0.420
Neg logit contributions
 your-0.338
 my-0.322
 big-0.307
 the-0.305
 new-0.293
Token.
Token ID13
Feature activation+8.24e+00

Pos logit contributions
oped+0.394
owing+0.391
amb+0.371
aring+0.368
anged+0.362
Neg logit contributions
 your-0.344
 my-0.331
 big-0.298
 our-0.294
 same-0.294
Token He
Token ID679
Feature activation+2.99e+00

Pos logit contributions
owing+0.233
oped+0.232
oled+0.212
amb+0.211
aring+0.210
Neg logit contributions
 your-0.197
 my-0.191
 our-0.168
 big-0.167
 new-0.165
Token cried
Token ID16896
Feature activation+1.65e+01

Pos logit contributions
oped+0.077
owing+0.076
oled+0.071
oling+0.070
aring+0.070
Neg logit contributions
 your-0.074
 my-0.072
 our-0.064
 same-0.063
 new-0.063
Token too
Token ID1165
Feature activation+3.11e+00

Pos logit contributions
oped+0.519
owing+0.493
idd+0.477
oled+0.471
oling+0.469
Neg logit contributions
 your-0.336
 my-0.321
 big-0.283
 new-0.282
 our-0.278
Token all
Token ID477
Feature activation-1.64e+00

Pos logit contributions
 my+0.040
 your+0.040
 big+0.038
 the+0.036
 our+0.035
Neg logit contributions
oped-0.066
owing-0.063
anged-0.062
oled-0.061
amb-0.061
Token so
Token ID523
Feature activation-7.17e+00

Pos logit contributions
 your+0.039
 my+0.038
 our+0.034
 big+0.033
 new+0.033
Neg logit contributions
oped-0.045
owing-0.043
oled-0.042
amb-0.041
oling-0.041
Token scared
Token ID12008
Feature activation+1.13e+01

Pos logit contributions
 big+0.126
 your+0.111
 new+0.108
 my+0.108
 the+0.100
Neg logit contributions
owing-0.263
oped-0.257
anged-0.253
amb-0.251
edly-0.247
Token,
Token ID11
Feature activation+6.77e-01

Pos logit contributions
oped+0.371
owing+0.352
oled+0.342
unch+0.339
amb+0.337
Neg logit contributions
 your-0.232
 my-0.223
 the-0.201
 our-0.196
 new-0.185
Token but
Token ID475
Feature activation+5.12e+00

Pos logit contributions
oped+0.021
owing+0.021
oled+0.020
oling+0.019
aring+0.019
Neg logit contributions
 your-0.013
 my-0.013
 our-0.011
 same-0.011
 new-0.011
Token they
Token ID484
Feature activation-1.55e-01

Pos logit contributions
oped+0.163
owing+0.159
oled+0.153
amb+0.153
oling+0.151
Neg logit contributions
 your-0.102
 my-0.099
 our-0.086
 the-0.085
 new-0.083
Token knew
Token ID2993
Feature activation+9.17e+00

Pos logit contributions
 your+0.003
 my+0.003
 the+0.003
 big+0.003
 our+0.003
Neg logit contributions
oped-0.004
owing-0.004
aring-0.004
unch-0.004
amb-0.004
Token they
Token ID484
Feature activation-2.54e-01

Pos logit contributions
oped+0.300
owing+0.293
oled+0.282
oling+0.278
aring+0.276
Neg logit contributions
 your-0.168
 my-0.161
 our-0.138
 new-0.133
 same-0.132
Token had
Token ID550
Feature activation-1.69e+00

Pos logit contributions
 your+0.005
 my+0.005
 big+0.005
 the+0.005
 our+0.005
Neg logit contributions
oped-0.007
owing-0.007
amb-0.007
unch-0.007
idd-0.007
Token to
Token ID284
Feature activation-1.26e+01

Pos logit contributions
 your+0.031
 my+0.030
 our+0.025
 same+0.025
 new+0.023
Neg logit contributions
owing-0.052
oped-0.052
anged-0.049
aring-0.049
oled-0.048
Token work
Token ID670
Feature activation+1.06e+01

Pos logit contributions
 your+0.206
 my+0.198
 our+0.164
 same+0.161
 new+0.159
Neg logit contributions
oped-0.424
owing-0.422
oled-0.399
aring-0.398
amb-0.395
Token mad
Token ID8805
Feature activation+8.98e+00

Pos logit contributions
 your+0.148
 my+0.144
 same+0.127
 our+0.127
 new+0.125
Neg logit contributions
oped-0.172
owing-0.171
oled-0.159
aring-0.158
oling-0.158
Token if
Token ID611
Feature activation+3.18e+00

Pos logit contributions
oped+0.298
anged+0.268
eled+0.267
owing+0.266
idd+0.257
Neg logit contributions
 your-0.200
 my-0.194
 our-0.167
 same-0.166
 big-0.165
Token we
Token ID356
Feature activation-1.80e+00

Pos logit contributions
oped+0.099
owing+0.097
oled+0.092
oling+0.091
aring+0.091
Neg logit contributions
 your-0.061
 my-0.059
 our-0.051
 same-0.050
 new-0.049
Token go
Token ID467
Feature activation+1.99e+00

Pos logit contributions
 your+0.028
 my+0.026
 big+0.022
 the+0.022
 our+0.022
Neg logit contributions
oped-0.063
ement-0.063
oled-0.062
oling-0.062
edly-0.062
Token,"
Token ID553
Feature activation+8.62e+00

Pos logit contributions
oped+0.060
owing+0.058
oled+0.057
oling+0.056
umbled+0.056
Neg logit contributions
 your-0.043
 my-0.041
 our-0.036
 new-0.035
 big-0.035
Token Tom
Token ID4186
Feature activation+5.60e+00

Pos logit contributions
oped+0.260
owing+0.256
oled+0.243
aring+0.241
oling+0.240
Neg logit contributions
 your-0.189
 my-0.181
 the-0.159
 our-0.158
 new-0.156
Token said
Token ID531
Feature activation+9.27e+00

Pos logit contributions
oped+0.166
idd+0.159
oled+0.158
oling+0.156
unch+0.153
Neg logit contributions
 your-0.120
 my-0.118
 the-0.116
 big-0.107
 same-0.102
Token.
Token ID13
Feature activation+6.95e+00

Pos logit contributions
oped+0.277
idd+0.260
amb+0.257
unch+0.251
eled+0.250
Neg logit contributions
 your-0.209
 the-0.198
 my-0.191
 new-0.185
 big-0.181
Token
Token ID198
Feature activation+1.59e+00

Pos logit contributions
owing+0.213
oped+0.205
oled+0.190
eled+0.187
owed+0.187
Neg logit contributions
 your-0.154
 my-0.150
 big-0.135
 the-0.134
 new-0.132
Token
Token ID198
Feature activation+1.61e+00

Pos logit contributions
owing+0.049
oped+0.047
oled+0.044
anged+0.044
edly+0.044
Neg logit contributions
 your-0.035
 my-0.033
 big-0.031
 the-0.030
 our-0.030
TokenSam
Token ID16305
Feature activation+1.02e+01

Pos logit contributions
oped+0.039
owing+0.038
oled+0.036
oling+0.035
anged+0.035
Neg logit contributions
 your-0.043
 my-0.042
 our-0.037
 same-0.037
 new-0.037
Token to
Token ID284
Feature activation-1.32e+01

Pos logit contributions
owing+0.235
oped+0.227
aring+0.223
oled+0.221
uts+0.219
Neg logit contributions
 your-0.138
 my-0.137
 same-0.124
 our-0.119
 big-0.113
Token be
Token ID307
Feature activation-5.37e+00

Pos logit contributions
 your+0.203
 my+0.192
 our+0.158
 same+0.153
 new+0.149
Neg logit contributions
oped-0.471
owing-0.457
oled-0.446
oling-0.441
anged-0.437
Token careful
Token ID8161
Feature activation+8.19e+00

Pos logit contributions
 your+0.114
 my+0.112
 our+0.099
 same+0.098
 new+0.094
Neg logit contributions
owing-0.148
oped-0.148
aring-0.137
oled-0.137
idd-0.136
Token and
Token ID290
Feature activation-3.92e+00

Pos logit contributions
oped+0.242
owing+0.228
oled+0.222
idd+0.219
anged+0.219
Neg logit contributions
 your-0.181
 my-0.174
 our-0.152
 same-0.148
 new-0.148
Token he
Token ID339
Feature activation+2.71e-01

Pos logit contributions
 your+0.070
 my+0.068
 our+0.059
 same+0.058
 new+0.056
Neg logit contributions
oped-0.123
owing-0.122
aring-0.116
oled-0.115
anged-0.114
Token should
Token ID815
Feature activation+1.58e+00

Pos logit contributions
oped+0.007
owing+0.007
oled+0.007
unch+0.007
oling+0.007
Neg logit contributions
 your-0.006
 my-0.006
 big-0.006
 the-0.005
 same-0.005
Token never
Token ID1239
Feature activation+1.57e+00

Pos logit contributions
oped+0.056
owing+0.055
oled+0.053
oling+0.052
anged+0.052
Neg logit contributions
 your-0.025
 my-0.024
 our-0.019
 same-0.019
 big-0.018
Token try
Token ID1949
Feature activation+8.66e+00

Pos logit contributions
oped+0.058
oled+0.055
owing+0.055
idd+0.054
oling+0.054
Neg logit contributions
 your-0.023
 my-0.021
 same-0.017
 big-0.017
 our-0.017
Token to
Token ID284
Feature activation-1.33e+01

Pos logit contributions
owing+0.252
oped+0.244
aring+0.237
uts+0.235
oling+0.232
Neg logit contributions
 your-0.162
 my-0.160
 our-0.140
 same-0.140
 big-0.128
Token do
Token ID466
Feature activation+7.07e-01

Pos logit contributions
 your+0.222
 my+0.212
 our+0.177
 same+0.173
 new+0.171
Neg logit contributions
oped-0.459
owing-0.445
oled-0.434
oling-0.427
anged-0.424
Token something
Token ID1223
Feature activation-1.46e+00

Pos logit contributions
oped+0.022
owing+0.021
oled+0.020
aring+0.020
oling+0.020
Neg logit contributions
 your-0.013
 my-0.013
 our-0.011
 same-0.011
 new-0.010
Token yellow
Token ID7872
Feature activation+1.70e+00

Pos logit contributions
 your+0.409
 my+0.387
 our+0.333
 same+0.304
 new+0.302
Neg logit contributions
oped-0.726
owing-0.703
oled-0.684
oling-0.673
ocular-0.670
Token ball
Token ID2613
Feature activation+1.77e+01

Pos logit contributions
oped+0.052
owing+0.051
oled+0.049
oling+0.048
anged+0.048
Neg logit contributions
 your-0.033
 my-0.032
 our-0.028
 same-0.026
 new-0.026
Token and
Token ID290
Feature activation-3.90e+00

Pos logit contributions
oped+0.527
oled+0.508
owing+0.506
oling+0.492
eled+0.490
Neg logit contributions
 your-0.363
 my-0.347
 the-0.322
 big-0.320
 new-0.319
Token shouted
Token ID17293
Feature activation+1.54e+01

Pos logit contributions
 your+0.101
 my+0.099
 the+0.091
 our+0.088
 big+0.087
Neg logit contributions
owing-0.100
oped-0.097
aring-0.093
unch-0.091
oled-0.091
Token,
Token ID11
Feature activation+2.24e-02

Pos logit contributions
oped+0.491
owing+0.474
eled+0.457
anged+0.455
umbled+0.455
Neg logit contributions
 your-0.310
 my-0.292
 our-0.258
 new-0.254
 the-0.252
Token "
Token ID366
Feature activation+3.98e+00

Pos logit contributions
owing+0.001
oped+0.001
anged+0.001
umbled+0.001
eled+0.001
Neg logit contributions
 your-0.000
 my-0.000
 the-0.000
 big-0.000
 new-0.000
TokenLook
Token ID8567
Feature activation+1.32e+01

Pos logit contributions
owing+0.123
owed+0.111
aring+0.110
oped+0.109
oot+0.109
Neg logit contributions
 your-0.085
 my-0.084
 same-0.075
 our-0.072
 the-0.069
Token!
Token ID0
Feature activation+7.28e+00

Pos logit contributions
oped+0.412
edly+0.396
oled+0.392
owing+0.391
umbled+0.388
Neg logit contributions
 your-0.294
 my-0.285
 our-0.250
 the-0.238
 big-0.230
Token What
Token ID1867
Feature activation+1.98e+00

Pos logit contributions
owing+0.217
oped+0.205
anged+0.199
eled+0.197
edly+0.195
Neg logit contributions
 your-0.167
 my-0.166
 our-0.143
 the-0.136
 big-0.133
Token is
Token ID318
Feature activation-5.25e+00

Pos logit contributions
oped+0.058
owing+0.057
aw+0.056
aring+0.056
uts+0.055
Neg logit contributions
 your-0.036
 my-0.035
 same-0.030
 our-0.030
 new-0.029
Token that
Token ID326
Feature activation-4.39e+00

Pos logit contributions
 same+0.090
 my+0.086
 your+0.086
 new+0.082
 task+0.082
Neg logit contributions
idd-0.129
oot-0.126
aw-0.126
amb-0.125
oped-0.124
Token felt
Token ID2936
Feature activation-3.37e-01

Pos logit contributions
oped+0.376
owing+0.375
amb+0.371
oled+0.368
aring+0.365
Neg logit contributions
 your-0.255
 my-0.247
 big-0.240
 the-0.234
 same-0.230
Token a
Token ID257
Feature activation-1.42e+01

Pos logit contributions
 your+0.006
 my+0.006
 our+0.006
 same+0.005
 new+0.005
Neg logit contributions
owing-0.009
oped-0.009
oled-0.009
oling-0.008
olded-0.008
Token warm
Token ID5814
Feature activation+3.43e+00

Pos logit contributions
 your+0.244
 my+0.228
 our+0.196
 same+0.177
 new+0.173
Neg logit contributions
oped-0.463
owing-0.451
oled-0.442
oling-0.440
unch-0.425
Token breeze
Token ID28633
Feature activation+1.74e+01

Pos logit contributions
oped+0.095
owing+0.094
oled+0.089
oling+0.088
amb+0.087
Neg logit contributions
 your-0.078
 my-0.075
 our-0.067
 same-0.064
 new-0.063
Token around
Token ID1088
Feature activation-1.23e-01

Pos logit contributions
oped+0.481
owing+0.469
aring+0.451
oled+0.447
amb+0.447
Neg logit contributions
 your-0.385
 my-0.370
 big-0.329
 same-0.327
 our-0.327
Token it
Token ID340
Feature activation-7.25e-01

Pos logit contributions
 your+0.003
 my+0.002
 the+0.002
 our+0.002
 new+0.002
Neg logit contributions
oped-0.004
owing-0.004
aring-0.004
oled-0.004
amb-0.003
Token.
Token ID13
Feature activation+7.46e+00

Pos logit contributions
 your+0.017
 my+0.016
 big+0.015
 the+0.015
 new+0.015
Neg logit contributions
oped-0.019
owing-0.019
amb-0.019
idd-0.019
aring-0.019
Token It
Token ID632
Feature activation+2.56e+00

Pos logit contributions
owing+0.267
oped+0.260
aring+0.246
eled+0.245
anged+0.244
Neg logit contributions
 your-0.129
 my-0.122
 the-0.114
 new-0.101
 our-0.100
Token was
Token ID373
Feature activation-6.21e+00

Pos logit contributions
oped+0.069
owing+0.067
oled+0.064
oling+0.063
aring+0.063
Neg logit contributions
 your-0.061
 my-0.059
 our-0.052
 same-0.051
 new-0.051
Token the
Token ID262
Feature activation-2.33e+01

Pos logit contributions
 your+0.118
 my+0.111
 our+0.099
 same+0.093
 those+0.091
Neg logit contributions
owing-0.177
oped-0.174
eled-0.168
oled-0.166
umbled-0.165
Token wind
Token ID2344
Feature activation+1.44e+01

Pos logit contributions
 your+0.407
 my+0.385
 our+0.332
 new+0.298
 same+0.294
Neg logit contributions
owing-0.750
oped-0.749
oled-0.707
oling-0.705
ocular-0.701
Token she
Token ID673
Feature activation-3.95e+00

Pos logit contributions
oped+0.039
oled+0.037
aw+0.036
owing+0.036
uts+0.036
Neg logit contributions
 your-0.029
 my-0.028
 our-0.025
 same-0.025
 new-0.024
Token could
Token ID714
Feature activation-1.41e+00

Pos logit contributions
 your+0.092
 my+0.090
 same+0.080
 big+0.080
 the+0.079
Neg logit contributions
oped-0.105
owing-0.104
oled-0.099
aring-0.099
oling-0.099
Token run
Token ID1057
Feature activation+8.48e+00

Pos logit contributions
 your+0.026
 my+0.026
 our+0.022
 same+0.020
 new+0.020
Neg logit contributions
owing-0.044
oped-0.044
uts-0.041
oot-0.040
aring-0.040
Token,
Token ID11
Feature activation-3.70e+00

Pos logit contributions
oped+0.220
owing+0.214
oled+0.204
aring+0.200
oling+0.200
Neg logit contributions
 your-0.203
 my-0.198
 our-0.177
 same-0.173
 new-0.171
Token and
Token ID290
Feature activation-7.50e+00

Pos logit contributions
 your+0.075
 my+0.074
 our+0.066
 same+0.063
 new+0.063
Neg logit contributions
owing-0.104
oped-0.103
uts-0.097
aring-0.097
ocular-0.096
Token how
Token ID703
Feature activation-8.71e+00

Pos logit contributions
 your+0.129
 my+0.125
 our+0.107
 same+0.102
 new+0.101
Neg logit contributions
oped-0.241
owing-0.238
oled-0.228
anged-0.226
aring-0.226
Token loud
Token ID7812
Feature activation+1.81e+00

Pos logit contributions
 my+0.163
 your+0.157
 our+0.138
 same+0.130
 new+0.122
Neg logit contributions
owing-0.261
oped-0.257
aring-0.249
uts-0.246
aw-0.244
Token she
Token ID673
Feature activation-4.42e+00

Pos logit contributions
oped+0.052
owing+0.050
oled+0.049
oling+0.048
uts+0.047
Neg logit contributions
 your-0.038
 my-0.036
 our-0.032
 same-0.032
 new-0.031
Token could
Token ID714
Feature activation-1.89e+00

Pos logit contributions
 your+0.097
 my+0.095
 same+0.084
 big+0.083
 the+0.083
Neg logit contributions
oped-0.123
owing-0.122
oled-0.118
aring-0.117
oling-0.117
Token scream
Token ID8196
Feature activation+1.68e+01

Pos logit contributions
 your+0.035
 my+0.035
 our+0.030
 new+0.028
 same+0.027
Neg logit contributions
owing-0.057
oped-0.057
uts-0.054
oot-0.053
unch-0.052
Token.
Token ID13
Feature activation+3.77e+00

Pos logit contributions
oped+0.413
owing+0.403
oled+0.383
oling+0.375
aring+0.374
Neg logit contributions
 your-0.428
 my-0.417
 our-0.374
 same-0.367
 new-0.364
Token princess
Token ID21752
Feature activation+1.33e+01

Pos logit contributions
 your+0.417
 my+0.396
 our+0.345
 same+0.322
 new+0.316
Neg logit contributions
oped-0.698
owing-0.688
oled-0.658
idd-0.653
oling-0.648
Token could
Token ID714
Feature activation+1.98e+00

Pos logit contributions
oped+0.368
owing+0.362
oled+0.349
oling+0.345
aring+0.343
Neg logit contributions
 your-0.297
 my-0.288
 our-0.252
 big-0.251
 the-0.248
Token not
Token ID407
Feature activation-1.31e+00

Pos logit contributions
oped+0.058
owing+0.056
uts+0.055
amb+0.054
oot+0.053
Neg logit contributions
 your-0.039
 my-0.038
 our-0.033
 new-0.032
 same-0.032
Token resist
Token ID4180
Feature activation+4.77e+00

Pos logit contributions
 your+0.026
 my+0.025
 our+0.022
 same+0.021
 new+0.021
Neg logit contributions
oped-0.040
owing-0.039
oled-0.038
oling-0.037
aring-0.037
Token playing
Token ID2712
Feature activation+6.77e+00

Pos logit contributions
oped+0.131
owing+0.130
oled+0.123
oling+0.121
aring+0.120
Neg logit contributions
 your-0.105
 my-0.103
 our-0.090
 same-0.088
 new-0.086
Token with
Token ID351
Feature activation-5.80e+00

Pos logit contributions
oped+0.161
owing+0.160
oled+0.152
uts+0.148
ement+0.147
Neg logit contributions
 your-0.163
 my-0.161
 our-0.145
 same-0.142
 new-0.134
Token it
Token ID340
Feature activation-6.05e-01

Pos logit contributions
 your+0.075
 my+0.071
 our+0.056
 same+0.054
 new+0.052
Neg logit contributions
oped-0.216
owing-0.213
oled-0.205
oling-0.203
anged-0.202
Token.
Token ID13
Feature activation+7.96e+00

Pos logit contributions
 your+0.016
 my+0.016
 our+0.014
 new+0.014
 same+0.014
Neg logit contributions
oped-0.015
owing-0.014
oled-0.013
oling-0.013
amb-0.013
Token The
Token ID383
Feature activation-1.22e+01

Pos logit contributions
oped+0.235
owing+0.235
oling+0.218
eled+0.217
anged+0.216
Neg logit contributions
 your-0.173
 my-0.169
 the-0.148
 same-0.147
 new-0.145
Token original
Token ID2656
Feature activation-9.25e-01

Pos logit contributions
 your+0.250
 my+0.238
 our+0.210
 same+0.196
 new+0.192
Neg logit contributions
oped-0.360
owing-0.356
oled-0.339
idd-0.338
anged-0.334
Token light
Token ID1657
Feature activation+1.30e+01

Pos logit contributions
 your+0.019
 my+0.018
 our+0.016
 same+0.015
 big+0.014
Neg logit contributions
oped-0.027
owing-0.027
idd-0.025
amb-0.025
oled-0.025
Token and
Token ID290
Feature activation-4.59e+00

Pos logit contributions
oped+0.442
owing+0.426
oled+0.413
oling+0.408
anged+0.403
Neg logit contributions
 your-0.303
 my-0.293
 our-0.255
 new-0.251
 big-0.248
Token said
Token ID531
Feature activation+9.62e+00

Pos logit contributions
 your+0.142
 my+0.139
 same+0.128
 our+0.127
 new+0.124
Neg logit contributions
oped-0.084
owing-0.079
anged-0.075
oled-0.074
amb-0.074
Token,
Token ID11
Feature activation-7.14e-01

Pos logit contributions
oped+0.286
owing+0.280
oled+0.268
aring+0.264
oling+0.263
Neg logit contributions
 your-0.197
 my-0.191
 our-0.166
 same-0.164
 new-0.161
Token "
Token ID366
Feature activation+2.48e+00

Pos logit contributions
 your+0.013
 my+0.012
 the+0.011
 new+0.010
 big+0.010
Neg logit contributions
oped-0.024
owing-0.024
anged-0.023
idd-0.022
eled-0.022
TokenWhat
Token ID2061
Feature activation+2.12e+00

Pos logit contributions
owing+0.069
oped+0.066
aring+0.063
anged+0.062
oled+0.061
Neg logit contributions
 your-0.059
 my-0.059
 same-0.052
 our-0.050
 big-0.050
Token a
Token ID257
Feature activation-1.44e+01

Pos logit contributions
owing+0.060
oped+0.058
aw+0.058
aring+0.056
uts+0.056
Neg logit contributions
 your-0.040
 my-0.039
 same-0.034
 our-0.033
 new-0.031
Token nice
Token ID3621
Feature activation+3.78e+00

Pos logit contributions
 your+0.166
 my+0.162
 big+0.129
 new+0.127
 our+0.122
Neg logit contributions
oped-0.585
owing-0.579
oled-0.554
anged-0.549
umbled-0.549
Token dinosaur
Token ID28257
Feature activation+1.43e+01

Pos logit contributions
oped+0.121
owing+0.119
oled+0.114
oling+0.113
anged+0.111
Neg logit contributions
 your-0.075
 my-0.074
 big-0.064
 new-0.064
 our-0.063
Token."
Token ID526
Feature activation+1.15e+01

Pos logit contributions
oped+0.336
owing+0.327
oled+0.308
oling+0.302
aring+0.302
Neg logit contributions
 your-0.382
 my-0.372
 our-0.335
 same-0.331
 new-0.328
Token
Token ID198
Feature activation+1.71e+00

Pos logit contributions
oped+0.316
owing+0.312
oled+0.293
oling+0.289
aring+0.287
Neg logit contributions
 your-0.286
 my-0.279
 our-0.244
 the-0.244
 new-0.241
Token
Token ID198
Feature activation+1.73e+00

Pos logit contributions
owing+0.053
oped+0.051
anged+0.049
oling+0.048
oled+0.048
Neg logit contributions
 your-0.038
 my-0.035
 big-0.033
 the-0.032
 new-0.032
Token with
Token ID351
Feature activation-6.92e+00

Pos logit contributions
oped+0.471
owing+0.457
idd+0.444
anged+0.438
oled+0.438
Neg logit contributions
 your-0.314
 my-0.302
 new-0.267
 the-0.265
 big-0.265
Token his
Token ID465
Feature activation-1.81e+01

Pos logit contributions
 your+0.105
 my+0.101
 our+0.082
 new+0.082
 big+0.081
Neg logit contributions
oped-0.255
owing-0.251
amb-0.239
aring-0.239
oling-0.238
Token family
Token ID1641
Feature activation+1.43e+01

Pos logit contributions
 your+0.362
 my+0.350
 new+0.314
 big+0.311
 our+0.305
Neg logit contributions
oped-0.576
owing-0.552
oled-0.540
oling-0.533
aring-0.531
Token and
Token ID290
Feature activation-5.40e+00

Pos logit contributions
oped+0.417
owing+0.387
oled+0.383
idd+0.381
oling+0.379
Neg logit contributions
 your-0.326
 my-0.315
 the-0.288
 new-0.281
 our-0.280
Token played
Token ID2826
Feature activation+5.91e+00

Pos logit contributions
 your+0.108
 my+0.105
 our+0.090
 same+0.090
 new+0.087
Neg logit contributions
oped-0.160
owing-0.156
oled-0.150
anged-0.149
oling-0.147
Token with
Token ID351
Feature activation-7.19e+00

Pos logit contributions
oped+0.156
owing+0.154
oled+0.146
oling+0.144
amb+0.143
Neg logit contributions
 your-0.135
 my-0.133
 our-0.117
 same-0.116
 new-0.112
Token his
Token ID465
Feature activation-1.84e+01

Pos logit contributions
 your+0.111
 my+0.105
 our+0.087
 new+0.085
 big+0.083
Neg logit contributions
oped-0.261
owing-0.257
oled-0.246
aring-0.245
oling-0.244
Token baby
Token ID5156
Feature activation+8.33e+00

Pos logit contributions
 your+0.376
 my+0.363
 our+0.314
 same+0.307
 new+0.296
Neg logit contributions
oped-0.548
owing-0.541
oled-0.510
anged-0.504
oling-0.504
Token sister
Token ID6621
Feature activation+1.18e+01

Pos logit contributions
oped+0.262
oled+0.250
oling+0.246
owing+0.241
unch+0.240
Neg logit contributions
 your-0.173
 my-0.168
 new-0.152
 big-0.150
 our-0.147
Token.
Token ID13
Feature activation+6.61e+00

Pos logit contributions
oped+0.335
ipt+0.316
unch+0.315
umbled+0.315
owing+0.315
Neg logit contributions
 your-0.277
 my-0.266
 the-0.248
 our-0.236
 big-0.235
Token Tim
Token ID5045
Feature activation+4.36e+00

Pos logit contributions
oped+0.186
owing+0.184
oled+0.170
oling+0.169
aring+0.167
Neg logit contributions
 your-0.154
 my-0.150
 our-0.132
 same-0.129
 new-0.129
Token
Token ID198
Feature activation+9.60e-01

Pos logit contributions
owing+0.238
oped+0.226
eled+0.221
amb+0.218
anged+0.216
Neg logit contributions
 your-0.120
 my-0.116
 the-0.112
 big-0.103
 new-0.102
Token
Token ID198
Feature activation+9.55e-01

Pos logit contributions
owing+0.030
oped+0.028
anged+0.028
edly+0.027
oled+0.027
Neg logit contributions
 your-0.021
 my-0.020
 big-0.018
 the-0.018
 new-0.018
TokenHis
Token ID6653
Feature activation-5.88e+00

Pos logit contributions
owing+0.027
oped+0.026
oled+0.025
anged+0.025
amb+0.025
Neg logit contributions
 your-0.022
 my-0.022
 our-0.019
 big-0.018
 new-0.018
Token mum
Token ID25682
Feature activation+1.16e+01

Pos logit contributions
 new+0.100
 big+0.100
 your+0.096
 my+0.095
 same+0.086
Neg logit contributions
oped-0.210
oled-0.202
owing-0.199
oling-0.199
unch-0.192
Token came
Token ID1625
Feature activation+2.85e+00

Pos logit contributions
uts+0.378
amb+0.366
edly+0.364
keeping+0.362
aring+0.347
Neg logit contributions
 the-0.227
 big-0.195
 my-0.190
 your-0.188
 new-0.170
Token to
Token ID284
Feature activation-1.50e+01

Pos logit contributions
oped+0.098
oled+0.092
oling+0.091
unch+0.090
uts+0.090
Neg logit contributions
 your-0.052
 my-0.050
 the-0.044
 big-0.042
 our-0.042
Token him
Token ID683
Feature activation-3.40e+00

Pos logit contributions
 your+0.257
 my+0.250
 same+0.226
 our+0.214
 new+0.210
Neg logit contributions
oped-0.458
owing-0.454
oled-0.428
idd-0.422
anged-0.422
Token and
Token ID290
Feature activation-6.00e+00

Pos logit contributions
 your+0.049
 my+0.047
 the+0.046
 new+0.041
 big+0.040
Neg logit contributions
oped-0.127
idd-0.122
umbled-0.120
oled-0.118
aw-0.118
Token said
Token ID531
Feature activation+8.33e+00

Pos logit contributions
 your+0.157
 my+0.153
 our+0.136
 the+0.136
 new+0.135
Neg logit contributions
oped-0.146
owing-0.146
oled-0.136
aring-0.136
amb-0.136
Token softly
Token ID26625
Feature activation+1.24e+01

Pos logit contributions
oped+0.278
owing+0.273
amb+0.260
anged+0.259
oling+0.259
Neg logit contributions
 your-0.154
 my-0.144
 our-0.121
 the-0.121
 new-0.119
Token,
Token ID11
Feature activation-2.13e+00

Pos logit contributions
oped+0.447
umbled+0.437
ipt+0.435
aw+0.433
unch+0.430
Neg logit contributions
 your-0.186
 the-0.181
 my-0.169
 new-0.151
 our-0.139
Token Whenever
Token ID21326
Feature activation+4.71e+00

Pos logit contributions
owing+0.273
oped+0.265
anged+0.256
ked+0.253
eled+0.248
Neg logit contributions
 your-0.186
 my-0.183
 the-0.162
 our-0.151
 new-0.146
Token the
Token ID262
Feature activation-2.16e+01

Pos logit contributions
oped+0.155
owing+0.153
anged+0.146
oled+0.146
aw+0.144
Neg logit contributions
 your-0.066
 my-0.065
 same-0.056
 our-0.054
 big-0.052
Token elderly
Token ID13830
Feature activation+6.96e+00

Pos logit contributions
 your+0.385
 my+0.373
 new+0.319
 same+0.318
 big+0.317
Neg logit contributions
oped-0.724
owing-0.706
oled-0.678
oling-0.671
anged-0.666
Token man
Token ID582
Feature activation+1.81e+01

Pos logit contributions
oped+0.206
owing+0.200
oled+0.192
oling+0.190
anged+0.188
Neg logit contributions
 your-0.150
 my-0.146
 new-0.127
 big-0.126
 the-0.125
Token watched
Token ID7342
Feature activation+9.65e+00

Pos logit contributions
oped+0.475
owing+0.464
oled+0.443
oling+0.437
aring+0.432
Neg logit contributions
 your-0.433
 my-0.421
 our-0.373
 same-0.368
 new-0.366
Token the
Token ID262
Feature activation-2.15e+01

Pos logit contributions
oped+0.322
owing+0.319
oled+0.306
oling+0.300
anged+0.299
Neg logit contributions
 your-0.150
 my-0.145
 same-0.122
 our-0.121
 new-0.114
Token sunset
Token ID26428
Feature activation+1.76e+01

Pos logit contributions
 your+0.387
 my+0.377
 new+0.336
 same+0.334
 big+0.334
Neg logit contributions
oped-0.720
owing-0.696
oled-0.669
oling-0.663
anged-0.658
Token from
Token ID422
Feature activation-1.18e+01

Pos logit contributions
oped+0.517
owing+0.510
oled+0.480
aring+0.475
oling+0.474
Neg logit contributions
 your-0.366
 my-0.354
 our-0.308
 same-0.300
 new-0.294
Token that
Token ID326
Feature activation-4.10e+00

Pos logit contributions
 your+0.125
 my+0.119
 our+0.091
 same+0.085
 new+0.084
Neg logit contributions
oped-0.443
owing-0.441
anged-0.422
eled-0.421
oled-0.418
Token day
Token ID1110
Feature activation+1.04e+01

Pos logit contributions
 your+0.078
 my+0.076
 our+0.066
 same+0.062
 new+0.061
Neg logit contributions
oped-0.124
owing-0.123
ement-0.115
oled-0.114
oling-0.112
Token on
Token ID319
Feature activation-9.67e+00

Pos logit contributions
oped+0.320
owing+0.314
oled+0.300
aring+0.297
oling+0.297
Neg logit contributions
 your-0.206
 my-0.197
 our-0.170
 new-0.166
 same-0.166
Token up
Token ID510
Feature activation-2.10e+00

Pos logit contributions
oped+0.212
owing+0.209
aring+0.200
oled+0.200
oling+0.197
Neg logit contributions
 your-0.130
 my-0.125
 our-0.108
 new-0.106
 the-0.106
Token to
Token ID284
Feature activation-1.23e+01

Pos logit contributions
 your+0.039
 my+0.038
 our+0.032
 same+0.032
 new+0.031
Neg logit contributions
oped-0.067
owing-0.065
oled-0.063
oling-0.062
anged-0.061
Token the
Token ID262
Feature activation-2.14e+01

Pos logit contributions
 your+0.159
 my+0.154
 same+0.120
 our+0.119
 new+0.112
Neg logit contributions
oped-0.428
owing-0.427
oled-0.400
idd-0.400
oling-0.397
Token top
Token ID1353
Feature activation+1.08e+01

Pos logit contributions
 your+0.453
 my+0.437
 our+0.381
 same+0.370
 new+0.367
Neg logit contributions
oped-0.629
owing-0.615
oled-0.588
oling-0.581
aring-0.577
Token of
Token ID286
Feature activation-1.36e+01

Pos logit contributions
oped+0.328
owing+0.320
oled+0.313
amb+0.310
oling+0.302
Neg logit contributions
 your-0.219
 my-0.215
 big-0.198
 the-0.195
 new-0.192
Token the
Token ID262
Feature activation-2.13e+01

Pos logit contributions
 your+0.105
 my+0.093
 same+0.066
 our+0.057
 new+0.050
Neg logit contributions
oped-0.539
owing-0.525
eled-0.522
idd-0.521
oled-0.510
Token tank
Token ID6873
Feature activation+1.94e+01

Pos logit contributions
 your+0.486
 my+0.471
 our+0.415
 same+0.406
 new+0.402
Neg logit contributions
oped-0.596
owing-0.582
oled-0.554
oling-0.546
aring-0.544
Token.
Token ID13
Feature activation+9.36e+00

Pos logit contributions
oped+0.590
amb+0.567
oled+0.559
eled+0.552
anged+0.547
Neg logit contributions
 the-0.381
 your-0.374
 big-0.373
 my-0.360
 new-0.357
Token He
Token ID679
Feature activation+3.99e+00

Pos logit contributions
owing+0.331
oped+0.320
eled+0.302
oot+0.299
anged+0.299
Neg logit contributions
 your-0.159
 my-0.156
 the-0.138
 big-0.128
 new-0.126
Token told
Token ID1297
Feature activation+1.10e+01

Pos logit contributions
owing+0.119
oped+0.115
oled+0.111
aring+0.111
unch+0.110
Neg logit contributions
 your-0.085
 my-0.084
 the-0.077
 big-0.076
 our-0.074
Token the
Token ID262
Feature activation-2.12e+01

Pos logit contributions
oped+0.464
owing+0.463
oled+0.444
anged+0.443
aring+0.442
Neg logit contributions
 your-0.080
 my-0.073
 our-0.044
 same-0.043
 new-0.037
Token.
Token ID13
Feature activation+7.98e+00

Pos logit contributions
oped+0.360
owing+0.343
oled+0.332
oling+0.326
eled+0.323
Neg logit contributions
 your-0.348
 my-0.337
 our-0.302
 new-0.297
 big-0.297
Token She
Token ID1375
Feature activation+1.96e+00

Pos logit contributions
oped+0.258
owing+0.254
eled+0.244
anged+0.239
oled+0.236
Neg logit contributions
 your-0.171
 my-0.160
 the-0.134
 our-0.133
 big-0.131
Token followed
Token ID3940
Feature activation+8.67e+00

Pos logit contributions
owing+0.054
oped+0.052
oled+0.050
aring+0.050
unch+0.049
Neg logit contributions
 your-0.046
 my-0.046
 big-0.041
 same-0.040
 the-0.040
Token Tom
Token ID4186
Feature activation+6.79e+00

Pos logit contributions
oped+0.284
owing+0.276
aring+0.266
oled+0.266
oling+0.264
Neg logit contributions
 your-0.168
 my-0.160
 our-0.137
 the-0.134
 same-0.131
Token to
Token ID284
Feature activation-1.33e+01

Pos logit contributions
oped+0.256
idd+0.247
ement+0.246
unch+0.244
umbled+0.243
Neg logit contributions
 your-0.100
 my-0.090
 the-0.081
 new-0.075
 our-0.074
Token the
Token ID262
Feature activation-2.27e+01

Pos logit contributions
 your+0.125
 my+0.124
 our+0.089
 same+0.087
 fake+0.078
Neg logit contributions
owing-0.482
oped-0.464
anged-0.455
oled-0.451
ocular-0.448
Token table
Token ID3084
Feature activation+1.15e+01

Pos logit contributions
 your+0.452
 my+0.437
 our+0.381
 the+0.343
 same+0.342
Neg logit contributions
oped-0.617
owing-0.610
idd-0.595
oling-0.590
oled-0.589
Token.
Token ID13
Feature activation+8.13e+00

Pos logit contributions
oped+0.301
owing+0.285
oled+0.275
amb+0.273
oling+0.273
Neg logit contributions
 your-0.293
 my-0.281
 our-0.252
 big-0.251
 new-0.251
Token
Token ID198
Feature activation+2.41e+00

Pos logit contributions
owing+0.252
oped+0.249
eled+0.240
idd+0.234
aring+0.231
Neg logit contributions
 your-0.173
 my-0.161
 the-0.142
 new-0.138
 big-0.138
Token
Token ID198
Feature activation+2.57e+00

Pos logit contributions
owing+0.083
oped+0.078
anged+0.076
ked+0.076
ement+0.075
Neg logit contributions
 your-0.048
 my-0.043
 the-0.042
 big-0.041
 new-0.039
TokenTom
Token ID13787
Feature activation+1.11e+01

Pos logit contributions
owing+0.068
oped+0.068
anged+0.063
oled+0.063
oling+0.062
Neg logit contributions
 your-0.064
 my-0.061
 our-0.055
 big-0.053
 same-0.052
Token She
Token ID1375
Feature activation+1.14e+00

Pos logit contributions
oped+0.161
owing+0.154
oled+0.151
oling+0.146
aring+0.145
Neg logit contributions
 your-0.175
 my-0.170
 our-0.157
 same-0.148
 new-0.148
Token loved
Token ID6151
Feature activation+1.59e+00

Pos logit contributions
oped+0.024
oled+0.022
owing+0.022
amb+0.022
ushed+0.022
Neg logit contributions
 your-0.031
 my-0.031
 our-0.029
 same-0.027
 new-0.027
Token playing
Token ID2712
Feature activation+5.36e+00

Pos logit contributions
owing+0.037
uts+0.036
amb+0.036
anged+0.036
ocular+0.035
Neg logit contributions
 my-0.031
 your-0.031
 same-0.029
 common-0.028
 our-0.028
Token outside
Token ID2354
Feature activation+3.86e+00

Pos logit contributions
oped+0.114
amb+0.114
owing+0.110
idd+0.109
aw+0.109
Neg logit contributions
 my-0.134
 your-0.133
 same-0.124
 our-0.124
 new-0.116
Token in
Token ID287
Feature activation-1.57e+01

Pos logit contributions
owing+0.082
amb+0.077
oped+0.076
iled+0.074
edly+0.073
Neg logit contributions
 your-0.095
 my-0.094
 our-0.089
 common-0.087
 same-0.086
Token the
Token ID262
Feature activation-2.39e+01

Pos logit contributions
 same+0.160
 your+0.154
 my+0.145
 task+0.143
 common+0.138
Neg logit contributions
eled-0.475
ipt-0.464
oped-0.446
idd-0.443
aw-0.441
Token mud
Token ID17492
Feature activation+1.15e+01

Pos logit contributions
 your+0.435
 my+0.422
 our+0.383
 common+0.337
 same+0.332
Neg logit contributions
aw-0.688
oped-0.654
owing-0.641
eled-0.639
ipt-0.631
Token and
Token ID290
Feature activation-5.39e+00

Pos logit contributions
oped+0.291
owing+0.285
oled+0.268
oling+0.264
anged+0.263
Neg logit contributions
 your-0.289
 my-0.282
 our-0.252
 same-0.245
 new-0.244
Token dirt
Token ID13647
Feature activation+9.87e+00

Pos logit contributions
 my+0.104
 your+0.101
 our+0.092
 common+0.090
 new+0.088
Neg logit contributions
owing-0.140
oped-0.139
eled-0.135
anged-0.133
ocular-0.129
Token.
Token ID13
Feature activation+6.17e+00

Pos logit contributions
oped+0.235
owing+0.228
oled+0.216
oling+0.212
aring+0.211
Neg logit contributions
 your-0.264
 my-0.257
 our-0.231
 same-0.229
 new-0.227
Token One
Token ID1881
Feature activation+1.90e+00

Pos logit contributions
oped+0.173
owing+0.169
oled+0.161
oling+0.159
aring+0.158
Neg logit contributions
 your-0.140
 my-0.136
 our-0.120
 same-0.117
 new-0.116
Token bikes
Token ID16715
Feature activation+1.12e+01

Pos logit contributions
oped+0.173
owing+0.171
oled+0.163
anged+0.162
amb+0.162
Neg logit contributions
 your-0.075
 my-0.072
 same-0.058
 our-0.058
 new-0.055
Token.
Token ID13
Feature activation+7.04e+00

Pos logit contributions
oped+0.331
oled+0.312
eled+0.304
oling+0.302
anged+0.301
Neg logit contributions
 your-0.267
 my-0.255
 new-0.240
 the-0.237
 big-0.235
Token They
Token ID1119
Feature activation+2.20e+00

Pos logit contributions
owing+0.205
oped+0.201
oled+0.185
anged+0.185
eled+0.182
Neg logit contributions
 your-0.170
 my-0.165
 our-0.149
 new-0.143
 big-0.141
Token run
Token ID1057
Feature activation+1.07e+01

Pos logit contributions
oped+0.063
owing+0.060
amb+0.059
oled+0.058
aring+0.057
Neg logit contributions
 your-0.046
 my-0.044
 our-0.039
 new-0.037
 same-0.036
Token to
Token ID284
Feature activation-1.41e+01

Pos logit contributions
oped+0.361
owing+0.358
oled+0.341
oling+0.340
unch+0.339
Neg logit contributions
 your-0.186
 my-0.177
 our-0.152
 new-0.148
 big-0.147
Token the
Token ID262
Feature activation-2.33e+01

Pos logit contributions
 your+0.111
 my+0.108
 our+0.065
 same+0.064
 big+0.050
Neg logit contributions
oped-0.553
owing-0.548
oled-0.529
anged-0.529
eled-0.527
Token box
Token ID3091
Feature activation+1.52e+01

Pos logit contributions
 your+0.443
 my+0.424
 our+0.362
 same+0.333
 new+0.326
Neg logit contributions
oped-0.701
owing-0.669
ocular-0.665
oled-0.655
idd-0.654
Token and
Token ID290
Feature activation-4.98e+00

Pos logit contributions
oped+0.441
owing+0.421
oled+0.415
oling+0.408
anged+0.399
Neg logit contributions
 your-0.339
 my-0.327
 new-0.291
 big-0.289
 same-0.288
Token grab
Token ID5552
Feature activation+4.18e+00

Pos logit contributions
 your+0.085
 my+0.084
 same+0.070
 our+0.070
 new+0.069
Neg logit contributions
oped-0.151
ocular-0.143
owing-0.142
anged-0.142
amb-0.138
Token a
Token ID257
Feature activation-1.45e+01

Pos logit contributions
oped+0.165
owing+0.164
oled+0.158
oling+0.157
aring+0.157
Neg logit contributions
 your-0.053
 my-0.050
 our-0.040
 the-0.039
 new-0.039
Token bike
Token ID7161
Feature activation+1.48e+01

Pos logit contributions
 your+0.248
 my+0.238
 our+0.201
 same+0.195
 new+0.192
Neg logit contributions
oped-0.485
owing-0.475
oled-0.456
oling-0.451
aring-0.449