TOP ACTIVATIONS
MAX = 1.361

. Source : Anonymous <|endoftext|> T AM PA ,
He points to another biblical account that uses this verb ,
. And at the last minute he called and said ,
out at http :// w ashington beer . com / w
Lot Better " ( B yr ds Cover ) ( via
easy : + -------------------- --+ | ... | -
sa ison made with S ich uan pe pperc orns (
that the reputation of S ich uan ese as leading slow
--+ + -------------------- --+ < -- Start of system () '
credentials -- prov ider aw s -- key < Access Key
ning said . Regardless of the competition results ,
--+ + -------------------- --+ < -- Special frame for pop /
Reviewer : V the Happy L ur ker - favorite
border . The earliest ancient texts from the region Mes
off of travel from Down Under ? Not something I would
) Mem c py In Memory 4 66 284 4 64
_ t count | < -- read () ' s frame
and reading guys . < 3 <|endoftext|> Are we all feeling
Despite enjoying a fair amount of possession and forcing
) R attle Snake : La N m is

MIN ACTIVATIONS
MIN = -1.824

: 13 PH OTOS Donald Trump 's potential running
mount ing demands . AFP PHOTO / Saul LO EB SA
racing toward extinction How Vera Rubin changed science
teach a new trick Dr one video captures
23 12 . e ce / edd 75 / AUT OC
e ce / edd 75 / AUT OC R OP /
a new trick Dr one video captures killer
bur . org / 2015 / 08 / 11 / e
an atom from Shakespeare ? Sl ime m olds
, singing a live du et of " The Rainbow Connection
Ker mit sing the du et " I Hope That S
ee pl inks / 2016 / 06 / t att oo
Vera Rubin changed science Dear Science : Could my
Hide Caption 7 of 15 Photos : Carly Fiorina 's political
gov / data / 2015 / acs 5 / profile ?
. Is it really likely that Amazon is going
atom from Shakespeare ? Sl ime m olds prove
of imper t inence for which no lady of delic acy
: 10 . 10 86 / 34 110 7
ground . com / 2016 / 09 / 08 / the

INTERVAL 0.565 - 1.361
CONTAINS 1.071%

and the word Dep ression , though
the complete story at Boston Gl obe . com .
owns Stan za so if you re looking
debate B ac ile 's movie does not excuse
llo said . " But if it were easy , anybody

INTERVAL -0.232 - 0.565
CONTAINS 84.174%

satire . Neither me or my supporters want rape to be
the corner . As you set out from the
this week would be his performance on the road this season
social media , and it 's a different path ," says
free agents . If they decide too quickly , they risk

INTERVAL -1.028 - -0.232
CONTAINS 14.738%

ia looked up . Her eyes were still red from cutting
It just creates a mapping onto the data that you provide
essay on the cover of Harper s , and
. The big hope is that the country can
s effortlessly imaginative , as are the sweeping back

INTERVAL -1.824 - -1.028
CONTAINS 0.017%

law , the Commission can fine companies found guilty of price
don t be afraid to send this post to
one of Lois G . Lerner s apparently lost
Pont and Dow Chemical were fined 59 . 3 m and
e ce / edd 75 / AUT OC R OP /
Token.
Token ID13
Feature activation-7.98e-03

Pos logit contributions
002+1.627
003+1.520
 Stretch+1.498
 Reef+1.497
662+1.462
Neg logit contributions
undai-1.509
ascus-1.425
ottesville-1.404
occup-1.377
iction-1.353
Token
Token ID198
Feature activation+7.14e-02

Pos logit contributions
002+0.029
003+0.027
 Reef+0.026
 Stretch+0.026
662+0.026
Neg logit contributions
undai-0.028
ascus-0.026
ottesville-0.026
occup-0.026
iction-0.026
Token
Token ID198
Feature activation+7.06e-02

Pos logit contributions
undai+0.201
occup+0.196
ottesville+0.193
ascus+0.191
iction+0.189
Neg logit contributions
002-0.294
 Stretch-0.276
 Reef-0.276
003-0.275
662-0.268
TokenSource
Token ID7416
Feature activation-2.25e-02

Pos logit contributions
undai+0.233
ascus+0.217
ottesville+0.216
occup+0.215
iction+0.210
Neg logit contributions
002-0.271
 Reef-0.255
 Stretch-0.255
003-0.254
 Dialogue-0.247
Token:
Token ID25
Feature activation+6.49e-01

Pos logit contributions
002+0.080
003+0.075
 Stretch+0.074
 Reef+0.074
662+0.072
Neg logit contributions
undai-0.082
ascus-0.077
ottesville-0.077
occup-0.075
iction-0.074
Token Anonymous
Token ID19200
Feature activation+1.36e+00

Pos logit contributions
undai+2.548
ascus+2.397
ottesville+2.369
occup+2.356
iction+2.337
Neg logit contributions
002-2.050
003-1.884
 Reef-1.859
 Stretch-1.846
662-1.826
Token<|endoftext|>
Token ID50256
Feature activation+2.16e-01

Pos logit contributions
undai+4.354
ascus+4.089
ottesville+4.058
occup+4.039
iction+4.020
Neg logit contributions
002-4.967
 Reef-4.668
 Stretch-4.665
003-4.641
662-4.538
TokenT
Token ID51
Feature activation+5.20e-01

Pos logit contributions
undai+0.728
ascus+0.688
occup+0.685
ottesville+0.678
iction+0.659
Neg logit contributions
002-0.802
 Stretch-0.759
 Reef-0.759
003-0.748
 Dialogue-0.732
TokenAM
Token ID2390
Feature activation+9.97e-03

Pos logit contributions
undai+1.916
ascus+1.823
ottesville+1.801
occup+1.777
iction+1.758
Neg logit contributions
002-1.805
003-1.664
 Reef-1.658
 Stretch-1.655
662-1.619
TokenPA
Token ID4537
Feature activation+4.89e-01

Pos logit contributions
undai+0.019
ascus+0.018
ottesville+0.017
occup+0.017
 assailant+0.016
Neg logit contributions
002-0.052
003-0.049
 Stretch-0.049
 Reef-0.049
662-0.048
Token,
Token ID11
Feature activation+1.81e-01

Pos logit contributions
undai+1.479
ottesville+1.396
ascus+1.391
occup+1.361
iction+1.356
Neg logit contributions
002-1.966
003-1.833
 Stretch-1.822
 Reef-1.803
662-1.793
Token He
Token ID679
Feature activation+2.68e-01

Pos logit contributions
undai+0.717
ottesville+0.692
occup+0.692
ascus+0.687
iction+0.683
Neg logit contributions
002-0.661
003-0.610
 Stretch-0.605
 Reef-0.605
662-0.594
Token points
Token ID2173
Feature activation+3.89e-01

Pos logit contributions
undai+0.857
ascus+0.816
ottesville+0.803
occup+0.793
iction+0.775
Neg logit contributions
002-1.054
003-0.986
 Stretch-0.981
 Reef-0.976
662-0.960
Token to
Token ID284
Feature activation+3.42e-01

Pos logit contributions
undai+1.326
ascus+1.268
ottesville+1.247
occup+1.224
iction+1.217
Neg logit contributions
002-1.439
003-1.334
 Stretch-1.328
 Reef-1.328
662-1.300
Token another
Token ID1194
Feature activation+2.90e-01

Pos logit contributions
undai+1.237
ascus+1.170
ottesville+1.141
occup+1.137
 assailant+1.127
Neg logit contributions
002-1.203
003-1.116
 Reef-1.088
 Stretch-1.087
662-1.083
Token biblical
Token ID24726
Feature activation+9.90e-01

Pos logit contributions
undai+0.960
ascus+0.910
 assailant+0.892
ottesville+0.883
occup+0.880
Neg logit contributions
002-1.113
003-1.038
 Reef-1.017
 Stretch-1.010
662-1.009
Token account
Token ID1848
Feature activation+1.29e+00

Pos logit contributions
undai+3.200
 assailant+3.080
ascus+3.043
 attacker+2.983
occup+2.967
Neg logit contributions
002-3.772
003-3.497
 Reef-3.412
 Stretch-3.397
662-3.395
Token that
Token ID326
Feature activation+4.20e-01

Pos logit contributions
undai+4.044
ascus+3.869
occup+3.831
 assailant+3.819
iction+3.797
Neg logit contributions
002-4.763
 Reef-4.463
 Stretch-4.463
003-4.452
662-4.354
Token uses
Token ID3544
Feature activation+2.32e-01

Pos logit contributions
undai+1.441
ascus+1.358
ottesville+1.337
occup+1.335
 assailant+1.324
Neg logit contributions
002-1.541
003-1.430
 Reef-1.405
662-1.402
 Stretch-1.397
Token this
Token ID428
Feature activation+1.83e-01

Pos logit contributions
undai+0.832
ascus+0.783
ottesville+0.756
occup+0.755
 assailant+0.754
Neg logit contributions
002-0.834
003-0.772
 Reef-0.761
 Stretch-0.757
662-0.754
Token verb
Token ID15942
Feature activation+6.27e-02

Pos logit contributions
undai+0.645
ascus+0.610
ottesville+0.596
 assailant+0.594
iction+0.592
Neg logit contributions
002-0.673
003-0.623
 Reef-0.611
 Stretch-0.608
662-0.606
Token,
Token ID11
Feature activation+1.46e-01

Pos logit contributions
undai+0.216
ascus+0.208
ottesville+0.203
occup+0.202
iction+0.199
Neg logit contributions
002-0.232
003-0.216
 Reef-0.215
 Stretch-0.213
662-0.209
Token.
Token ID13
Feature activation-1.33e-01

Pos logit contributions
002+0.681
003+0.635
 Stretch+0.623
 Reef+0.622
662+0.610
Neg logit contributions
undai-0.670
ascus-0.634
ottesville-0.625
occup-0.615
iction-0.603
Token And
Token ID843
Feature activation-1.83e-01

Pos logit contributions
002+0.430
003+0.399
 Reef+0.384
 Stretch+0.383
662+0.383
Neg logit contributions
undai-0.502
ottesville-0.483
occup-0.481
ascus-0.479
iction-0.474
Token at
Token ID379
Feature activation+2.71e-01

Pos logit contributions
002+0.677
003+0.633
 Stretch+0.615
 Reef+0.614
662+0.610
Neg logit contributions
undai-0.636
ascus-0.596
ottesville-0.586
occup-0.581
 assailant-0.579
Token the
Token ID262
Feature activation-1.31e-01

Pos logit contributions
undai+0.892
ascus+0.824
occup+0.817
ottesville+0.809
 assailant+0.803
Neg logit contributions
002-1.040
003-0.971
 Stretch-0.941
 Reef-0.940
662-0.929
Token last
Token ID938
Feature activation-3.73e-01

Pos logit contributions
002+0.452
003+0.420
 Stretch+0.404
 Reef+0.403
662+0.402
Neg logit contributions
undai-0.495
ascus-0.465
ottesville-0.460
occup-0.455
 assailant-0.454
Token minute
Token ID5664
Feature activation+1.22e+00

Pos logit contributions
002+1.592
003+1.501
 Stretch+1.476
 Reef+1.475
662+1.454
Neg logit contributions
undai-1.097
ascus-1.023
ottesville-1.013
occup-0.987
iction-0.971
Token he
Token ID339
Feature activation+4.77e-02

Pos logit contributions
undai+3.730
ascus+3.490
 assailant+3.482
ottesville+3.435
occup+3.410
Neg logit contributions
002-4.657
003-4.402
 Stretch-4.239
662-4.207
 Reef-4.185
Token called
Token ID1444
Feature activation-1.28e-01

Pos logit contributions
undai+0.163
ascus+0.154
ottesville+0.152
occup+0.149
 assailant+0.149
Neg logit contributions
002-0.180
003-0.169
 Stretch-0.165
 Reef-0.164
662-0.162
Token and
Token ID290
Feature activation+2.94e-01

Pos logit contributions
002+0.522
003+0.490
 Reef+0.477
 Stretch+0.475
662+0.474
Neg logit contributions
undai-0.391
ascus-0.373
ottesville-0.360
occup-0.359
 assailant-0.356
Token said
Token ID531
Feature activation+3.88e-01

Pos logit contributions
undai+0.938
ascus+0.889
ottesville+0.862
 assailant+0.859
occup+0.850
Neg logit contributions
002-1.164
003-1.089
 Reef-1.060
 Stretch-1.056
662-1.052
Token,
Token ID11
Feature activation+2.94e-01

Pos logit contributions
undai+1.279
ascus+1.203
ottesville+1.189
occup+1.189
 assailant+1.174
Neg logit contributions
002-1.460
003-1.366
662-1.323
 Reef-1.320
 Stretch-1.307
Token out
Token ID503
Feature activation+1.95e-01

Pos logit contributions
undai+1.137
ascus+1.077
ottesville+1.067
occup+1.043
iction+1.030
Neg logit contributions
002-1.321
003-1.225
 Reef-1.219
662-1.205
 Stretch-1.201
Token at
Token ID379
Feature activation+3.56e-01

Pos logit contributions
undai+0.648
ascus+0.610
ottesville+0.603
occup+0.596
iction+0.584
Neg logit contributions
002-0.743
003-0.695
 Reef-0.685
 Stretch-0.682
662-0.674
Token http
Token ID2638
Feature activation-4.75e-01

Pos logit contributions
undai+1.279
ascus+1.213
ottesville+1.206
occup+1.189
iction+1.161
Neg logit contributions
002-1.267
003-1.172
 Reef-1.141
 Stretch-1.135
662-1.133
Token://
Token ID1378
Feature activation-9.62e-02

Pos logit contributions
002+1.840
003+1.718
 Stretch+1.715
 Reef+1.715
662+1.662
Neg logit contributions
undai-1.539
ascus-1.457
ottesville-1.456
occup-1.436
iction-1.402
Tokenw
Token ID86
Feature activation+2.21e-01

Pos logit contributions
002+0.358
003+0.334
 Reef+0.333
 Stretch+0.331
 Dialogue+0.322
Neg logit contributions
undai-0.337
ascus-0.317
ottesville-0.314
occup-0.311
iction-0.302
Tokenashington
Token ID2542
Feature activation+1.20e+00

Pos logit contributions
undai+0.825
ascus+0.791
ottesville+0.778
occup+0.763
iction+0.751
Neg logit contributions
002-0.766
 Stretch-0.715
 Reef-0.711
003-0.710
 Dialogue-0.685
Tokenbeer
Token ID42428
Feature activation+5.56e-01

Pos logit contributions
undai+3.628
ascus+3.512
occup+3.398
ottesville+3.373
iction+3.304
Neg logit contributions
002-4.684
 Stretch-4.625
 Reef-4.535
 Transparency-4.408
003-4.391
Token.
Token ID13
Feature activation-4.63e-02

Pos logit contributions
undai+1.869
ascus+1.761
ottesville+1.730
occup+1.719
iction+1.689
Neg logit contributions
002-2.100
 Stretch-1.989
 Reef-1.982
003-1.966
 Dialogue-1.910
Tokencom
Token ID785
Feature activation-3.39e-02

Pos logit contributions
002+0.138
003+0.126
 Stretch+0.125
 Reef+0.125
662+0.120
Neg logit contributions
undai-0.196
ascus-0.187
ottesville-0.185
occup-0.183
iction-0.180
Token/
Token ID14
Feature activation-3.97e-01

Pos logit contributions
002+0.126
003+0.118
 Reef+0.116
 Stretch+0.116
662+0.114
Neg logit contributions
undai-0.117
ascus-0.111
ottesville-0.110
occup-0.108
iction-0.106
Tokenw
Token ID86
Feature activation-1.21e-01

Pos logit contributions
002+1.469
003+1.371
 Stretch+1.353
 Reef+1.352
662+1.320
Neg logit contributions
undai-1.394
ascus-1.317
ottesville-1.301
occup-1.277
iction-1.250
Token Lot
Token ID15099
Feature activation+4.33e-01

Pos logit contributions
002+1.820
003+1.678
 Stretch+1.604
 Reef+1.600
662+1.592
Neg logit contributions
undai-2.513
ascus-2.422
ottesville-2.387
occup-2.345
iction-2.309
Token Better
Token ID11625
Feature activation-2.74e-01

Pos logit contributions
undai+1.534
ascus+1.483
ottesville+1.462
occup+1.430
iction+1.418
Neg logit contributions
002-1.532
003-1.428
662-1.376
 Reef-1.370
 Stretch-1.335
Token"
Token ID1
Feature activation+1.62e-01

Pos logit contributions
002+0.977
003+0.911
 Stretch+0.884
 Reef+0.880
662+0.878
Neg logit contributions
undai-0.988
ascus-0.941
ottesville-0.925
occup-0.914
iction-0.904
Token (
Token ID357
Feature activation+1.51e-01

Pos logit contributions
undai+0.564
ascus+0.537
ottesville+0.527
occup+0.521
 assailant+0.517
Neg logit contributions
002-0.583
003-0.544
662-0.530
 Reef-0.526
 Stretch-0.524
TokenB
Token ID33
Feature activation+2.59e-01

Pos logit contributions
undai+0.558
ascus+0.529
occup+0.522
ottesville+0.519
iction+0.510
Neg logit contributions
002-0.515
 Reef-0.483
 Stretch-0.478
003-0.477
662-0.461
Tokenyr
Token ID2417
Feature activation+1.19e+00

Pos logit contributions
undai+0.970
ascus+0.921
ottesville+0.899
occup+0.888
iction+0.885
Neg logit contributions
002-0.872
 Stretch-0.820
 Reef-0.819
003-0.812
662-0.798
Tokends
Token ID9310
Feature activation+4.72e-01

Pos logit contributions
undai+3.478
ascus+3.210
ottesville+3.203
occup+3.015
iction+3.012
Neg logit contributions
002-4.996
003-4.731
 Stretch-4.628
 Reef-4.622
662-4.567
Token Cover
Token ID17546
Feature activation+4.10e-01

Pos logit contributions
undai+1.681
ascus+1.614
ottesville+1.587
iction+1.552
occup+1.550
Neg logit contributions
002-1.640
003-1.527
 Reef-1.507
 Stretch-1.492
662-1.485
Token)
Token ID8
Feature activation-1.25e-02

Pos logit contributions
undai+1.444
ascus+1.379
ottesville+1.364
iction+1.336
occup+1.329
Neg logit contributions
002-1.440
003-1.341
 Reef-1.316
662-1.309
 Stretch-1.292
Token (
Token ID357
Feature activation-1.28e-03

Pos logit contributions
002+0.048
003+0.045
 Reef+0.044
 Stretch+0.044
662+0.044
Neg logit contributions
undai-0.041
ascus-0.039
ottesville-0.038
occup-0.038
iction-0.037
Tokenvia
Token ID8869
Feature activation+2.78e-02

Pos logit contributions
002+0.004
 Reef+0.004
 Stretch+0.004
003+0.004
662+0.004
Neg logit contributions
undai-0.005
ascus-0.004
occup-0.004
ottesville-0.004
iction-0.004
Token easy
Token ID2562
Feature activation+5.51e-01

Pos logit contributions
002+1.105
003+1.033
 Reef+1.012
 Stretch+1.008
662+0.995
Neg logit contributions
undai-0.979
ascus-0.931
ottesville-0.917
occup-0.896
iction-0.886
Token:
Token ID25
Feature activation-1.64e-02

Pos logit contributions
undai+1.801
ascus+1.712
ottesville+1.680
occup+1.657
iction+1.641
Neg logit contributions
002-2.129
003-1.994
 Stretch-1.958
 Reef-1.958
662-1.924
Token
Token ID198
Feature activation+3.58e-01

Pos logit contributions
002+0.065
003+0.061
 Stretch+0.060
 Reef+0.060
662+0.059
Neg logit contributions
undai-0.053
ascus-0.049
ottesville-0.049
occup-0.048
iction-0.047
Token
Token ID198
Feature activation+3.91e-01

Pos logit contributions
undai+0.944
occup+0.940
ottesville+0.913
iction+0.905
ascus+0.890
Neg logit contributions
002-1.501
 Stretch-1.428
 Reef-1.419
003-1.409
DAQ-1.387
Token+
Token ID10
Feature activation+2.64e-02

Pos logit contributions
undai+1.377
ascus+1.292
occup+1.276
ottesville+1.274
iction+1.238
Neg logit contributions
002-1.406
 Stretch-1.326
 Reef-1.321
003-1.318
 Dialogue-1.284
Token--------------------
Token ID19351
Feature activation+1.18e+00

Pos logit contributions
undai+0.092
ascus+0.086
ottesville+0.086
occup+0.084
iction+0.083
Neg logit contributions
002-0.097
003-0.090
 Reef-0.090
 Stretch-0.090
662-0.088
Token--+
Token ID44785
Feature activation+6.13e-01

Pos logit contributions
undai+2.634
ascus+2.413
ottesville+2.395
occup+2.374
iction+2.287
Neg logit contributions
002-5.571
 Stretch-5.344
003-5.315
 Reef-5.291
662-5.222
Token |
Token ID930
Feature activation+3.53e-01

Pos logit contributions
undai+1.877
ascus+1.749
ottesville+1.732
occup+1.702
iction+1.681
Neg logit contributions
002-2.449
003-2.312
 Stretch-2.298
 Reef-2.297
662-2.263
Token...
Token ID2644
Feature activation+2.78e-01

Pos logit contributions
undai+1.309
ascus+1.233
ottesville+1.223
occup+1.213
iction+1.188
Neg logit contributions
002-1.204
003-1.123
 Reef-1.103
 Stretch-1.094
662-1.087
Token |
Token ID930
Feature activation+4.77e-01

Pos logit contributions
undai+0.855
ascus+0.802
ottesville+0.790
occup+0.782
iction+0.767
Neg logit contributions
002-1.120
003-1.056
 Reef-1.046
 Stretch-1.038
662-1.021
Token -
Token ID532
Feature activation+4.06e-01

Pos logit contributions
undai+1.464
ascus+1.360
ottesville+1.347
occup+1.338
iction+1.309
Neg logit contributions
002-1.912
003-1.805
 Reef-1.779
 Stretch-1.775
662-1.758
Token sa
Token ID473
Feature activation+4.30e-01

Pos logit contributions
undai+0.513
ascus+0.491
ottesville+0.477
 assailant+0.471
occup+0.469
Neg logit contributions
002-0.523
003-0.488
 Stretch-0.476
 Reef-0.474
662-0.471
Tokenison
Token ID1653
Feature activation-2.39e-01

Pos logit contributions
undai+1.331
ascus+1.248
ottesville+1.230
occup+1.212
iction+1.185
Neg logit contributions
002-1.745
003-1.653
 Stretch-1.645
 Reef-1.643
662-1.602
Token made
Token ID925
Feature activation-1.55e-01

Pos logit contributions
002+0.881
003+0.825
 Stretch+0.817
 Reef+0.812
662+0.794
Neg logit contributions
undai-0.826
ascus-0.797
ottesville-0.777
occup-0.766
 assailant-0.754
Token with
Token ID351
Feature activation-1.56e-01

Pos logit contributions
002+0.544
003+0.508
 Stretch+0.501
 Reef+0.499
662+0.484
Neg logit contributions
undai-0.570
ascus-0.543
ottesville-0.536
occup-0.529
 assailant-0.518
Token S
Token ID311
Feature activation+8.91e-02

Pos logit contributions
002+0.527
003+0.490
 Stretch+0.478
 Reef+0.474
662+0.470
Neg logit contributions
undai-0.590
ascus-0.569
ottesville-0.554
occup-0.542
 assailant-0.542
Tokenich
Token ID488
Feature activation+1.17e+00

Pos logit contributions
undai+0.309
ascus+0.297
ottesville+0.291
occup+0.284
iction+0.277
Neg logit contributions
002-0.330
003-0.309
 Stretch-0.308
 Reef-0.305
 Dialogue-0.299
Tokenuan
Token ID7258
Feature activation+3.63e-01

Pos logit contributions
undai+3.177
ascus+3.086
occup+2.933
ottesville+2.873
 assailant+2.777
Neg logit contributions
002-5.106
003-4.891
 Stretch-4.733
DAQ-4.660
 Reef-4.650
Token pe
Token ID613
Feature activation-8.01e-02

Pos logit contributions
undai+1.308
ascus+1.280
ottesville+1.218
occup+1.209
 assailant+1.197
Neg logit contributions
002-1.255
003-1.170
 Stretch-1.157
662-1.139
 Reef-1.136
Tokenpperc
Token ID39921
Feature activation-1.80e-01

Pos logit contributions
002+0.352
003+0.333
 Stretch+0.330
 Reef+0.328
662+0.322
Neg logit contributions
undai-0.226
ascus-0.211
ottesville-0.206
occup-0.202
iction-0.197
Tokenorns
Token ID19942
Feature activation+3.45e-02

Pos logit contributions
002+0.677
003+0.631
 Stretch+0.628
 Reef+0.619
662+0.607
Neg logit contributions
undai-0.623
ascus-0.589
ottesville-0.584
occup-0.569
iction-0.563
Token (
Token ID357
Feature activation-1.83e-01

Pos logit contributions
undai+0.121
ascus+0.115
ottesville+0.114
occup+0.111
 assailant+0.110
Neg logit contributions
002-0.126
003-0.118
 Stretch-0.116
 Reef-0.116
662-0.114
Token that
Token ID326
Feature activation+9.03e-02

Pos logit contributions
002+0.148
003+0.138
 Stretch+0.135
662+0.134
 Reef+0.134
Neg logit contributions
undai-0.147
ascus-0.138
ottesville-0.137
occup-0.136
 assailant-0.134
Token the
Token ID262
Feature activation+3.11e-01

Pos logit contributions
undai+0.315
ascus+0.301
ottesville+0.292
occup+0.291
iction+0.286
Neg logit contributions
002-0.331
003-0.310
 Stretch-0.303
662-0.300
 Reef-0.297
Token reputation
Token ID8507
Feature activation+4.46e-01

Pos logit contributions
undai+0.952
ascus+0.893
ottesville+0.872
occup+0.863
 assailant+0.858
Neg logit contributions
002-1.280
003-1.206
 Stretch-1.174
662-1.167
 Reef-1.160
Token of
Token ID286
Feature activation+2.46e-01

Pos logit contributions
undai+1.478
ascus+1.406
ottesville+1.369
occup+1.365
 assailant+1.346
Neg logit contributions
002-1.699
003-1.589
 Stretch-1.559
662-1.538
 Reef-1.529
Token S
Token ID311
Feature activation+9.48e-02

Pos logit contributions
undai+0.881
ascus+0.844
ottesville+0.817
occup+0.808
 assailant+0.795
Neg logit contributions
002-0.886
003-0.829
 Stretch-0.803
662-0.802
 Reef-0.791
Tokenich
Token ID488
Feature activation+1.16e+00

Pos logit contributions
undai+0.331
ascus+0.315
ottesville+0.310
occup+0.303
iction+0.296
Neg logit contributions
002-0.353
003-0.330
 Stretch-0.328
 Reef-0.325
662-0.319
Tokenuan
Token ID7258
Feature activation+3.82e-01

Pos logit contributions
undai+3.176
ascus+3.080
occup+2.931
ottesville+2.876
iction+2.809
Neg logit contributions
002-5.063
003-4.831
 Stretch-4.706
 Reef-4.643
662-4.631
Tokenese
Token ID2771
Feature activation-9.80e-03

Pos logit contributions
undai+1.298
ascus+1.237
ottesville+1.199
occup+1.193
iction+1.176
Neg logit contributions
002-1.440
003-1.345
 Stretch-1.327
662-1.314
 Reef-1.302
Token as
Token ID355
Feature activation+2.33e-02

Pos logit contributions
002+0.040
003+0.037
 Stretch+0.037
 Reef+0.036
662+0.036
Neg logit contributions
undai-0.031
ascus-0.029
ottesville-0.028
occup-0.028
iction-0.027
Token leading
Token ID3756
Feature activation+6.63e-02

Pos logit contributions
undai+0.081
ascus+0.077
ottesville+0.075
occup+0.074
 assailant+0.073
Neg logit contributions
002-0.087
003-0.081
 Stretch-0.080
 Reef-0.079
662-0.078
Token slow
Token ID3105
Feature activation+3.39e-01

Pos logit contributions
undai+0.229
ascus+0.218
ottesville+0.213
occup+0.210
 assailant+0.206
Neg logit contributions
002-0.248
003-0.232
 Stretch-0.228
 Reef-0.225
662-0.224
Token--+
Token ID44785
Feature activation+1.91e-01

Pos logit contributions
undai+0.391
ascus+0.301
ottesville+0.295
occup+0.276
iction+0.244
Neg logit contributions
002-3.064
 Stretch-2.957
 Reef-2.938
003-2.935
662-2.892
Token +
Token ID1343
Feature activation-1.85e-01

Pos logit contributions
undai+0.500
ascus+0.464
ottesville+0.456
occup+0.441
iction+0.430
Neg logit contributions
002-0.882
003-0.835
 Stretch-0.826
 Reef-0.824
662-0.810
Token--------------------
Token ID19351
Feature activation+3.09e-01

Pos logit contributions
002+0.730
 Stretch+0.686
003+0.685
 Reef+0.678
662+0.665
Neg logit contributions
undai-0.585
ascus-0.549
ottesville-0.548
occup-0.543
iction-0.531
Token--+
Token ID44785
Feature activation+2.09e-01

Pos logit contributions
undai+0.277
ascus+0.220
ottesville+0.212
occup+0.198
iction+0.177
Neg logit contributions
002-1.929
 Stretch-1.852
003-1.849
 Reef-1.841
662-1.818
Token <
Token ID1279
Feature activation+4.35e-01

Pos logit contributions
undai+0.627
ascus+0.583
ottesville+0.575
occup+0.567
iction+0.554
Neg logit contributions
002-0.873
003-0.822
 Reef-0.811
 Stretch-0.811
662-0.799
Token--
Token ID438
Feature activation+1.16e+00

Pos logit contributions
undai+0.924
occup+0.888
ottesville+0.840
ascus+0.822
iction+0.812
Neg logit contributions
002-2.087
 Reef-2.011
 Stretch-2.002
003-1.972
 Dialogue-1.951
Token Start
Token ID7253
Feature activation+3.46e-01

Pos logit contributions
undai+4.807
ascus+4.558
ottesville+4.554
occup+4.532
 attacker+4.494
Neg logit contributions
002-3.227
003-2.962
662-2.898
 Reef-2.795
 Stretch-2.709
Token of
Token ID286
Feature activation+1.11e-01

Pos logit contributions
undai+1.115
occup+1.075
ascus+1.064
ottesville+1.060
iction+1.042
Neg logit contributions
002-1.302
003-1.212
 Reef-1.202
 Stretch-1.201
662-1.178
Token system
Token ID1080
Feature activation+2.92e-01

Pos logit contributions
undai+0.364
ascus+0.343
ottesville+0.339
occup+0.330
iction+0.324
Neg logit contributions
002-0.439
003-0.412
 Stretch-0.407
 Reef-0.406
662-0.397
Token()
Token ID3419
Feature activation+1.55e-01

Pos logit contributions
undai+1.064
ottesville+1.014
ascus+1.013
occup+1.010
iction+0.998
Neg logit contributions
002-0.977
 Stretch-0.914
 Reef-0.914
003-0.912
 Dialogue-0.878
Token'
Token ID6
Feature activation+3.67e-01

Pos logit contributions
undai+0.497
occup+0.467
 assailant+0.466
 attacker+0.465
ascus+0.463
Neg logit contributions
002-0.588
003-0.554
 Reef-0.537
662-0.537
 Stretch-0.535
Token credentials
Token ID18031
Feature activation+3.71e-01

Pos logit contributions
002+0.451
003+0.423
 Reef+0.420
 Stretch+0.419
662+0.410
Neg logit contributions
undai-0.361
ascus-0.340
ottesville-0.334
occup-0.329
iction-0.321
Token --
Token ID1377
Feature activation+9.41e-01

Pos logit contributions
undai+1.195
ascus+1.137
ottesville+1.113
occup+1.102
iction+1.077
Neg logit contributions
002-1.444
003-1.350
 Reef-1.344
 Stretch-1.339
662-1.320
Tokenprov
Token ID15234
Feature activation+5.07e-01

Pos logit contributions
undai+3.294
occup+3.145
ascus+3.125
ottesville+3.056
iction+2.997
Neg logit contributions
002-3.299
 Reef-3.108
 Stretch-3.089
003-3.074
662-3.013
Tokenider
Token ID1304
Feature activation+4.85e-01

Pos logit contributions
undai+1.102
ascus+1.011
ottesville+0.974
occup+0.959
iction+0.945
Neg logit contributions
002-2.518
003-2.401
 Reef-2.395
 Stretch-2.388
662-2.352
Token aw
Token ID3253
Feature activation+7.55e-01

Pos logit contributions
undai+1.772
ascus+1.692
occup+1.660
ottesville+1.659
 assailant+1.617
Neg logit contributions
002-1.671
003-1.548
 Reef-1.536
 Stretch-1.525
662-1.506
Tokens
Token ID82
Feature activation+1.15e+00

Pos logit contributions
undai+2.859
ascus+2.725
occup+2.653
ottesville+2.591
iction+2.558
Neg logit contributions
002-2.472
 Reef-2.341
 Stretch-2.305
 Dialogue-2.279
003-2.268
Token --
Token ID1377
Feature activation+1.05e+00

Pos logit contributions
undai+3.775
ascus+3.628
occup+3.607
ottesville+3.529
 attacker+3.528
Neg logit contributions
002-4.144
 Reef-3.979
 Stretch-3.908
 Dialogue-3.864
003-3.843
Tokenkey
Token ID2539
Feature activation+6.00e-02

Pos logit contributions
undai+3.603
occup+3.469
ascus+3.402
ottesville+3.329
iction+3.246
Neg logit contributions
002-3.758
 Reef-3.583
 Stretch-3.536
003-3.508
662-3.447
Token <
Token ID1279
Feature activation+8.41e-01

Pos logit contributions
undai+0.209
ascus+0.199
ottesville+0.196
occup+0.194
 assailant+0.190
Neg logit contributions
002-0.220
003-0.205
 Reef-0.203
 Stretch-0.203
662-0.201
TokenAccess
Token ID15457
Feature activation+4.85e-01

Pos logit contributions
undai+2.798
occup+2.698
ascus+2.665
ottesville+2.612
 assailant+2.586
Neg logit contributions
002-3.108
 Reef-2.900
003-2.893
 Stretch-2.887
662-2.821
Token Key
Token ID7383
Feature activation+3.15e-01

Pos logit contributions
undai+1.844
ascus+1.757
ottesville+1.733
occup+1.717
iction+1.694
Neg logit contributions
002-1.608
003-1.494
 Reef-1.469
 Stretch-1.466
662-1.435
Tokenning
Token ID768
Feature activation+2.77e-02

Pos logit contributions
002+0.590
003+0.546
 Stretch+0.540
 Reef+0.535
662+0.525
Neg logit contributions
undai-0.696
ascus-0.662
ottesville-0.651
occup-0.648
iction-0.633
Token said
Token ID531
Feature activation-3.70e-02

Pos logit contributions
undai+0.092
ascus+0.087
ottesville+0.086
occup+0.085
iction+0.083
Neg logit contributions
002-0.106
003-0.099
 Reef-0.098
 Stretch-0.098
662-0.096
Token.
Token ID13
Feature activation+2.03e-02

Pos logit contributions
002+0.139
003+0.130
 Stretch+0.128
 Reef+0.128
662+0.125
Neg logit contributions
undai-0.128
ascus-0.121
ottesville-0.120
occup-0.117
iction-0.115
Token
Token ID564
Feature activation+2.86e-02

Pos logit contributions
undai+0.077
ottesville+0.074
ascus+0.073
occup+0.073
iction+0.071
Neg logit contributions
002-0.067
003-0.061
 Stretch-0.061
 Reef-0.060
662-0.059
Token
Token ID250
Feature activation+1.48e-01

Pos logit contributions
undai+0.126
ottesville+0.121
occup+0.120
ascus+0.118
iction+0.118
Neg logit contributions
002-0.075
 Stretch-0.068
003-0.068
 Reef-0.068
662-0.065
TokenRegardless
Token ID27894
Feature activation+1.15e+00

Pos logit contributions
undai+0.455
ottesville+0.426
occup+0.425
ascus+0.424
iction+0.411
Neg logit contributions
002-0.593
 Reef-0.561
 Stretch-0.560
003-0.556
662-0.537
Token of
Token ID286
Feature activation+4.52e-01

Pos logit contributions
undai+3.851
ottesville+3.600
ascus+3.599
occup+3.574
iction+3.495
Neg logit contributions
002-4.271
003-3.968
 Stretch-3.947
 Reef-3.944
662-3.854
Token the
Token ID262
Feature activation+2.43e-01

Pos logit contributions
undai+1.482
ascus+1.391
occup+1.373
ottesville+1.373
 assailant+1.369
Neg logit contributions
002-1.731
003-1.621
662-1.592
 Reef-1.582
 Stretch-1.582
Token competition
Token ID5449
Feature activation+3.16e-01

Pos logit contributions
undai+0.826
ascus+0.776
ottesville+0.771
 assailant+0.761
occup+0.753
Neg logit contributions
002-0.912
003-0.855
 Stretch-0.833
 Reef-0.831
662-0.830
Token results
Token ID2482
Feature activation-4.02e-02

Pos logit contributions
undai+1.090
ascus+1.036
ottesville+1.030
occup+1.018
iction+1.005
Neg logit contributions
002-1.162
003-1.087
 Reef-1.061
 Stretch-1.058
662-1.050
Token,
Token ID11
Feature activation+3.99e-02

Pos logit contributions
002+0.147
003+0.137
 Stretch+0.136
 Reef+0.135
662+0.133
Neg logit contributions
undai-0.141
ascus-0.134
ottesville-0.133
occup-0.131
iction-0.129
Token--+
Token ID44785
Feature activation+2.28e-01

Pos logit contributions
undai+0.371
ascus+0.291
ottesville+0.287
occup+0.265
iction+0.236
Neg logit contributions
002-2.757
 Stretch-2.654
003-2.641
 Reef-2.635
662-2.599
Token +
Token ID1343
Feature activation-1.15e-01

Pos logit contributions
undai+0.448
occup+0.420
ottesville+0.410
ascus+0.408
iction+0.404
Neg logit contributions
002-1.134
003-1.079
 Reef-1.067
 Stretch-1.065
662-1.051
Token--------------------
Token ID19351
Feature activation+2.94e-01

Pos logit contributions
002+0.458
 Stretch+0.432
003+0.430
 Reef+0.425
662+0.418
Neg logit contributions
undai-0.359
ottesville-0.337
ascus-0.337
occup-0.336
iction-0.328
Token--+
Token ID44785
Feature activation+1.77e-01

Pos logit contributions
undai+0.267
ascus+0.214
ottesville+0.207
occup+0.192
iction+0.173
Neg logit contributions
002-1.829
 Stretch-1.755
003-1.753
 Reef-1.745
662-1.723
Token <
Token ID1279
Feature activation+3.84e-01

Pos logit contributions
undai+0.543
ascus+0.508
ottesville+0.502
occup+0.489
iction+0.478
Neg logit contributions
002-0.738
003-0.694
 Stretch-0.686
 Reef-0.684
662-0.671
Token--
Token ID438
Feature activation+1.15e+00

Pos logit contributions
undai+0.784
occup+0.766
ottesville+0.727
iction+0.706
ascus+0.703
Neg logit contributions
002-1.850
 Reef-1.782
 Stretch-1.774
003-1.748
 Dialogue-1.733
Token Special
Token ID6093
Feature activation+3.81e-01

Pos logit contributions
undai+4.153
ottesville+3.931
occup+3.918
ascus+3.917
iction+3.848
Neg logit contributions
002-3.868
003-3.616
662-3.509
 Reef-3.396
 Stretch-3.266
Token frame
Token ID5739
Feature activation+1.60e-01

Pos logit contributions
undai+1.291
ascus+1.213
ottesville+1.205
occup+1.187
iction+1.174
Neg logit contributions
002-1.441
003-1.351
 Reef-1.312
 Stretch-1.305
662-1.297
Token for
Token ID329
Feature activation+2.95e-02

Pos logit contributions
undai+0.531
ascus+0.502
ottesville+0.493
occup+0.491
 assailant+0.484
Neg logit contributions
002-0.612
003-0.575
 Reef-0.565
 Stretch-0.565
662-0.556
Token pop
Token ID1461
Feature activation-1.47e-01

Pos logit contributions
undai+0.101
ascus+0.094
ottesville+0.093
occup+0.092
 assailant+0.091
Neg logit contributions
002-0.111
003-0.104
 Reef-0.102
 Stretch-0.102
662-0.101
Token/
Token ID14
Feature activation-1.33e-02

Pos logit contributions
002+0.545
003+0.509
 Stretch+0.502
 Reef+0.501
662+0.490
Neg logit contributions
undai-0.516
ascus-0.489
ottesville-0.482
occup-0.472
iction-0.464
Token
Token ID198
Feature activation-4.05e-01

Pos logit contributions
002+1.355
003+1.271
 Stretch+1.263
 Reef+1.260
662+1.231
Neg logit contributions
undai-1.046
ottesville-0.987
ascus-0.985
occup-0.978
iction-0.954
TokenReviewer
Token ID35407
Feature activation-1.07e+00

Pos logit contributions
002+1.910
003+1.813
 Stretch+1.807
 Reef+1.801
662+1.761
Neg logit contributions
undai-1.003
ascus-0.920
ottesville-0.909
occup-0.891
iction-0.862
Token:
Token ID25
Feature activation-4.73e-02

Pos logit contributions
002+3.545
003+3.287
 Stretch+3.213
 Reef+3.191
662+3.136
Neg logit contributions
undai-4.285
ascus-4.069
ottesville-3.993
occup-3.886
 assailant-3.841
Token V
Token ID569
Feature activation+2.02e-01

Pos logit contributions
002+0.166
003+0.155
 Stretch+0.150
 Reef+0.150
662+0.149
Neg logit contributions
undai-0.174
ascus-0.165
ottesville-0.163
occup-0.160
 assailant-0.158
Tokenthe
Token ID1169
Feature activation+2.07e-01

Pos logit contributions
undai+0.740
ascus+0.699
ottesville+0.686
occup+0.676
iction+0.669
Neg logit contributions
002-0.713
003-0.663
 Stretch-0.662
 Reef-0.658
662-0.640
TokenHappy
Token ID25082
Feature activation+1.15e+00

Pos logit contributions
undai+0.762
ascus+0.721
ottesville+0.714
occup+0.703
iction+0.690
Neg logit contributions
002-0.722
 Stretch-0.674
003-0.673
 Reef-0.668
662-0.648
TokenL
Token ID43
Feature activation+6.62e-01

Pos logit contributions
undai+4.014
ottesville+3.776
ascus+3.769
occup+3.748
iction+3.699
Neg logit contributions
002-3.898
003-3.668
 Stretch-3.644
 Reef-3.634
 Dialogue-3.549
Tokenur
Token ID333
Feature activation+4.90e-01

Pos logit contributions
undai+2.309
ascus+2.190
ottesville+2.164
occup+2.109
iction+2.093
Neg logit contributions
002-2.402
 Stretch-2.260
 Reef-2.253
003-2.253
 Dialogue-2.178
Tokenker
Token ID6122
Feature activation+7.62e-02

Pos logit contributions
undai+1.262
ascus+1.164
ottesville+1.127
occup+1.110
iction+1.076
Neg logit contributions
002-2.266
003-2.150
 Reef-2.124
 Stretch-2.121
662-2.087
Token -
Token ID532
Feature activation+4.02e-01

Pos logit contributions
undai+0.212
ascus+0.197
ottesville+0.195
occup+0.189
iction+0.185
Neg logit contributions
002-0.337
003-0.318
 Stretch-0.315
 Reef-0.314
662-0.308
Token favorite
Token ID4004
Feature activation+5.01e-01

Pos logit contributions
undai+1.060
ascus+1.001
ottesville+0.974
occup+0.970
iction+0.961
Neg logit contributions
002-1.772
003-1.670
 Stretch-1.646
 Reef-1.639
662-1.610
Token border
Token ID4865
Feature activation+7.40e-02

Pos logit contributions
undai+0.601
ascus+0.575
ottesville+0.561
occup+0.555
 assailant+0.549
Neg logit contributions
002-0.699
003-0.653
662-0.632
 Stretch-0.632
 Reef-0.632
Token.
Token ID13
Feature activation+7.90e-02

Pos logit contributions
undai+0.256
ascus+0.244
ottesville+0.240
occup+0.240
iction+0.233
Neg logit contributions
002-0.273
003-0.256
 Stretch-0.250
 Reef-0.249
662-0.246
Token The
Token ID383
Feature activation+9.33e-02

Pos logit contributions
undai+0.281
occup+0.271
ascus+0.271
ottesville+0.271
iction+0.267
Neg logit contributions
002-0.268
003-0.249
 Reef-0.240
662-0.240
 Stretch-0.239
Token earliest
Token ID14555
Feature activation+1.22e-01

Pos logit contributions
undai+0.323
ascus+0.306
occup+0.298
ottesville+0.298
 assailant+0.296
Neg logit contributions
002-0.345
003-0.322
 Stretch-0.312
 Reef-0.312
662-0.311
Token ancient
Token ID6156
Feature activation+3.72e-01

Pos logit contributions
undai+0.416
ascus+0.400
ottesville+0.388
occup+0.387
 assailant+0.385
Neg logit contributions
002-0.453
003-0.422
 Reef-0.410
 Stretch-0.409
662-0.407
Token texts
Token ID13399
Feature activation+1.14e+00

Pos logit contributions
undai+1.265
ascus+1.206
occup+1.177
 assailant+1.175
ottesville+1.174
Neg logit contributions
002-1.383
003-1.287
 Stretch-1.251
 Reef-1.247
662-1.243
Token from
Token ID422
Feature activation+3.94e-01

Pos logit contributions
undai+3.616
ascus+3.481
occup+3.479
iction+3.412
ottesville+3.349
Neg logit contributions
002-4.217
003-3.934
 Reef-3.920
 Stretch-3.904
DAQ-3.887
Token the
Token ID262
Feature activation+1.19e-01

Pos logit contributions
undai+1.424
ascus+1.378
occup+1.335
ottesville+1.321
 assailant+1.310
Neg logit contributions
002-1.371
003-1.275
 Reef-1.243
 Stretch-1.238
662-1.236
Token region
Token ID3814
Feature activation+3.97e-02

Pos logit contributions
undai+0.447
ascus+0.429
ottesville+0.417
occup+0.415
 assailant+0.413
Neg logit contributions
002-0.403
003-0.373
 Stretch-0.363
 Reef-0.362
662-0.360
Token
Token ID784
Feature activation+2.92e-01

Pos logit contributions
undai+0.137
ascus+0.131
ottesville+0.129
occup+0.128
iction+0.126
Neg logit contributions
002-0.147
003-0.137
 Reef-0.136
 Stretch-0.135
662-0.132
Token Mes
Token ID14937
Feature activation+3.33e-01

Pos logit contributions
undai+1.011
ascus+0.969
ottesville+0.939
occup+0.936
iction+0.926
Neg logit contributions
002-1.065
003-0.995
 Stretch-0.983
 Reef-0.977
662-0.955
Token off
Token ID572
Feature activation-2.96e-01

Pos logit contributions
002+0.710
003+0.660
 Stretch+0.654
 Reef+0.648
662+0.633
Neg logit contributions
undai-0.727
ascus-0.690
ottesville-0.676
occup-0.667
iction-0.654
Token of
Token ID286
Feature activation-3.41e-01

Pos logit contributions
002+1.063
003+0.989
 Reef+0.973
 Stretch+0.972
662+0.951
Neg logit contributions
undai-1.072
ascus-1.014
ottesville-0.996
occup-0.984
iction-0.963
Token travel
Token ID3067
Feature activation+4.97e-02

Pos logit contributions
002+1.225
003+1.142
 Stretch+1.115
 Reef+1.113
662+1.097
Neg logit contributions
undai-1.244
ascus-1.172
ottesville-1.150
occup-1.139
iction-1.114
Token from
Token ID422
Feature activation-1.02e-01

Pos logit contributions
undai+0.168
ascus+0.161
ottesville+0.158
occup+0.155
iction+0.154
Neg logit contributions
002-0.189
003-0.176
 Reef-0.174
 Stretch-0.172
662-0.169
Token Down
Token ID5588
Feature activation-1.24e-01

Pos logit contributions
002+0.353
003+0.328
 Stretch+0.319
 Reef+0.318
662+0.314
Neg logit contributions
undai-0.380
ascus-0.364
ottesville-0.353
occup-0.351
 assailant-0.345
Token Under
Token ID4698
Feature activation+1.13e+00

Pos logit contributions
002+0.415
003+0.389
 Stretch+0.379
662+0.376
 Reef+0.371
Neg logit contributions
undai-0.468
ascus-0.455
ottesville-0.447
occup-0.433
 assailant-0.426
Token?
Token ID30
Feature activation+5.16e-02

Pos logit contributions
undai+3.473
ascus+3.297
ottesville+3.221
iction+3.185
occup+3.175
Neg logit contributions
002-4.330
003-4.083
 Stretch-3.981
 Reef-3.957
662-3.952
Token Not
Token ID1892
Feature activation-1.53e-01

Pos logit contributions
undai+0.193
ottesville+0.184
ascus+0.183
occup+0.181
iction+0.180
Neg logit contributions
002-0.170
003-0.157
 Reef-0.152
 Stretch-0.152
662-0.151
Token something
Token ID1223
Feature activation+3.50e-02

Pos logit contributions
002+0.579
003+0.541
 Stretch+0.529
 Reef+0.528
662+0.519
Neg logit contributions
undai-0.532
ascus-0.499
ottesville-0.489
occup-0.479
iction-0.478
Token I
Token ID314
Feature activation-4.69e-01

Pos logit contributions
undai+0.120
ascus+0.114
ottesville+0.111
occup+0.110
iction+0.110
Neg logit contributions
002-0.131
003-0.122
 Stretch-0.118
662-0.117
 Reef-0.116
Token would
Token ID561
Feature activation+2.10e-01

Pos logit contributions
002+1.865
003+1.751
 Stretch+1.725
 Reef+1.719
662+1.688
Neg logit contributions
undai-1.522
ascus-1.435
ottesville-1.408
occup-1.385
iction-1.356
Token)
Token ID8
Feature activation+7.11e-01

Pos logit contributions
undai+1.371
ascus+1.294
ottesville+1.277
occup+1.256
iction+1.240
Neg logit contributions
002-1.418
003-1.319
 Reef-1.318
 Stretch-1.303
662-1.275
Token Mem
Token ID4942
Feature activation+7.84e-01

Pos logit contributions
undai+2.643
ascus+2.524
ottesville+2.488
occup+2.481
iction+2.453
Neg logit contributions
002-2.340
003-2.182
 Reef-2.132
 Stretch-2.090
662-2.076
Tokenc
Token ID66
Feature activation+1.07e-01

Pos logit contributions
undai+2.860
ascus+2.765
ottesville+2.666
occup+2.657
iction+2.641
Neg logit contributions
002-2.672
 Reef-2.505
003-2.481
 Stretch-2.429
 Dialogue-2.394
Tokenpy
Token ID9078
Feature activation+1.38e-01

Pos logit contributions
undai+0.172
ascus+0.157
ottesville+0.151
occup+0.140
iction+0.136
Neg logit contributions
002-0.592
003-0.566
 Reef-0.563
 Stretch-0.563
 Dialogue-0.554
TokenIn
Token ID818
Feature activation+3.47e-01

Pos logit contributions
undai+0.522
ascus+0.501
ottesville+0.493
occup+0.486
iction+0.481
Neg logit contributions
002-0.464
003-0.431
 Reef-0.425
 Stretch-0.420
662-0.413
TokenMemory
Token ID30871
Feature activation+1.13e+00

Pos logit contributions
undai+1.238
ascus+1.168
ottesville+1.167
occup+1.145
iction+1.123
Neg logit contributions
002-1.246
003-1.163
 Reef-1.151
 Stretch-1.138
662-1.121
Token 4
Token ID604
Feature activation+3.24e-01

Pos logit contributions
undai+4.002
ascus+3.857
ottesville+3.799
occup+3.767
iction+3.719
Neg logit contributions
002-3.838
 Reef-3.570
003-3.565
 Stretch-3.444
 Dialogue-3.413
Token66
Token ID2791
Feature activation-1.84e-01

Pos logit contributions
undai+1.257
ascus+1.202
ottesville+1.190
occup+1.173
iction+1.171
Neg logit contributions
002-1.037
 Reef-0.954
003-0.953
 Stretch-0.942
 Dialogue-0.918
Token284
Token ID30336
Feature activation-3.31e-01

Pos logit contributions
002+0.588
003+0.544
 Reef+0.541
 Stretch+0.540
 Dialogue+0.521
Neg logit contributions
undai-0.725
ascus-0.691
ottesville-0.685
occup-0.673
iction-0.665
Token 4
Token ID604
Feature activation+8.24e-02

Pos logit contributions
002+1.082
003+1.001
 Reef+0.987
 Stretch+0.986
662+0.955
Neg logit contributions
undai-1.301
ascus-1.237
ottesville-1.224
occup-1.202
iction-1.187
Token64
Token ID2414
Feature activation-3.34e-01

Pos logit contributions
undai+0.360
ascus+0.347
ottesville+0.345
occup+0.339
iction+0.338
Neg logit contributions
002-0.225
 Reef-0.203
003-0.203
 Stretch-0.200
 Dialogue-0.193
Token_
Token ID62
Feature activation+3.21e-01

Pos logit contributions
undai+0.504
occup+0.486
ottesville+0.483
ascus+0.481
iction+0.478
Neg logit contributions
002-0.366
003-0.335
 Stretch-0.335
 Reef-0.332
 Dialogue-0.319
Tokent
Token ID83
Feature activation-6.54e-03

Pos logit contributions
undai+1.002
occup+0.946
ascus+0.931
ottesville+0.929
iction+0.906
Neg logit contributions
002-1.272
 Stretch-1.207
 Reef-1.205
003-1.192
 Dialogue-1.171
Token count
Token ID954
Feature activation+1.18e-01

Pos logit contributions
002+0.019
003+0.017
 Stretch+0.017
 Reef+0.017
662+0.017
Neg logit contributions
undai-0.028
ascus-0.027
ottesville-0.027
occup-0.026
iction-0.026
Token |
Token ID930
Feature activation+5.94e-01

Pos logit contributions
undai+0.338
occup+0.320
ascus+0.319
ottesville+0.317
iction+0.309
Neg logit contributions
002-0.492
003-0.462
 Stretch-0.460
 Reef-0.459
662-0.449
Token <
Token ID1279
Feature activation+4.06e-01

Pos logit contributions
undai+1.411
ascus+1.293
ottesville+1.274
occup+1.240
iction+1.201
Neg logit contributions
002-2.861
003-2.718
 Stretch-2.687
 Reef-2.680
662-2.641
Token--
Token ID438
Feature activation+1.12e+00

Pos logit contributions
undai+1.086
ascus+1.006
ottesville+0.993
occup+0.965
iction+0.939
Neg logit contributions
002-1.840
003-1.741
 Stretch-1.723
 Reef-1.719
662-1.689
Token read
Token ID1100
Feature activation+4.10e-01

Pos logit contributions
undai+4.078
occup+3.851
 attacker+3.835
ascus+3.831
 assailant+3.807
Neg logit contributions
002-3.705
003-3.465
662-3.358
 Reef-3.283
 Stretch-3.217
Token()
Token ID3419
Feature activation+8.01e-02

Pos logit contributions
undai+1.507
ascus+1.430
ottesville+1.421
occup+1.404
 assailant+1.375
Neg logit contributions
002-1.426
003-1.337
 Reef-1.310
 Stretch-1.301
662-1.278
Token'
Token ID6
Feature activation+2.73e-01

Pos logit contributions
undai+0.274
ascus+0.259
ottesville+0.257
occup+0.253
iction+0.249
Neg logit contributions
002-0.301
003-0.283
 Reef-0.276
 Stretch-0.275
662-0.272
Tokens
Token ID82
Feature activation+1.09e-01

Pos logit contributions
undai+1.083
occup+1.036
ascus+1.033
ottesville+1.026
iction+1.009
Neg logit contributions
002-0.843
003-0.779
 Reef-0.772
 Stretch-0.772
662-0.750
Token frame
Token ID5739
Feature activation+2.25e-01

Pos logit contributions
undai+0.397
ascus+0.376
ottesville+0.372
occup+0.367
 assailant+0.361
Neg logit contributions
002-0.388
003-0.363
 Reef-0.353
 Stretch-0.352
662-0.347
Token and
Token ID290
Feature activation+1.82e-01

Pos logit contributions
undai+0.794
ascus+0.752
ottesville+0.742
occup+0.734
iction+0.726
Neg logit contributions
002-0.843
003-0.787
 Reef-0.772
 Stretch-0.769
662-0.757
Token reading
Token ID3555
Feature activation+3.11e-01

Pos logit contributions
undai+0.602
ascus+0.562
ottesville+0.560
occup+0.558
iction+0.552
Neg logit contributions
002-0.694
003-0.645
 Reef-0.629
662-0.626
 Stretch-0.619
Token guys
Token ID3730
Feature activation+1.19e-01

Pos logit contributions
undai+1.041
ascus+0.983
ottesville+0.974
occup+0.958
iction+0.950
Neg logit contributions
002-1.182
003-1.105
 Reef-1.088
 Stretch-1.082
662-1.067
Token.
Token ID13
Feature activation+9.91e-02

Pos logit contributions
undai+0.404
ascus+0.382
ottesville+0.377
occup+0.370
iction+0.364
Neg logit contributions
002-0.450
003-0.421
 Reef-0.416
 Stretch-0.415
662-0.406
Token <
Token ID1279
Feature activation+4.79e-01

Pos logit contributions
undai+0.342
ottesville+0.327
ascus+0.325
occup+0.321
iction+0.317
Neg logit contributions
002-0.358
003-0.334
 Reef-0.330
 Stretch-0.327
662-0.322
Token3
Token ID18
Feature activation+1.11e+00

Pos logit contributions
undai+2.074
ottesville+2.011
ascus+1.994
occup+1.982
iction+1.967
Neg logit contributions
002-1.277
 Reef-1.143
 Stretch-1.140
003-1.117
662-1.105
Token<|endoftext|>
Token ID50256
Feature activation+1.57e-01

Pos logit contributions
undai+3.467
ottesville+3.291
ascus+3.262
occup+3.241
iction+3.217
Neg logit contributions
002-4.199
003-3.931
 Reef-3.893
 Stretch-3.851
662-3.814
TokenAre
Token ID8491
Feature activation-4.87e-01

Pos logit contributions
undai+0.532
ascus+0.501
occup+0.499
ottesville+0.495
iction+0.480
Neg logit contributions
002-0.585
 Stretch-0.552
 Reef-0.552
003-0.546
 Dialogue-0.533
Token we
Token ID356
Feature activation-4.12e-02

Pos logit contributions
002+1.924
003+1.807
 Stretch+1.775
 Reef+1.769
662+1.743
Neg logit contributions
undai-1.599
ascus-1.502
ottesville-1.487
occup-1.456
iction-1.419
Token all
Token ID477
Feature activation+6.93e-03

Pos logit contributions
002+0.155
003+0.145
 Stretch+0.141
 Reef+0.140
662+0.140
Neg logit contributions
undai-0.141
ascus-0.133
ottesville-0.130
occup-0.130
 assailant-0.128
Token feeling
Token ID4203
Feature activation+1.64e-01

Pos logit contributions
undai+0.024
ascus+0.022
ottesville+0.022
occup+0.021
 assailant+0.021
Neg logit contributions
002-0.026
003-0.025
 Stretch-0.024
662-0.024
 Reef-0.024
Token
Token ID198
Feature activation+4.32e-01

Pos logit contributions
undai+0.286
ascus+0.273
ottesville+0.272
occup+0.266
iction+0.263
Neg logit contributions
002-0.321
003-0.300
 Reef-0.293
 Stretch-0.292
662-0.291
Token
Token ID198
Feature activation+3.75e-01

Pos logit contributions
occup+1.118
undai+1.111
ottesville+1.080
iction+1.072
ascus+1.055
Neg logit contributions
002-1.816
 Stretch-1.715
 Reef-1.708
003-1.706
DAQ-1.685
TokenDespite
Token ID8332
Feature activation+1.49e-01

Pos logit contributions
undai+1.157
occup+1.089
ottesville+1.083
ascus+1.083
iction+1.051
Neg logit contributions
002-1.476
 Stretch-1.405
 Reef-1.403
003-1.389
 Dialogue-1.361
Token enjoying
Token ID13226
Feature activation+9.21e-02

Pos logit contributions
undai+0.524
ascus+0.494
ottesville+0.483
occup+0.479
 assailant+0.477
Neg logit contributions
002-0.541
003-0.507
 Stretch-0.496
 Reef-0.494
662-0.490
Token a
Token ID257
Feature activation+2.96e-01

Pos logit contributions
undai+0.322
ascus+0.303
ottesville+0.299
 assailant+0.293
occup+0.292
Neg logit contributions
002-0.341
003-0.319
 Stretch-0.311
 Reef-0.310
662-0.306
Token fair
Token ID3148
Feature activation+1.11e+00

Pos logit contributions
undai+1.034
ascus+0.980
ottesville+0.956
occup+0.943
 assailant+0.942
Neg logit contributions
002-1.094
003-1.023
 Stretch-0.995
 Reef-0.991
662-0.987
Token amount
Token ID2033
Feature activation+2.49e-01

Pos logit contributions
undai+3.408
ascus+3.120
ottesville+3.117
occup+3.100
 assailant+3.052
Neg logit contributions
002-4.463
003-4.225
 Stretch-4.057
662-4.054
 Reef-4.025
Token of
Token ID286
Feature activation+2.16e-01

Pos logit contributions
undai+0.955
ascus+0.906
ottesville+0.898
occup+0.878
iction+0.860
Neg logit contributions
002-0.843
003-0.781
 Stretch-0.771
 Reef-0.771
662-0.750
Token possession
Token ID7797
Feature activation+3.33e-01

Pos logit contributions
undai+0.730
ascus+0.692
ottesville+0.676
 assailant+0.667
occup+0.663
Neg logit contributions
002-0.825
003-0.774
 Stretch-0.751
 Reef-0.749
662-0.744
Token and
Token ID290
Feature activation-1.28e-01

Pos logit contributions
undai+1.145
ascus+1.095
ottesville+1.067
occup+1.053
 assailant+1.041
Neg logit contributions
002-1.232
003-1.157
 Stretch-1.123
 Reef-1.118
662-1.108
Token forcing
Token ID10833
Feature activation+4.47e-01

Pos logit contributions
002+0.480
003+0.450
 Stretch+0.441
 Reef+0.440
662+0.433
Neg logit contributions
undai-0.442
ascus-0.418
ottesville-0.410
occup-0.403
 assailant-0.402
Token)
Token ID8
Feature activation+2.54e-02

Pos logit contributions
002+0.336
003+0.313
 Reef+0.308
 Stretch+0.305
662+0.303
Neg logit contributions
undai-0.324
ascus-0.306
ottesville-0.302
occup-0.297
iction-0.294
Token
Token ID198
Feature activation+5.21e-02

Pos logit contributions
undai+0.081
ascus+0.077
ottesville+0.075
occup+0.075
iction+0.073
Neg logit contributions
002-0.101
003-0.095
 Reef-0.093
 Stretch-0.093
662-0.092
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
undai+0.144
occup+0.141
ottesville+0.139
ascus+0.137
iction+0.137
Neg logit contributions
002-0.215
 Stretch-0.203
 Reef-0.203
003-0.202
662-0.196
TokenR
Token ID49
Feature activation+3.17e-01

Pos logit contributions
undai+0.530
ascus+0.502
occup+0.501
ottesville+0.495
iction+0.483
Neg logit contributions
002-0.598
 Stretch-0.567
 Reef-0.565
003-0.559
 Dialogue-0.544
Tokenattle
Token ID1999
Feature activation-1.00e-01

Pos logit contributions
undai+1.174
ascus+1.129
ottesville+1.121
occup+1.089
iction+1.088
Neg logit contributions
002-1.079
 Stretch-1.016
 Reef-1.003
003-1.002
662-0.979
TokenSnake
Token ID49795
Feature activation+1.10e+00

Pos logit contributions
002+0.356
003+0.332
 Stretch+0.326
 Reef+0.322
662+0.320
Neg logit contributions
undai-0.361
ascus-0.347
ottesville-0.343
occup-0.337
iction-0.329
Token:
Token ID25
Feature activation+4.46e-02

Pos logit contributions
undai+3.822
ascus+3.728
occup+3.659
ottesville+3.644
iction+3.552
Neg logit contributions
002-3.695
 Stretch-3.450
003-3.444
 Reef-3.422
662-3.322
Token La
Token ID4689
Feature activation+1.42e-01

Pos logit contributions
undai+0.168
ascus+0.161
ottesville+0.158
occup+0.156
iction+0.154
Neg logit contributions
002-0.150
003-0.139
 Reef-0.136
 Stretch-0.136
662-0.134
TokenN
Token ID45
Feature activation-2.29e-01

Pos logit contributions
undai+0.535
ascus+0.512
ottesville+0.503
occup+0.495
iction+0.484
Neg logit contributions
002-0.488
003-0.453
 Stretch-0.447
 Reef-0.443
662-0.438
Tokenm
Token ID76
Feature activation+8.06e-02

Pos logit contributions
002+0.843
003+0.787
 Stretch+0.777
 Reef+0.776
662+0.757
Neg logit contributions
undai-0.812
ascus-0.769
ottesville-0.759
occup-0.744
iction-0.730
Token is
Token ID318
Feature activation-1.59e-01

Pos logit contributions
undai+0.294
ascus+0.281
ottesville+0.276
occup+0.271
iction+0.267
Neg logit contributions
002-0.284
003-0.265
 Stretch-0.262
 Reef-0.261
662-0.255
Token:
Token ID25
Feature activation-5.25e-02

Pos logit contributions
002+0.535
003+0.504
 Reef+0.498
 Stretch+0.498
662+0.489
Neg logit contributions
undai-0.392
ascus-0.364
ottesville-0.362
occup-0.352
iction-0.348
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
002+0.202
003+0.189
 Reef+0.186
 Stretch+0.185
662+0.182
Neg logit contributions
undai-0.176
ascus-0.166
ottesville-0.165
occup-0.160
iction-0.157
Token
Token ID198
Feature activation-1.02e-01

Pos logit contributions
002+0.626
003+0.587
 Stretch+0.584
 Reef+0.582
662+0.568
Neg logit contributions
undai-0.476
ottesville-0.449
ascus-0.448
occup-0.446
iction-0.435
Token13
Token ID1485
Feature activation+1.84e-01

Pos logit contributions
002+0.388
003+0.363
 Stretch+0.360
 Reef+0.360
662+0.349
Neg logit contributions
undai-0.349
ascus-0.328
ottesville-0.326
occup-0.321
iction-0.312
Token PH
Token ID9370
Feature activation-4.85e-01

Pos logit contributions
undai+0.662
ottesville+0.628
ascus+0.623
occup+0.612
 assailant+0.603
Neg logit contributions
002-0.653
003-0.606
 Reef-0.601
 Stretch-0.591
662-0.581
TokenOTOS
Token ID33291
Feature activation-1.82e+00

Pos logit contributions
002+1.643
003+1.525
 Stretch+1.500
 Reef+1.497
662+1.464
Neg logit contributions
undai-1.854
ascus-1.751
ottesville-1.747
occup-1.712
iction-1.688
Token Donald
Token ID3759
Feature activation+1.90e-02

Pos logit contributions
002+5.855
 Stretch+5.441
003+5.409
 Reef+5.325
 Dialogue+5.217
Neg logit contributions
undai-7.421
ascus-7.035
ottesville-6.731
occup-6.621
 assailant-6.569
Token Trump
Token ID1301
Feature activation+8.83e-02

Pos logit contributions
undai+0.062
ottesville+0.060
ascus+0.059
occup+0.059
iction+0.058
Neg logit contributions
002-0.072
003-0.068
 Reef-0.067
 Stretch-0.066
662-0.065
Token's
Token ID338
Feature activation-1.95e-01

Pos logit contributions
undai+0.306
ottesville+0.289
ascus+0.289
occup+0.282
 assailant+0.279
Neg logit contributions
002-0.325
003-0.303
 Reef-0.298
 Stretch-0.294
662-0.293
Token potential
Token ID2785
Feature activation-3.73e-02

Pos logit contributions
002+0.724
003+0.675
 Reef+0.660
 Stretch+0.658
662+0.648
Neg logit contributions
undai-0.683
ascus-0.639
ottesville-0.633
occup-0.623
 assailant-0.613
Token running
Token ID2491
Feature activation+9.06e-02

Pos logit contributions
002+0.100
003+0.090
 Reef+0.088
 Stretch+0.087
662+0.087
Neg logit contributions
undai-0.169
ascus-0.160
ottesville-0.159
occup-0.158
 assailant-0.157
Tokenmount
Token ID14948
Feature activation+1.81e-01

Pos logit contributions
002+0.312
003+0.289
 Reef+0.287
 Stretch+0.286
662+0.279
Neg logit contributions
undai-0.339
ascus-0.321
ottesville-0.316
occup-0.315
iction-0.306
Tokening
Token ID278
Feature activation+2.40e-02

Pos logit contributions
undai+0.618
ascus+0.588
ottesville+0.581
occup+0.575
iction+0.566
Neg logit contributions
002-0.680
003-0.635
 Stretch-0.626
 Reef-0.625
662-0.609
Token demands
Token ID8665
Feature activation+3.37e-01

Pos logit contributions
undai+0.076
ascus+0.071
ottesville+0.070
occup+0.070
 assailant+0.068
Neg logit contributions
002-0.097
003-0.091
 Reef-0.089
 Stretch-0.089
662-0.088
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
undai+1.118
ascus+1.056
occup+1.036
ottesville+1.030
iction+1.003
Neg logit contributions
002-1.297
003-1.211
 Stretch-1.197
 Reef-1.196
662-1.171
Token AFP
Token ID8916
Feature activation-2.63e-01

Pos logit contributions
002+0.761
003+0.709
 Stretch+0.697
 Reef+0.696
662+0.684
Neg logit contributions
undai-0.726
ascus-0.688
ottesville-0.680
occup-0.668
iction-0.655
Token PHOTO
Token ID41153
Feature activation-1.54e+00

Pos logit contributions
002+0.817
003+0.751
 Stretch+0.740
 Reef+0.739
662+0.720
Neg logit contributions
undai-1.077
ascus-1.026
ottesville-1.016
occup-0.996
 assailant-0.983
Token /
Token ID1220
Feature activation-4.32e-01

Pos logit contributions
002+5.804
003+5.431
 Stretch+5.353
 Reef+5.317
662+5.220
Neg logit contributions
undai-5.366
ascus-5.049
ottesville-4.964
occup-4.806
iction-4.735
Token Saul
Token ID31603
Feature activation+7.91e-02

Pos logit contributions
002+1.334
003+1.225
 Stretch+1.199
 Reef+1.195
662+1.168
Neg logit contributions
undai-1.775
ascus-1.692
ottesville-1.681
occup-1.655
iction-1.628
Token LO
Token ID17579
Feature activation+9.16e-02

Pos logit contributions
undai+0.331
ascus+0.321
occup+0.317
ottesville+0.317
 assailant+0.313
Neg logit contributions
002-0.219
003-0.202
 Stretch-0.193
 Dialogue-0.192
 Reef-0.190
TokenEB
Token ID30195
Feature activation-3.75e-01

Pos logit contributions
undai+0.365
ascus+0.347
ottesville+0.343
occup+0.337
iction+0.332
Neg logit contributions
002-0.296
003-0.273
 Reef-0.269
 Stretch-0.269
662-0.261
TokenSA
Token ID4090
Feature activation-3.06e-02

Pos logit contributions
002+1.465
003+1.372
 Stretch+1.355
 Reef+1.352
662+1.328
Neg logit contributions
undai-1.225
ascus-1.155
ottesville-1.140
occup-1.116
 assailant-1.096
Token racing
Token ID11717
Feature activation+9.77e-02

Pos logit contributions
002+0.732
003+0.685
 Stretch+0.665
 Reef+0.663
662+0.659
Neg logit contributions
undai-0.660
ascus-0.628
ottesville-0.614
occup-0.609
 assailant-0.602
Token toward
Token ID3812
Feature activation-6.70e-01

Pos logit contributions
undai+0.337
ascus+0.322
ottesville+0.315
occup+0.309
 assailant+0.308
Neg logit contributions
002-0.364
003-0.339
 Stretch-0.330
662-0.330
 Reef-0.325
Token extinction
Token ID21935
Feature activation-1.93e-01

Pos logit contributions
002+2.518
003+2.353
 Stretch+2.311
 Reef+2.306
662+2.269
Neg logit contributions
undai-2.324
ascus-2.193
ottesville-2.166
occup-2.118
iction-2.081
Token
Token ID198
Feature activation-1.07e+00

Pos logit contributions
002+0.742
003+0.693
 Stretch+0.687
 Reef+0.679
662+0.670
Neg logit contributions
undai-0.646
ascus-0.612
ottesville-0.601
occup-0.594
iction-0.584
Token
Token ID198
Feature activation-1.15e+00

Pos logit contributions
002+4.031
003+3.773
 Stretch+3.699
 Reef+3.691
662+3.616
Neg logit contributions
undai-3.835
ascus-3.613
ottesville-3.531
occup-3.396
 assailant-3.368
TokenHow
Token ID2437
Feature activation-1.53e+00

Pos logit contributions
002+4.319
003+4.037
 Stretch+3.947
 Reef+3.943
662+3.881
Neg logit contributions
undai-4.021
ascus-3.802
ottesville-3.736
occup-3.604
 assailant-3.578
Token Vera
Token ID44413
Feature activation-3.32e-01

Pos logit contributions
002+5.371
003+4.996
 Stretch+4.946
 Reef+4.933
662+4.779
Neg logit contributions
undai-5.644
ascus-5.339
ottesville-5.311
occup-5.181
iction-5.080
Token Rubin
Token ID34599
Feature activation-3.46e-01

Pos logit contributions
002+1.126
003+1.053
 Stretch+1.021
 Reef+1.015
662+1.011
Neg logit contributions
undai-1.255
ascus-1.200
ottesville-1.186
occup-1.156
 assailant-1.149
Token changed
Token ID3421
Feature activation-5.24e-01

Pos logit contributions
002+1.252
003+1.169
 Stretch+1.153
 Reef+1.145
662+1.128
Neg logit contributions
undai-1.233
ascus-1.167
ottesville-1.161
occup-1.127
 assailant-1.113
Token science
Token ID3783
Feature activation-9.27e-02

Pos logit contributions
002+1.868
003+1.735
 Stretch+1.704
662+1.679
 Reef+1.677
Neg logit contributions
undai-1.916
ascus-1.818
ottesville-1.784
occup-1.764
iction-1.737
Token
Token ID198
Feature activation-1.17e+00

Pos logit contributions
002+0.353
003+0.331
 Stretch+0.328
 Reef+0.323
662+0.318
Neg logit contributions
undai-0.311
ascus-0.296
ottesville-0.293
occup-0.288
iction-0.284
Token teach
Token ID4545
Feature activation+2.20e-01

Pos logit contributions
002+1.745
003+1.625
 Reef+1.606
 Stretch+1.603
662+1.574
Neg logit contributions
undai-1.608
ascus-1.506
ottesville-1.491
occup-1.465
 assailant-1.454
Token
Token ID851
Feature activation-3.49e-01

Pos logit contributions
undai+0.689
ottesville+0.645
ascus+0.644
occup+0.629
iction+0.629
Neg logit contributions
002-0.888
003-0.832
 Reef-0.826
 Stretch-0.819
662-0.808
Token a
Token ID257
Feature activation-9.01e-02

Pos logit contributions
002+1.156
003+1.065
 Stretch+1.042
 Reef+1.040
662+1.027
Neg logit contributions
undai-1.352
ascus-1.293
ottesville-1.272
iction-1.254
occup-1.250
Token new
Token ID649
Feature activation-3.54e-01

Pos logit contributions
002+0.346
003+0.323
 Reef+0.317
 Stretch+0.317
662+0.313
Neg logit contributions
undai-0.302
ascus-0.288
ottesville-0.282
occup-0.275
iction-0.274
Token trick
Token ID6908
Feature activation-6.99e-02

Pos logit contributions
002+1.556
003+1.467
 Stretch+1.447
 Reef+1.444
662+1.422
Neg logit contributions
undai-1.000
ascus-0.935
ottesville-0.919
occup-0.894
iction-0.877
Token
Token ID198
Feature activation-1.43e+00

Pos logit contributions
002+0.282
003+0.264
 Stretch+0.261
 Reef+0.261
662+0.255
Neg logit contributions
undai-0.220
ascus-0.209
ottesville-0.206
occup-0.203
iction-0.200
Token
Token ID198
Feature activation-1.40e+00

Pos logit contributions
002+5.171
003+4.840
 Stretch+4.694
 Reef+4.682
662+4.605
Neg logit contributions
undai-5.448
ascus-5.130
ottesville-4.964
 assailant-4.740
occup-4.706
TokenDr
Token ID6187
Feature activation+1.07e-01

Pos logit contributions
002+5.217
003+4.879
 Stretch+4.742
 Reef+4.719
662+4.680
Neg logit contributions
undai-4.951
ascus-4.681
ottesville-4.582
 assailant-4.389
occup-4.385
Tokenone
Token ID505
Feature activation-2.96e-01

Pos logit contributions
undai+0.371
ascus+0.349
ottesville+0.345
occup+0.336
iction+0.334
Neg logit contributions
002-0.404
003-0.377
 Stretch-0.369
 Reef-0.368
662-0.364
Token video
Token ID2008
Feature activation-6.87e-02

Pos logit contributions
002+1.056
003+0.984
 Stretch+0.963
 Reef+0.962
662+0.948
Neg logit contributions
undai-1.074
ascus-1.028
ottesville-1.009
occup-0.993
 assailant-0.984
Token captures
Token ID23007
Feature activation-6.68e-02

Pos logit contributions
002+0.232
003+0.216
 Stretch+0.210
 Reef+0.209
662+0.208
Neg logit contributions
undai-0.261
ascus-0.247
ottesville-0.246
occup-0.241
 assailant-0.241
Token23
Token ID1954
Feature activation-5.85e-01

Pos logit contributions
002+1.937
003+1.751
 Stretch+1.716
 Reef+1.709
662+1.652
Neg logit contributions
undai-3.522
ascus-3.376
ottesville-3.349
occup-3.292
iction-3.248
Token12
Token ID1065
Feature activation-3.37e-01

Pos logit contributions
002+1.484
003+1.341
 Stretch+1.340
 Reef+1.335
662+1.266
Neg logit contributions
undai-2.692
ascus-2.587
ottesville-2.565
occup-2.538
iction-2.505
Token.
Token ID13
Feature activation-9.57e-01

Pos logit contributions
002+1.284
003+1.200
 Stretch+1.198
 Reef+1.191
662+1.162
Neg logit contributions
undai-1.118
ascus-1.057
ottesville-1.049
occup-1.034
iction-1.018
Tokene
Token ID68
Feature activation-9.46e-01

Pos logit contributions
002+2.963
003+2.734
 Reef+2.658
 Stretch+2.644
662+2.590
Neg logit contributions
undai-3.944
ascus-3.757
ottesville-3.740
occup-3.664
 assailant-3.607
Tokence
Token ID344
Feature activation-9.57e-01

Pos logit contributions
002+3.558
 Stretch+3.384
 Reef+3.382
003+3.291
 Dialogue+3.251
Neg logit contributions
undai-3.170
ascus-3.007
occup-2.951
ottesville-2.947
iction-2.883
Token/
Token ID14
Feature activation-1.41e+00

Pos logit contributions
002+3.372
003+3.146
 Reef+3.056
 Stretch+3.050
662+2.992
Neg logit contributions
undai-3.593
ascus-3.403
ottesville-3.367
occup-3.280
iction-3.213
Tokenedd
Token ID6048
Feature activation-5.20e-01

Pos logit contributions
002+4.812
003+4.481
662+4.293
 Stretch+4.200
 Reef+4.197
Neg logit contributions
undai-5.389
ascus-5.129
ottesville-5.093
 assailant-4.897
occup-4.884
Token75
Token ID2425
Feature activation-4.21e-01

Pos logit contributions
002+1.713
003+1.585
 Stretch+1.569
 Reef+1.563
662+1.517
Neg logit contributions
undai-2.037
ascus-1.937
ottesville-1.917
occup-1.880
iction-1.852
Token/
Token ID14
Feature activation-1.40e+00

Pos logit contributions
002+1.570
003+1.466
 Stretch+1.461
 Reef+1.453
662+1.411
Neg logit contributions
undai-1.457
ascus-1.376
ottesville-1.361
occup-1.336
iction-1.316
TokenAUT
Token ID39371
Feature activation-1.98e-01

Pos logit contributions
002+4.255
003+3.905
662+3.653
 Reef+3.645
 Stretch+3.523
Neg logit contributions
undai-5.937
ascus-5.791
ottesville-5.605
 assailant-5.459
occup-5.358
TokenOC
Token ID4503
Feature activation-7.21e-01

Pos logit contributions
002+0.580
003+0.532
 Stretch+0.528
 Reef+0.525
662+0.506
Neg logit contributions
undai-0.841
ottesville-0.801
ascus-0.800
occup-0.786
iction-0.773
Tokene
Token ID68
Feature activation-9.46e-01

Pos logit contributions
002+2.963
003+2.734
 Reef+2.658
 Stretch+2.644
662+2.590
Neg logit contributions
undai-3.944
ascus-3.757
ottesville-3.740
occup-3.664
 assailant-3.607
Tokence
Token ID344
Feature activation-9.57e-01

Pos logit contributions
002+3.558
 Stretch+3.384
 Reef+3.382
003+3.291
 Dialogue+3.251
Neg logit contributions
undai-3.170
ascus-3.007
occup-2.951
ottesville-2.947
iction-2.883
Token/
Token ID14
Feature activation-1.41e+00

Pos logit contributions
002+3.372
003+3.146
 Reef+3.056
 Stretch+3.050
662+2.992
Neg logit contributions
undai-3.593
ascus-3.403
ottesville-3.367
occup-3.280
iction-3.213
Tokenedd
Token ID6048
Feature activation-5.20e-01

Pos logit contributions
002+4.812
003+4.481
662+4.293
 Stretch+4.200
 Reef+4.197
Neg logit contributions
undai-5.389
ascus-5.129
ottesville-5.093
 assailant-4.897
occup-4.884
Token75
Token ID2425
Feature activation-4.21e-01

Pos logit contributions
002+1.713
003+1.585
 Stretch+1.569
 Reef+1.563
662+1.517
Neg logit contributions
undai-2.037
ascus-1.937
ottesville-1.917
occup-1.880
iction-1.852
Token/
Token ID14
Feature activation-1.40e+00

Pos logit contributions
002+1.570
003+1.466
 Stretch+1.461
 Reef+1.453
662+1.411
Neg logit contributions
undai-1.457
ascus-1.376
ottesville-1.361
occup-1.336
iction-1.316
TokenAUT
Token ID39371
Feature activation-1.98e-01

Pos logit contributions
002+4.255
003+3.905
662+3.653
 Reef+3.645
 Stretch+3.523
Neg logit contributions
undai-5.937
ascus-5.791
ottesville-5.605
 assailant-5.459
occup-5.358
TokenOC
Token ID4503
Feature activation-7.21e-01

Pos logit contributions
002+0.580
003+0.532
 Stretch+0.528
 Reef+0.525
662+0.506
Neg logit contributions
undai-0.841
ottesville-0.801
ascus-0.800
occup-0.786
iction-0.773
TokenR
Token ID49
Feature activation+9.19e-02

Pos logit contributions
002+1.992
003+1.813
 Stretch+1.772
 Reef+1.767
662+1.716
Neg logit contributions
undai-3.225
ascus-3.091
ottesville-3.057
occup-3.000
iction-2.962
TokenOP
Token ID3185
Feature activation-1.68e-01

Pos logit contributions
undai+0.353
ascus+0.332
ottesville+0.331
occup+0.330
iction+0.326
Neg logit contributions
002-0.300
 Stretch-0.277
 Reef-0.277
003-0.276
662-0.269
Token/
Token ID14
Feature activation-7.70e-01

Pos logit contributions
002+0.618
003+0.577
 Stretch+0.569
 Reef+0.567
662+0.555
Neg logit contributions
undai-0.593
ascus-0.560
ottesville-0.555
occup-0.542
iction-0.533
Token
Token ID851
Feature activation-3.49e-01

Pos logit contributions
undai+0.689
ottesville+0.645
ascus+0.644
occup+0.629
iction+0.629
Neg logit contributions
002-0.888
003-0.832
 Reef-0.826
 Stretch-0.819
662-0.808
Token a
Token ID257
Feature activation-9.01e-02

Pos logit contributions
002+1.156
003+1.065
 Stretch+1.042
 Reef+1.040
662+1.027
Neg logit contributions
undai-1.352
ascus-1.293
ottesville-1.272
iction-1.254
occup-1.250
Token new
Token ID649
Feature activation-3.54e-01

Pos logit contributions
002+0.346
003+0.323
 Reef+0.317
 Stretch+0.317
662+0.313
Neg logit contributions
undai-0.302
ascus-0.288
ottesville-0.282
occup-0.275
iction-0.274
Token trick
Token ID6908
Feature activation-6.99e-02

Pos logit contributions
002+1.556
003+1.467
 Stretch+1.447
 Reef+1.444
662+1.422
Neg logit contributions
undai-1.000
ascus-0.935
ottesville-0.919
occup-0.894
iction-0.877
Token
Token ID198
Feature activation-1.43e+00

Pos logit contributions
002+0.282
003+0.264
 Stretch+0.261
 Reef+0.261
662+0.255
Neg logit contributions
undai-0.220
ascus-0.209
ottesville-0.206
occup-0.203
iction-0.200
Token
Token ID198
Feature activation-1.40e+00

Pos logit contributions
002+5.171
003+4.840
 Stretch+4.694
 Reef+4.682
662+4.605
Neg logit contributions
undai-5.448
ascus-5.130
ottesville-4.964
 assailant-4.740
occup-4.706
TokenDr
Token ID6187
Feature activation+1.07e-01

Pos logit contributions
002+5.217
003+4.879
 Stretch+4.742
 Reef+4.719
662+4.680
Neg logit contributions
undai-4.951
ascus-4.681
ottesville-4.582
 assailant-4.389
occup-4.385
Tokenone
Token ID505
Feature activation-2.96e-01

Pos logit contributions
undai+0.371
ascus+0.349
ottesville+0.345
occup+0.336
iction+0.334
Neg logit contributions
002-0.404
003-0.377
 Stretch-0.369
 Reef-0.368
662-0.364
Token video
Token ID2008
Feature activation-6.87e-02

Pos logit contributions
002+1.056
003+0.984
 Stretch+0.963
 Reef+0.962
662+0.948
Neg logit contributions
undai-1.074
ascus-1.028
ottesville-1.009
occup-0.993
 assailant-0.984
Token captures
Token ID23007
Feature activation-6.68e-02

Pos logit contributions
002+0.232
003+0.216
 Stretch+0.210
 Reef+0.209
662+0.208
Neg logit contributions
undai-0.261
ascus-0.247
ottesville-0.246
occup-0.241
 assailant-0.241
Token killer
Token ID11868
Feature activation+7.09e-01

Pos logit contributions
002+0.242
003+0.226
 Stretch+0.220
 Reef+0.219
662+0.218
Neg logit contributions
undai-0.238
ascus-0.226
ottesville-0.222
 assailant-0.218
occup-0.218
Tokenbur
Token ID6236
Feature activation+6.38e-01

Pos logit contributions
undai+0.197
ascus+0.187
ottesville+0.186
occup+0.184
iction+0.181
Neg logit contributions
002-0.134
 Stretch-0.126
 Reef-0.124
003-0.124
 Dialogue-0.119
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
undai+2.178
ascus+2.035
ottesville+2.009
occup+1.944
iction+1.902
Neg logit contributions
002-2.398
 Stretch-2.290
003-2.258
 Reef-2.239
 Dialogue-2.207
Tokenorg
Token ID2398
Feature activation-1.14e-01

Pos logit contributions
002+0.542
003+0.498
 Stretch+0.493
 Reef+0.491
662+0.474
Neg logit contributions
undai-0.745
ascus-0.707
ottesville-0.703
occup-0.693
iction-0.683
Token/
Token ID14
Feature activation-6.43e-01

Pos logit contributions
002+0.424
003+0.396
 Stretch+0.391
 Reef+0.390
662+0.382
Neg logit contributions
undai-0.393
ascus-0.372
ottesville-0.369
occup-0.361
iction-0.354
Token2015
Token ID4626
Feature activation-3.40e-01

Pos logit contributions
002+2.171
003+2.013
 Stretch+1.988
 Reef+1.979
662+1.929
Neg logit contributions
undai-2.471
ascus-2.346
ottesville-2.323
occup-2.281
iction-2.238
Token/
Token ID14
Feature activation-1.37e+00

Pos logit contributions
002+1.244
003+1.161
 Stretch+1.144
 Reef+1.141
662+1.116
Neg logit contributions
undai-1.213
ascus-1.147
ottesville-1.135
occup-1.109
iction-1.089
Token08
Token ID2919
Feature activation-5.33e-01

Pos logit contributions
002+3.121
003+2.784
 Stretch+2.616
 Reef+2.603
662+2.549
Neg logit contributions
undai-6.843
ascus-6.572
ottesville-6.518
occup-6.325
iction-6.318
Token/
Token ID14
Feature activation-1.13e+00

Pos logit contributions
002+1.998
 Stretch+1.871
003+1.865
 Reef+1.861
662+1.805
Neg logit contributions
undai-1.780
ottesville-1.681
ascus-1.680
occup-1.671
iction-1.628
Token11
Token ID1157
Feature activation-1.19e-01

Pos logit contributions
002+3.227
003+2.947
 Reef+2.845
 Stretch+2.842
662+2.785
Neg logit contributions
undai-4.931
ascus-4.714
ottesville-4.679
occup-4.546
iction-4.513
Token/
Token ID14
Feature activation-8.54e-01

Pos logit contributions
002+0.450
 Stretch+0.426
 Reef+0.421
003+0.421
662+0.409
Neg logit contributions
undai-0.388
ascus-0.368
ottesville-0.365
occup-0.363
iction-0.353
Tokene
Token ID68
Feature activation-4.84e-01

Pos logit contributions
002+3.208
003+2.999
 Stretch+2.960
 Reef+2.952
662+2.887
Neg logit contributions
undai-2.955
ascus-2.790
ottesville-2.758
occup-2.696
iction-2.644
Token an
Token ID281
Feature activation-1.81e-01

Pos logit contributions
002+0.058
003+0.054
 Reef+0.053
662+0.053
 Stretch+0.052
Neg logit contributions
undai-0.059
ascus-0.055
ottesville-0.055
 assailant-0.054
occup-0.053
Token atom
Token ID22037
Feature activation-4.53e-02

Pos logit contributions
002+0.683
003+0.636
 Stretch+0.623
 Reef+0.622
662+0.613
Neg logit contributions
undai-0.626
ascus-0.588
ottesville-0.584
occup-0.572
 assailant-0.568
Token from
Token ID422
Feature activation-7.96e-02

Pos logit contributions
002+0.159
003+0.147
 Stretch+0.146
 Reef+0.145
662+0.142
Neg logit contributions
undai-0.166
ascus-0.159
ottesville-0.157
occup-0.155
iction-0.152
Token Shakespeare
Token ID22197
Feature activation+5.41e-01

Pos logit contributions
002+0.285
003+0.265
 Reef+0.259
 Stretch+0.257
662+0.257
Neg logit contributions
undai-0.287
ascus-0.272
ottesville-0.267
occup-0.262
iction-0.261
Token?
Token ID30
Feature activation-1.26e-01

Pos logit contributions
undai+1.887
ascus+1.816
ottesville+1.793
occup+1.763
iction+1.741
Neg logit contributions
002-1.937
003-1.786
 Reef-1.773
 Stretch-1.764
662-1.751
Token
Token ID198
Feature activation-1.36e+00

Pos logit contributions
002+0.498
003+0.467
 Reef+0.458
 Stretch+0.457
662+0.451
Neg logit contributions
undai-0.401
ottesville-0.378
ascus-0.378
occup-0.370
iction-0.364
Token
Token ID198
Feature activation-1.22e+00

Pos logit contributions
002+4.950
003+4.633
 Stretch+4.502
 Reef+4.489
662+4.416
Neg logit contributions
undai-5.085
ascus-4.790
ottesville-4.647
 assailant-4.437
occup-4.418
TokenSl
Token ID11122
Feature activation-1.53e-01

Pos logit contributions
002+4.617
003+4.318
 Stretch+4.220
 Reef+4.203
662+4.151
Neg logit contributions
undai-4.269
ascus-4.038
ottesville-3.963
occup-3.815
 assailant-3.792
Tokenime
Token ID524
Feature activation-2.24e-01

Pos logit contributions
002+0.638
003+0.600
 Stretch+0.593
 Reef+0.592
662+0.581
Neg logit contributions
undai-0.469
ascus-0.445
ottesville-0.440
occup-0.425
iction-0.420
Token m
Token ID285
Feature activation-1.29e-01

Pos logit contributions
002+0.810
003+0.757
 Stretch+0.737
 Reef+0.731
662+0.728
Neg logit contributions
undai-0.804
ascus-0.763
ottesville-0.753
occup-0.740
 assailant-0.728
Tokenolds
Token ID10119
Feature activation-7.29e-02

Pos logit contributions
002+0.419
003+0.388
 Stretch+0.386
 Reef+0.379
662+0.372
Neg logit contributions
undai-0.517
ascus-0.493
ottesville-0.486
occup-0.476
iction-0.474
Token,
Token ID11
Feature activation-7.28e-02

Pos logit contributions
002+0.691
003+0.642
 Stretch+0.635
 Reef+0.631
662+0.622
Neg logit contributions
undai-0.662
ascus-0.629
ottesville-0.620
occup-0.613
iction-0.604
Token singing
Token ID13777
Feature activation+1.13e-01

Pos logit contributions
002+0.273
003+0.255
 Stretch+0.250
 Reef+0.248
662+0.245
Neg logit contributions
undai-0.251
ascus-0.237
ottesville-0.232
occup-0.229
iction-0.226
Token a
Token ID257
Feature activation-1.99e-01

Pos logit contributions
undai+0.379
ascus+0.357
ottesville+0.352
occup+0.348
 assailant+0.343
Neg logit contributions
002-0.431
003-0.404
 Stretch-0.391
 Reef-0.390
662-0.389
Token live
Token ID2107
Feature activation-1.24e-01

Pos logit contributions
002+0.728
003+0.676
 Reef+0.660
 Stretch+0.660
662+0.651
Neg logit contributions
undai-0.702
ascus-0.667
ottesville-0.654
occup-0.647
iction-0.635
Token du
Token ID7043
Feature activation-7.56e-03

Pos logit contributions
002+0.432
003+0.401
 Stretch+0.392
 Reef+0.389
662+0.382
Neg logit contributions
undai-0.460
ascus-0.437
ottesville-0.431
occup-0.424
 assailant-0.419
Tokenet
Token ID316
Feature activation-1.29e+00

Pos logit contributions
002+0.022
003+0.020
 Stretch+0.020
 Reef+0.019
662+0.019
Neg logit contributions
undai-0.033
ascus-0.031
ottesville-0.031
occup-0.031
iction-0.030
Token of
Token ID286
Feature activation-4.11e-01

Pos logit contributions
002+4.430
003+4.114
 Stretch+4.072
 Reef+4.046
 Dialogue+3.944
Neg logit contributions
undai-4.867
ascus-4.598
ottesville-4.570
occup-4.421
iction-4.339
Token "
Token ID366
Feature activation-1.92e-01

Pos logit contributions
002+1.497
003+1.397
 Stretch+1.358
 Reef+1.355
662+1.345
Neg logit contributions
undai-1.466
ascus-1.376
ottesville-1.361
occup-1.344
iction-1.320
TokenThe
Token ID464
Feature activation-2.65e-01

Pos logit contributions
002+0.701
003+0.655
 Stretch+0.647
 Reef+0.645
662+0.629
Neg logit contributions
undai-0.675
ascus-0.635
ottesville-0.632
occup-0.625
iction-0.609
Token Rainbow
Token ID19909
Feature activation+1.38e-02

Pos logit contributions
002+0.886
003+0.822
 Stretch+0.798
 Reef+0.795
662+0.787
Neg logit contributions
undai-1.019
ascus-0.963
ottesville-0.957
occup-0.940
iction-0.928
Token Connection
Token ID26923
Feature activation-2.74e-01

Pos logit contributions
undai+0.053
ascus+0.051
ottesville+0.050
occup+0.050
 assailant+0.049
Neg logit contributions
002-0.045
003-0.042
662-0.040
 Stretch-0.040
 Reef-0.040
Token Ker
Token ID17337
Feature activation-1.97e-01

Pos logit contributions
undai+0.381
ascus+0.357
ottesville+0.352
occup+0.351
 assailant+0.349
Neg logit contributions
002-0.342
003-0.317
 Reef-0.307
662-0.305
 Stretch-0.305
Tokenmit
Token ID2781
Feature activation-5.06e-01

Pos logit contributions
002+0.575
003+0.529
 Stretch+0.525
 Reef+0.524
662+0.504
Neg logit contributions
undai-0.848
ascus-0.805
ottesville-0.796
occup-0.796
iction-0.774
Token sing
Token ID1702
Feature activation-3.23e-01

Pos logit contributions
002+1.953
003+1.830
 Stretch+1.805
 Reef+1.802
662+1.764
Neg logit contributions
undai-1.700
ascus-1.604
ottesville-1.583
occup-1.551
iction-1.520
Token the
Token ID262
Feature activation-3.64e-01

Pos logit contributions
002+1.197
003+1.118
 Reef+1.092
 Stretch+1.091
662+1.077
Neg logit contributions
undai-1.134
ascus-1.071
ottesville-1.060
occup-1.037
 assailant-1.024
Token du
Token ID7043
Feature activation+1.26e-03

Pos logit contributions
002+1.347
003+1.259
 Reef+1.220
 Stretch+1.220
662+1.209
Neg logit contributions
undai-1.283
ascus-1.205
ottesville-1.189
occup-1.172
 assailant-1.166
Tokenet
Token ID316
Feature activation-1.28e+00

Pos logit contributions
undai+0.005
ascus+0.005
ottesville+0.005
occup+0.005
iction+0.005
Neg logit contributions
002-0.004
003-0.003
 Stretch-0.003
 Reef-0.003
662-0.003
Token "
Token ID366
Feature activation-1.89e-01

Pos logit contributions
002+4.643
003+4.323
 Stretch+4.313
 Reef+4.293
662+4.155
Neg logit contributions
undai-4.578
ascus-4.324
ottesville-4.293
occup-4.157
iction-4.062
TokenI
Token ID40
Feature activation-2.19e-01

Pos logit contributions
002+0.692
003+0.646
 Stretch+0.638
 Reef+0.637
662+0.621
Neg logit contributions
undai-0.670
ascus-0.632
ottesville-0.626
occup-0.619
iction-0.603
Token Hope
Token ID13408
Feature activation-2.67e-01

Pos logit contributions
002+0.779
003+0.728
 Reef+0.712
 Stretch+0.708
662+0.698
Neg logit contributions
undai-0.799
ascus-0.754
ottesville-0.744
occup-0.735
iction-0.718
Token That
Token ID1320
Feature activation-4.09e-03

Pos logit contributions
002+0.932
003+0.873
662+0.838
 Reef+0.832
 Stretch+0.826
Neg logit contributions
undai-0.981
ascus-0.930
ottesville-0.915
occup-0.909
iction-0.900
Token S
Token ID311
Feature activation-2.02e-01

Pos logit contributions
002+0.014
003+0.013
662+0.013
 Stretch+0.012
 Reef+0.012
Neg logit contributions
undai-0.015
ascus-0.014
occup-0.014
ottesville-0.014
iction-0.014
Tokenee
Token ID1453
Feature activation-4.63e-01

Pos logit contributions
002+0.967
003+0.901
 Stretch+0.900
 Reef+0.898
662+0.871
Neg logit contributions
undai-0.934
ascus-0.883
ottesville-0.872
occup-0.852
iction-0.845
Tokenpl
Token ID489
Feature activation-2.03e-01

Pos logit contributions
002+1.310
003+1.197
 Stretch+1.172
 Reef+1.167
662+1.135
Neg logit contributions
undai-2.034
ascus-1.943
ottesville-1.928
occup-1.891
iction-1.868
Tokeninks
Token ID2973
Feature activation+1.13e-01

Pos logit contributions
002+0.516
003+0.464
 Stretch+0.462
 Reef+0.461
662+0.437
Neg logit contributions
undai-0.951
ascus-0.911
ottesville-0.904
occup-0.892
iction-0.883
Token/
Token ID14
Feature activation-8.15e-01

Pos logit contributions
undai+0.397
ascus+0.376
ottesville+0.373
occup+0.365
iction+0.359
Neg logit contributions
002-0.417
003-0.389
 Stretch-0.386
 Reef-0.385
662-0.375
Token2016
Token ID5304
Feature activation-4.87e-01

Pos logit contributions
002+3.005
003+2.805
 Stretch+2.755
 Reef+2.746
662+2.694
Neg logit contributions
undai-2.880
ascus-2.723
ottesville-2.693
occup-2.622
iction-2.580
Token/
Token ID14
Feature activation-1.26e+00

Pos logit contributions
002+1.772
003+1.652
 Stretch+1.626
 Reef+1.621
662+1.587
Neg logit contributions
undai-1.748
ascus-1.654
ottesville-1.636
occup-1.597
iction-1.570
Token06
Token ID3312
Feature activation-4.40e-01

Pos logit contributions
002+3.099
003+2.789
 Stretch+2.664
 Reef+2.638
662+2.590
Neg logit contributions
undai-5.981
ascus-5.738
ottesville-5.693
occup-5.538
iction-5.515
Token/
Token ID14
Feature activation-9.98e-01

Pos logit contributions
002+1.648
 Stretch+1.547
 Reef+1.541
003+1.539
662+1.492
Neg logit contributions
undai-1.475
ascus-1.395
ottesville-1.387
occup-1.382
iction-1.342
Tokent
Token ID83
Feature activation-5.86e-01

Pos logit contributions
002+3.604
003+3.358
 Stretch+3.276
 Reef+3.260
662+3.215
Neg logit contributions
undai-3.608
ascus-3.417
ottesville-3.384
occup-3.274
 assailant-3.236
Tokenatt
Token ID1078
Feature activation-2.98e-01

Pos logit contributions
002+2.628
003+2.486
 Stretch+2.448
 Reef+2.441
662+2.402
Neg logit contributions
undai-1.603
ascus-1.488
ottesville-1.466
occup-1.418
 assailant-1.388
Tokenoo
Token ID2238
Feature activation-1.62e-01

Pos logit contributions
002+0.935
003+0.863
 Stretch+0.852
 Reef+0.847
662+0.825
Neg logit contributions
undai-1.213
ascus-1.156
ottesville-1.147
occup-1.125
iction-1.108
Token Vera
Token ID44413
Feature activation-3.32e-01

Pos logit contributions
002+5.371
003+4.996
 Stretch+4.946
 Reef+4.933
662+4.779
Neg logit contributions
undai-5.644
ascus-5.339
ottesville-5.311
occup-5.181
iction-5.080
Token Rubin
Token ID34599
Feature activation-3.46e-01

Pos logit contributions
002+1.126
003+1.053
 Stretch+1.021
 Reef+1.015
662+1.011
Neg logit contributions
undai-1.255
ascus-1.200
ottesville-1.186
occup-1.156
 assailant-1.149
Token changed
Token ID3421
Feature activation-5.24e-01

Pos logit contributions
002+1.252
003+1.169
 Stretch+1.153
 Reef+1.145
662+1.128
Neg logit contributions
undai-1.233
ascus-1.167
ottesville-1.161
occup-1.127
 assailant-1.113
Token science
Token ID3783
Feature activation-9.27e-02

Pos logit contributions
002+1.868
003+1.735
 Stretch+1.704
662+1.679
 Reef+1.677
Neg logit contributions
undai-1.916
ascus-1.818
ottesville-1.784
occup-1.764
iction-1.737
Token
Token ID198
Feature activation-1.17e+00

Pos logit contributions
002+0.353
003+0.331
 Stretch+0.328
 Reef+0.323
662+0.318
Neg logit contributions
undai-0.311
ascus-0.296
ottesville-0.293
occup-0.288
iction-0.284
Token
Token ID198
Feature activation-1.24e+00

Pos logit contributions
002+4.334
003+4.058
 Stretch+3.962
 Reef+3.954
662+3.882
Neg logit contributions
undai-4.233
ascus-3.983
ottesville-3.885
occup-3.723
 assailant-3.708
TokenDear
Token ID20266
Feature activation-7.15e-01

Pos logit contributions
002+4.688
003+4.384
 Stretch+4.280
 Reef+4.274
662+4.212
Neg logit contributions
undai-4.350
ascus-4.106
ottesville-4.034
occup-3.890
 assailant-3.863
Token Science
Token ID5800
Feature activation-1.98e-01

Pos logit contributions
002+2.382
003+2.208
 Stretch+2.161
 Reef+2.156
662+2.117
Neg logit contributions
undai-2.789
ascus-2.645
ottesville-2.628
occup-2.570
iction-2.530
Token:
Token ID25
Feature activation-4.65e-01

Pos logit contributions
002+0.705
003+0.658
 Stretch+0.646
 Reef+0.646
662+0.635
Neg logit contributions
undai-0.711
ottesville-0.676
ascus-0.676
occup-0.659
iction-0.649
Token Could
Token ID10347
Feature activation-2.69e-01

Pos logit contributions
002+1.466
003+1.353
 Reef+1.309
 Stretch+1.306
662+1.296
Neg logit contributions
undai-1.871
ascus-1.785
ottesville-1.775
occup-1.746
iction-1.725
Token my
Token ID616
Feature activation-3.35e-01

Pos logit contributions
002+0.936
003+0.870
 Reef+0.849
 Stretch+0.847
662+0.840
Neg logit contributions
undai-1.003
ascus-0.945
ottesville-0.935
occup-0.917
iction-0.911
Token Hide
Token ID10415
Feature activation-2.68e-01

Pos logit contributions
002+0.159
003+0.142
 Reef+0.138
 Stretch+0.136
662+0.135
Neg logit contributions
undai-0.328
ottesville-0.316
ascus-0.315
occup-0.311
iction-0.308
Token Caption
Token ID11260
Feature activation-5.45e-01

Pos logit contributions
002+0.241
003+0.175
 Reef+0.162
 Stretch+0.159
662+0.147
Neg logit contributions
undai-1.642
ottesville-1.608
ascus-1.596
occup-1.593
iction-1.578
Token 7
Token ID767
Feature activation-1.02e-01

Pos logit contributions
002+2.014
003+1.871
 Stretch+1.838
 Reef+1.836
662+1.807
Neg logit contributions
undai-1.886
ascus-1.791
ottesville-1.790
occup-1.752
iction-1.715
Token of
Token ID286
Feature activation-3.87e-01

Pos logit contributions
002+0.377
 Stretch+0.349
003+0.349
 Reef+0.349
 Dialogue+0.338
Neg logit contributions
undai-0.335
occup-0.323
ascus-0.321
ottesville-0.321
iction-0.314
Token 15
Token ID1315
Feature activation+3.14e-01

Pos logit contributions
002+1.564
003+1.469
 Stretch+1.450
 Reef+1.446
662+1.418
Neg logit contributions
undai-1.226
ascus-1.152
ottesville-1.138
occup-1.110
iction-1.087
Token Photos
Token ID9434
Feature activation-1.24e+00

Pos logit contributions
undai+1.082
occup+1.081
ottesville+1.073
iction+1.043
ascus+1.042
Neg logit contributions
002-1.037
003-0.950
662-0.945
 Reef-0.933
 Stretch-0.928
Token:
Token ID25
Feature activation-5.34e-01

Pos logit contributions
002+4.036
003+3.741
 Stretch+3.648
 Reef+3.633
662+3.565
Neg logit contributions
undai-5.044
ascus-4.778
ottesville-4.665
occup-4.517
 assailant-4.497
Token Carly
Token ID35982
Feature activation-1.68e-01

Pos logit contributions
002+2.334
003+2.202
 Stretch+2.176
 Reef+2.170
662+2.136
Neg logit contributions
undai-1.507
ascus-1.407
ottesville-1.388
occup-1.353
iction-1.322
Token Fiorina
Token ID49028
Feature activation-2.27e-01

Pos logit contributions
002+0.446
003+0.403
 Stretch+0.393
 Reef+0.389
662+0.384
Neg logit contributions
undai-0.755
ascus-0.722
ottesville-0.721
occup-0.712
iction-0.702
Token's
Token ID338
Feature activation-3.65e-01

Pos logit contributions
002+0.830
003+0.772
 Stretch+0.764
 Reef+0.759
662+0.745
Neg logit contributions
undai-0.784
ascus-0.744
ottesville-0.742
occup-0.736
iction-0.721
Token political
Token ID1964
Feature activation-4.13e-01

Pos logit contributions
002+1.577
003+1.485
 Stretch+1.470
 Reef+1.464
662+1.441
Neg logit contributions
undai-1.054
ascus-0.987
ottesville-0.969
occup-0.949
iction-0.928
Tokengov
Token ID9567
Feature activation-1.56e-01

Pos logit contributions
002+0.578
003+0.522
 Reef+0.522
 Stretch+0.518
662+0.491
Neg logit contributions
undai-1.069
ascus-1.030
ottesville-1.017
occup-1.011
iction-0.991
Token/
Token ID14
Feature activation-6.99e-01

Pos logit contributions
002+0.576
003+0.538
 Stretch+0.531
 Reef+0.530
662+0.518
Neg logit contributions
undai-0.550
ascus-0.521
ottesville-0.515
occup-0.504
iction-0.495
Tokendata
Token ID7890
Feature activation-1.90e-01

Pos logit contributions
002+2.491
003+2.319
 Stretch+2.288
 Reef+2.283
662+2.228
Neg logit contributions
undai-2.553
ascus-2.419
ottesville-2.392
occup-2.345
iction-2.301
Token/
Token ID14
Feature activation-6.63e-01

Pos logit contributions
002+0.697
003+0.651
 Stretch+0.648
 Reef+0.647
662+0.629
Neg logit contributions
undai-0.663
ascus-0.628
ottesville-0.621
occup-0.611
iction-0.601
Token2015
Token ID4626
Feature activation-4.30e-01

Pos logit contributions
002+2.329
003+2.167
 Stretch+2.141
 Reef+2.136
662+2.081
Neg logit contributions
undai-2.453
ascus-2.326
ottesville-2.301
occup-2.260
iction-2.216
Token/
Token ID14
Feature activation-1.24e+00

Pos logit contributions
002+1.547
003+1.442
 Stretch+1.431
 Reef+1.427
662+1.388
Neg logit contributions
undai-1.543
ascus-1.465
ottesville-1.446
occup-1.428
iction-1.396
Tokenacs
Token ID16436
Feature activation-6.43e-01

Pos logit contributions
002+4.490
003+4.184
 Stretch+4.078
 Reef+4.056
662+3.997
Neg logit contributions
undai-4.456
ascus-4.207
ottesville-4.171
occup-4.008
 assailant-3.995
Token5
Token ID20
Feature activation-3.64e-01

Pos logit contributions
002+2.193
003+2.036
 Stretch+2.013
 Reef+2.009
662+1.954
Neg logit contributions
undai-2.443
ascus-2.320
ottesville-2.296
occup-2.257
iction-2.216
Token/
Token ID14
Feature activation-1.05e+00

Pos logit contributions
002+1.275
003+1.185
 Stretch+1.177
 Reef+1.171
662+1.137
Neg logit contributions
undai-1.342
ascus-1.273
ottesville-1.261
occup-1.242
iction-1.220
Tokenprofile
Token ID13317
Feature activation-3.81e-01

Pos logit contributions
002+3.749
003+3.490
 Stretch+3.422
 Reef+3.404
662+3.345
Neg logit contributions
undai-3.802
ascus-3.594
ottesville-3.562
occup-3.444
 assailant-3.418
Token?
Token ID30
Feature activation-2.05e-01

Pos logit contributions
002+1.368
003+1.275
 Stretch+1.266
 Reef+1.262
662+1.230
Neg logit contributions
undai-1.371
ascus-1.300
ottesville-1.287
occup-1.265
iction-1.242
Token.
Token ID13
Feature activation-3.65e-02

Pos logit contributions
002+0.889
003+0.829
 Stretch+0.817
 Reef+0.816
662+0.797
Neg logit contributions
undai-0.844
ascus-0.798
ottesville-0.785
occup-0.773
iction-0.762
Token
Token ID198
Feature activation+4.22e-04

Pos logit contributions
002+0.139
003+0.129
 Reef+0.127
662+0.126
 Stretch+0.126
Neg logit contributions
undai-0.116
ottesville-0.111
occup-0.111
iction-0.110
ascus-0.110
Token
Token ID198
Feature activation+3.56e-02

Pos logit contributions
undai+0.001
occup+0.001
ottesville+0.001
ascus+0.001
iction+0.001
Neg logit contributions
002-0.002
 Stretch-0.002
003-0.002
 Reef-0.002
662-0.002
TokenIs
Token ID3792
Feature activation-3.84e-01

Pos logit contributions
undai+0.117
occup+0.109
ascus+0.109
ottesville+0.109
iction+0.106
Neg logit contributions
002-0.137
 Reef-0.129
 Stretch-0.129
003-0.128
 Dialogue-0.125
Token it
Token ID340
Feature activation+5.67e-02

Pos logit contributions
002+1.345
003+1.249
 Reef+1.225
 Stretch+1.222
662+1.199
Neg logit contributions
undai-1.428
ascus-1.350
ottesville-1.330
occup-1.318
iction-1.305
Token really
Token ID1107
Feature activation-1.24e+00

Pos logit contributions
undai+0.181
ascus+0.170
ottesville+0.167
occup+0.164
iction+0.163
Neg logit contributions
002-0.228
003-0.213
 Reef-0.209
 Stretch-0.206
662-0.206
Token likely
Token ID1884
Feature activation-2.27e-01

Pos logit contributions
002+4.624
003+4.332
 Stretch+4.308
 Reef+4.276
662+4.174
Neg logit contributions
undai-4.250
ascus-4.009
ottesville-3.985
occup-3.874
iction-3.780
Token that
Token ID326
Feature activation+1.40e-01

Pos logit contributions
002+0.792
003+0.734
 Stretch+0.721
 Reef+0.721
662+0.709
Neg logit contributions
undai-0.840
ascus-0.795
ottesville-0.787
occup-0.776
iction-0.770
Token Amazon
Token ID6186
Feature activation-1.53e-01

Pos logit contributions
undai+0.478
ascus+0.447
ottesville+0.441
iction+0.440
occup+0.440
Neg logit contributions
002-0.523
003-0.486
 Reef-0.475
 Stretch-0.473
662-0.472
Token is
Token ID318
Feature activation-1.73e-01

Pos logit contributions
002+0.612
003+0.573
 Reef+0.570
 Stretch+0.568
662+0.559
Neg logit contributions
undai-0.485
ascus-0.451
ottesville-0.450
occup-0.443
iction-0.435
Token going
Token ID1016
Feature activation+6.78e-02

Pos logit contributions
002+0.654
003+0.611
 Reef+0.604
 Stretch+0.601
662+0.590
Neg logit contributions
undai-0.588
ascus-0.552
ottesville-0.548
occup-0.544
iction-0.537
Token atom
Token ID22037
Feature activation-4.53e-02

Pos logit contributions
002+0.683
003+0.636
 Stretch+0.623
 Reef+0.622
662+0.613
Neg logit contributions
undai-0.626
ascus-0.588
ottesville-0.584
occup-0.572
 assailant-0.568
Token from
Token ID422
Feature activation-7.96e-02

Pos logit contributions
002+0.159
003+0.147
 Stretch+0.146
 Reef+0.145
662+0.142
Neg logit contributions
undai-0.166
ascus-0.159
ottesville-0.157
occup-0.155
iction-0.152
Token Shakespeare
Token ID22197
Feature activation+5.41e-01

Pos logit contributions
002+0.285
003+0.265
 Reef+0.259
 Stretch+0.257
662+0.257
Neg logit contributions
undai-0.287
ascus-0.272
ottesville-0.267
occup-0.262
iction-0.261
Token?
Token ID30
Feature activation-1.26e-01

Pos logit contributions
undai+1.887
ascus+1.816
ottesville+1.793
occup+1.763
iction+1.741
Neg logit contributions
002-1.937
003-1.786
 Reef-1.773
 Stretch-1.764
662-1.751
Token
Token ID198
Feature activation-1.36e+00

Pos logit contributions
002+0.498
003+0.467
 Reef+0.458
 Stretch+0.457
662+0.451
Neg logit contributions
undai-0.401
ottesville-0.378
ascus-0.378
occup-0.370
iction-0.364
Token
Token ID198
Feature activation-1.22e+00

Pos logit contributions
002+4.950
003+4.633
 Stretch+4.502
 Reef+4.489
662+4.416
Neg logit contributions
undai-5.085
ascus-4.790
ottesville-4.647
 assailant-4.437
occup-4.418
TokenSl
Token ID11122
Feature activation-1.53e-01

Pos logit contributions
002+4.617
003+4.318
 Stretch+4.220
 Reef+4.203
662+4.151
Neg logit contributions
undai-4.269
ascus-4.038
ottesville-3.963
occup-3.815
 assailant-3.792
Tokenime
Token ID524
Feature activation-2.24e-01

Pos logit contributions
002+0.638
003+0.600
 Stretch+0.593
 Reef+0.592
662+0.581
Neg logit contributions
undai-0.469
ascus-0.445
ottesville-0.440
occup-0.425
iction-0.420
Token m
Token ID285
Feature activation-1.29e-01

Pos logit contributions
002+0.810
003+0.757
 Stretch+0.737
 Reef+0.731
662+0.728
Neg logit contributions
undai-0.804
ascus-0.763
ottesville-0.753
occup-0.740
 assailant-0.728
Tokenolds
Token ID10119
Feature activation-7.29e-02

Pos logit contributions
002+0.419
003+0.388
 Stretch+0.386
 Reef+0.379
662+0.372
Neg logit contributions
undai-0.517
ascus-0.493
ottesville-0.486
occup-0.476
iction-0.474
Token prove
Token ID5879
Feature activation-7.69e-03

Pos logit contributions
002+0.277
003+0.259
 Reef+0.253
 Stretch+0.251
662+0.250
Neg logit contributions
undai-0.246
ascus-0.232
ottesville-0.229
occup-0.226
 assailant-0.224
Token of
Token ID286
Feature activation+3.80e-02

Pos logit contributions
undai+0.902
ascus+0.855
ottesville+0.846
occup+0.828
iction+0.814
Neg logit contributions
002-0.847
003-0.788
 Stretch-0.776
 Reef-0.774
662-0.756
Token imper
Token ID11071
Feature activation-2.49e-02

Pos logit contributions
undai+0.118
ascus+0.113
ottesville+0.111
 assailant+0.110
occup+0.109
Neg logit contributions
002-0.154
003-0.143
 Stretch-0.141
 Reef-0.141
662-0.140
Tokent
Token ID83
Feature activation-1.04e-01

Pos logit contributions
002+0.099
003+0.093
 Stretch+0.092
 Reef+0.092
662+0.090
Neg logit contributions
undai-0.080
ascus-0.075
ottesville-0.074
occup-0.074
iction-0.072
Tokeninence
Token ID18386
Feature activation+8.56e-02

Pos logit contributions
002+0.407
003+0.381
 Stretch+0.376
 Reef+0.375
662+0.368
Neg logit contributions
undai-0.347
ascus-0.327
ottesville-0.323
occup-0.314
iction-0.309
Token for
Token ID329
Feature activation-3.05e-01

Pos logit contributions
undai+0.294
ascus+0.278
ottesville+0.274
occup+0.273
iction+0.268
Neg logit contributions
002-0.319
003-0.298
 Stretch-0.295
 Reef-0.295
662-0.289
Token which
Token ID543
Feature activation-1.22e+00

Pos logit contributions
002+1.102
003+1.023
 Reef+1.010
 Stretch+1.007
662+0.991
Neg logit contributions
undai-1.091
ascus-1.033
ottesville-1.017
occup-1.006
 assailant-0.997
Token no
Token ID645
Feature activation-3.32e-01

Pos logit contributions
002+4.358
003+4.065
 Stretch+4.005
 Reef+3.993
662+3.899
Neg logit contributions
undai-4.412
ascus-4.172
ottesville-4.131
occup-4.030
iction-3.955
Token lady
Token ID10846
Feature activation-9.74e-02

Pos logit contributions
002+1.303
003+1.218
 Stretch+1.201
 Reef+1.198
662+1.176
Neg logit contributions
undai-1.088
ascus-1.030
ottesville-1.016
occup-0.996
 assailant-0.989
Token of
Token ID286
Feature activation-1.89e-01

Pos logit contributions
002+0.380
003+0.356
 Reef+0.352
 Stretch+0.351
662+0.344
Neg logit contributions
undai-0.322
ascus-0.303
ottesville-0.301
occup-0.296
 assailant-0.291
Token delic
Token ID8675
Feature activation+4.57e-01

Pos logit contributions
002+0.715
003+0.664
 Stretch+0.656
 Reef+0.650
662+0.642
Neg logit contributions
undai-0.640
ascus-0.608
ottesville-0.596
occup-0.591
 assailant-0.590
Tokenacy
Token ID1590
Feature activation-2.30e-02

Pos logit contributions
undai+1.293
ascus+1.200
ottesville+1.187
occup+1.180
iction+1.175
Neg logit contributions
002-1.979
003-1.867
 Stretch-1.851
 Reef-1.841
662-1.799
Token:
Token ID25
Feature activation-5.00e-01

Pos logit contributions
002+2.908
003+2.699
 Stretch+2.656
 Reef+2.647
662+2.584
Neg logit contributions
undai-3.269
ascus-3.102
ottesville-3.070
occup-3.003
iction-2.953
Token 10
Token ID838
Feature activation+1.81e-02

Pos logit contributions
002+1.873
003+1.750
 Reef+1.738
 Stretch+1.735
662+1.703
Neg logit contributions
undai-1.705
ascus-1.627
ottesville-1.602
occup-1.572
iction-1.539
Token.
Token ID13
Feature activation-2.99e-01

Pos logit contributions
undai+0.057
ascus+0.055
ottesville+0.054
occup+0.054
iction+0.053
Neg logit contributions
002-0.070
003-0.066
 Reef-0.065
 Stretch-0.065
662-0.063
Token10
Token ID940
Feature activation-8.56e-02

Pos logit contributions
002+0.759
 Stretch+0.702
 Reef+0.701
003+0.688
 Dialogue+0.658
Neg logit contributions
undai-1.336
occup-1.294
ottesville-1.290
ascus-1.289
iction-1.267
Token86
Token ID4521
Feature activation-4.99e-01

Pos logit contributions
002+0.225
003+0.204
 Stretch+0.204
 Reef+0.202
662+0.193
Neg logit contributions
undai-0.390
ascus-0.374
ottesville-0.369
occup-0.366
iction-0.361
Token/
Token ID14
Feature activation-1.22e+00

Pos logit contributions
002+1.871
 Stretch+1.752
 Reef+1.752
003+1.747
662+1.691
Neg logit contributions
undai-1.637
ascus-1.566
ottesville-1.560
occup-1.549
iction-1.512
Token34
Token ID2682
Feature activation-4.06e-01

Pos logit contributions
002+3.640
003+3.342
 Stretch+3.275
 Reef+3.263
662+3.181
Neg logit contributions
undai-5.137
ascus-4.901
ottesville-4.857
occup-4.760
iction-4.691
Token110
Token ID11442
Feature activation-4.76e-01

Pos logit contributions
002+1.043
 Stretch+0.979
 Reef+0.952
003+0.949
 Dialogue+0.908
Neg logit contributions
undai-1.821
ascus-1.775
occup-1.744
ottesville-1.742
iction-1.710
Token7
Token ID22
Feature activation-3.65e-01

Pos logit contributions
002+1.397
 Stretch+1.279
003+1.278
 Reef+1.270
 Dialogue+1.215
Neg logit contributions
undai-1.999
ascus-1.924
ottesville-1.899
occup-1.878
iction-1.851
Token
Token ID198
Feature activation-9.12e-01

Pos logit contributions
002+1.280
 Stretch+1.190
003+1.187
 Reef+1.174
662+1.144
Neg logit contributions
undai-1.314
ascus-1.253
ottesville-1.246
occup-1.224
iction-1.212
Token
Token ID198
Feature activation-7.46e-01

Pos logit contributions
002+3.462
003+3.242
 Stretch+3.180
 Reef+3.172
662+3.113
Neg logit contributions
undai-3.189
ascus-3.003
ottesville-2.944
occup-2.845
 assailant-2.809
Tokenground
Token ID2833
Feature activation+3.75e-01

Pos logit contributions
undai+0.512
ascus+0.482
ottesville+0.479
occup+0.475
iction+0.465
Neg logit contributions
002-0.484
 Stretch-0.451
003-0.450
 Reef-0.449
 Dialogue-0.433
Token.
Token ID13
Feature activation+2.64e-02

Pos logit contributions
undai+1.288
ascus+1.214
ottesville+1.205
occup+1.180
iction+1.158
Neg logit contributions
002-1.406
003-1.314
 Stretch-1.308
 Reef-1.303
662-1.268
Tokencom
Token ID785
Feature activation-3.14e-02

Pos logit contributions
undai+0.090
ascus+0.085
ottesville+0.084
occup+0.083
iction+0.081
Neg logit contributions
002-0.099
003-0.093
 Reef-0.092
 Stretch-0.092
 Dialogue-0.090
Token/
Token ID14
Feature activation-6.28e-01

Pos logit contributions
002+0.114
003+0.106
 Stretch+0.105
 Reef+0.104
662+0.102
Neg logit contributions
undai-0.113
ascus-0.107
ottesville-0.105
occup-0.103
iction-0.101
Token2016
Token ID5304
Feature activation-2.59e-01

Pos logit contributions
002+2.224
003+2.070
 Stretch+2.039
 Reef+2.032
662+1.987
Neg logit contributions
undai-2.306
ascus-2.185
ottesville-2.163
occup-2.113
iction-2.077
Token/
Token ID14
Feature activation-1.20e+00

Pos logit contributions
002+0.935
003+0.872
 Stretch+0.856
 Reef+0.852
662+0.836
Neg logit contributions
undai-0.937
ascus-0.887
ottesville-0.879
occup-0.855
 assailant-0.842
Token09
Token ID2931
Feature activation-3.79e-01

Pos logit contributions
002+2.796
003+2.502
 Stretch+2.387
 Reef+2.363
662+2.313
Neg logit contributions
undai-5.909
ascus-5.676
ottesville-5.641
occup-5.488
 assailant-5.467
Token/
Token ID14
Feature activation-9.74e-01

Pos logit contributions
002+1.437
 Stretch+1.350
 Reef+1.343
003+1.340
662+1.301
Neg logit contributions
undai-1.233
ottesville-1.169
occup-1.168
ascus-1.164
iction-1.137
Token08
Token ID2919
Feature activation-5.14e-02

Pos logit contributions
002+3.909
003+3.667
 Stretch+3.592
 Reef+3.582
662+3.531
Neg logit contributions
undai-3.120
ascus-2.937
ottesville-2.914
occup-2.798
 assailant-2.772
Token/
Token ID14
Feature activation-7.70e-01

Pos logit contributions
002+0.195
 Stretch+0.185
 Reef+0.183
003+0.183
 Dialogue+0.178
Neg logit contributions
undai-0.166
ascus-0.158
ottesville-0.157
occup-0.157
iction-0.153
Tokenthe
Token ID1169
Feature activation-2.81e-01

Pos logit contributions
002+3.254
003+3.065
 Stretch+3.018
 Reef+3.010
662+2.962
Neg logit contributions
undai-2.304
ascus-2.155
ottesville-2.135
occup-2.060
 assailant-2.025
Token and
Token ID290
Feature activation+1.44e-03

Pos logit contributions
002+0.102
003+0.095
 Stretch+0.094
 Reef+0.094
662+0.091
Neg logit contributions
undai-0.097
ascus-0.092
ottesville-0.091
occup-0.089
 assailant-0.087
Token the
Token ID262
Feature activation-6.42e-02

Pos logit contributions
undai+0.005
ascus+0.005
ottesville+0.005
occup+0.005
 assailant+0.005
Neg logit contributions
002-0.005
003-0.005
 Stretch-0.005
 Reef-0.005
662-0.005
Token word
Token ID1573
Feature activation-2.06e-01

Pos logit contributions
002+0.249
003+0.233
 Stretch+0.229
 Reef+0.226
662+0.225
Neg logit contributions
undai-0.214
ascus-0.201
ottesville-0.199
occup-0.196
 assailant-0.195
Token
Token ID564
Feature activation+1.95e-01

Pos logit contributions
002+0.737
003+0.685
 Stretch+0.665
 Reef+0.664
662+0.662
Neg logit contributions
undai-0.743
ascus-0.707
ottesville-0.691
occup-0.687
 assailant-0.680
Token
Token ID246
Feature activation-1.53e-01

Pos logit contributions
undai+0.819
ascus+0.778
ottesville+0.773
occup+0.761
iction+0.747
Neg logit contributions
002-0.583
003-0.535
 Stretch-0.533
 Reef-0.530
662-0.512
TokenDep
Token ID12156
Feature activation+7.04e-01

Pos logit contributions
002+0.533
003+0.495
 Stretch+0.491
 Reef+0.489
662+0.476
Neg logit contributions
undai-0.565
ascus-0.539
ottesville-0.530
occup-0.523
iction-0.512
Tokenression
Token ID2234
Feature activation-3.94e-04

Pos logit contributions
undai+2.383
ottesville+2.231
ascus+2.227
iction+2.195
occup+2.144
Neg logit contributions
002-2.683
003-2.507
 Reef-2.503
 Stretch-2.485
662-2.411
Token
Token ID447
Feature activation+5.91e-02

Pos logit contributions
002+0.001
003+0.001
 Stretch+0.001
 Reef+0.001
662+0.001
Neg logit contributions
undai-0.002
ascus-0.001
ottesville-0.001
occup-0.001
iction-0.001
Token
Token ID247
Feature activation+4.21e-02

Pos logit contributions
undai+0.253
ascus+0.239
ottesville+0.238
occup+0.234
iction+0.231
Neg logit contributions
002-0.172
003-0.158
 Stretch-0.158
 Reef-0.154
662-0.151
Token,
Token ID11
Feature activation-6.82e-03

Pos logit contributions
undai+0.151
ascus+0.143
ottesville+0.141
occup+0.139
iction+0.137
Neg logit contributions
002-0.151
003-0.141
 Stretch-0.140
 Reef-0.139
662-0.136
Token though
Token ID996
Feature activation+1.02e-02

Pos logit contributions
002+0.026
003+0.024
 Stretch+0.024
 Reef+0.023
662+0.023
Neg logit contributions
undai-0.023
ascus-0.022
ottesville-0.022
occup-0.022
iction-0.021
Token the
Token ID262
Feature activation+1.62e-01

Pos logit contributions
undai+1.515
ottesville+1.470
ascus+1.447
occup+1.422
iction+1.385
Neg logit contributions
002-1.860
003-1.742
 Reef-1.728
 Stretch-1.712
662-1.691
Token complete
Token ID1844
Feature activation-4.06e-01

Pos logit contributions
undai+0.547
ascus+0.517
ottesville+0.514
 assailant+0.513
 attacker+0.504
Neg logit contributions
002-0.607
003-0.564
 Reef-0.552
662-0.549
 Stretch-0.544
Token story
Token ID1621
Feature activation+1.26e-01

Pos logit contributions
002+1.202
003+1.095
 Reef+1.071
 Stretch+1.065
662+1.058
Neg logit contributions
undai-1.707
ascus-1.636
ottesville-1.619
occup-1.603
 assailant-1.590
Token at
Token ID379
Feature activation+2.27e-02

Pos logit contributions
undai+0.420
ottesville+0.393
ascus+0.391
occup+0.386
 assailant+0.375
Neg logit contributions
002-0.483
003-0.453
 Reef-0.449
 Stretch-0.446
662-0.438
Token Boston
Token ID6182
Feature activation-2.63e-02

Pos logit contributions
undai+0.087
ascus+0.082
ottesville+0.082
occup+0.081
iction+0.079
Neg logit contributions
002-0.076
003-0.070
 Stretch-0.068
 Reef-0.068
662-0.067
TokenGl
Token ID9861
Feature activation+7.36e-01

Pos logit contributions
002+0.082
 Stretch+0.076
 Reef+0.076
003+0.076
662+0.074
Neg logit contributions
undai-0.105
ottesville-0.100
ascus-0.100
occup-0.097
 assailant-0.096
Tokenobe
Token ID5910
Feature activation+5.20e-01

Pos logit contributions
undai+2.000
ottesville+1.841
ascus+1.824
occup+1.747
iction+1.744
Neg logit contributions
002-3.292
 Stretch-3.139
 Reef-3.119
003-3.108
662-3.032
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
undai+1.633
ascus+1.563
ottesville+1.541
occup+1.525
iction+1.497
Neg logit contributions
002-2.033
 Stretch-1.908
 Reef-1.905
003-1.899
662-1.843
Tokencom
Token ID785
Feature activation+4.87e-02

Pos logit contributions
undai+0.635
ascus+0.608
ottesville+0.605
occup+0.597
iction+0.590
Neg logit contributions
002-0.428
003-0.389
 Stretch-0.386
 Reef-0.385
662-0.370
Token.
Token ID13
Feature activation+2.23e-02

Pos logit contributions
undai+0.164
ascus+0.156
ottesville+0.154
occup+0.150
iction+0.147
Neg logit contributions
002-0.186
003-0.174
 Reef-0.172
 Stretch-0.171
662-0.168
Token
Token ID198
Feature activation+8.42e-02

Pos logit contributions
undai+0.073
ascus+0.070
ottesville+0.069
occup+0.067
iction+0.066
Neg logit contributions
002-0.086
003-0.081
 Reef-0.080
 Stretch-0.080
662-0.078
Token owns
Token ID12216
Feature activation-3.43e-01

Pos logit contributions
undai+0.761
ascus+0.704
occup+0.687
ottesville+0.685
iction+0.677
Neg logit contributions
002-1.080
 Reef-1.017
003-1.015
 Stretch-1.000
662-0.993
Token Stan
Token ID7299
Feature activation+4.49e-02

Pos logit contributions
002+1.250
003+1.163
 Reef+1.137
 Stretch+1.134
662+1.120
Neg logit contributions
undai-1.211
ascus-1.151
ottesville-1.128
occup-1.116
iction-1.104
Tokenza
Token ID4496
Feature activation-1.70e-01

Pos logit contributions
undai+0.134
ascus+0.126
ottesville+0.123
occup+0.123
iction+0.120
Neg logit contributions
002-0.188
003-0.177
 Reef-0.176
 Stretch-0.176
 Dialogue-0.171
Token
Token ID960
Feature activation+1.16e-01

Pos logit contributions
002+0.636
003+0.595
 Reef+0.587
 Stretch+0.586
662+0.574
Neg logit contributions
undai-0.578
ascus-0.548
ottesville-0.542
occup-0.531
iction-0.531
Tokenso
Token ID568
Feature activation-2.01e-01

Pos logit contributions
undai+0.404
occup+0.383
ascus+0.381
ottesville+0.374
iction+0.368
Neg logit contributions
002-0.421
 Reef-0.394
003-0.392
 Stretch-0.388
 Dialogue-0.377
Token if
Token ID611
Feature activation+6.09e-01

Pos logit contributions
002+0.776
003+0.724
 Reef+0.718
 Stretch+0.710
662+0.703
Neg logit contributions
undai-0.668
ascus-0.621
ottesville-0.614
occup-0.614
iction-0.602
Token you
Token ID345
Feature activation-5.80e-02

Pos logit contributions
undai+1.671
ascus+1.531
occup+1.522
iction+1.498
ottesville+1.488
Neg logit contributions
002-2.625
003-2.465
 Reef-2.441
662-2.401
 Stretch-2.397
Token
Token ID447
Feature activation+4.99e-02

Pos logit contributions
002+0.234
003+0.220
 Reef+0.220
 Stretch+0.216
662+0.213
Neg logit contributions
undai-0.183
ascus-0.171
ottesville-0.168
occup-0.167
iction-0.164
Token
Token ID247
Feature activation+2.93e-02

Pos logit contributions
undai+0.240
ottesville+0.229
ascus+0.227
occup+0.227
iction+0.224
Neg logit contributions
002-0.111
 Stretch-0.103
003-0.101
 Dialogue-0.098
 Reef-0.097
Tokenre
Token ID260
Feature activation-1.85e-01

Pos logit contributions
undai+0.108
ascus+0.102
occup+0.101
ottesville+0.101
iction+0.098
Neg logit contributions
002-0.102
 Reef-0.095
003-0.095
 Stretch-0.094
 Dialogue-0.092
Token looking
Token ID2045
Feature activation-3.64e-02

Pos logit contributions
002+0.698
003+0.653
 Reef+0.646
 Stretch+0.640
662+0.627
Neg logit contributions
undai-0.637
ascus-0.602
ottesville-0.592
occup-0.585
iction-0.574
Token debate
Token ID4384
Feature activation+3.32e-01

Pos logit contributions
undai+0.364
ascus+0.347
ottesville+0.345
 assailant+0.339
occup+0.339
Neg logit contributions
002-0.332
003-0.309
 Stretch-0.301
 Reef-0.297
662-0.296
Token
Token ID198
Feature activation+1.96e-01

Pos logit contributions
undai+1.072
ascus+1.013
ottesville+1.006
occup+0.999
 assailant+0.985
Neg logit contributions
002-1.285
003-1.206
 Stretch-1.177
 Reef-1.174
662-1.162
Token
Token ID198
Feature activation+1.98e-01

Pos logit contributions
undai+0.540
occup+0.531
ottesville+0.519
iction+0.511
ascus+0.511
Neg logit contributions
002-0.808
 Stretch-0.763
 Reef-0.761
003-0.759
662-0.738
TokenB
Token ID33
Feature activation+1.43e-01

Pos logit contributions
undai+0.634
occup+0.593
ascus+0.593
ottesville+0.593
iction+0.573
Neg logit contributions
002-0.767
 Stretch-0.728
 Reef-0.725
003-0.720
 Dialogue-0.697
Tokenac
Token ID330
Feature activation+5.22e-01

Pos logit contributions
undai+0.320
ascus+0.295
ottesville+0.286
occup+0.276
iction+0.270
Neg logit contributions
002-0.710
003-0.675
 Reef-0.671
 Stretch-0.671
662-0.658
Tokenile
Token ID576
Feature activation+6.30e-01

Pos logit contributions
undai+1.760
ottesville+1.644
ascus+1.638
occup+1.607
iction+1.605
Neg logit contributions
002-1.963
 Stretch-1.863
 Reef-1.838
003-1.828
 Dialogue-1.787
Token's
Token ID338
Feature activation+1.01e-01

Pos logit contributions
undai+2.073
ottesville+1.993
ascus+1.976
occup+1.933
 assailant+1.914
Neg logit contributions
002-2.375
003-2.211
 Stretch-2.199
 Reef-2.179
662-2.156
Token movie
Token ID3807
Feature activation-9.32e-03

Pos logit contributions
undai+0.385
ascus+0.368
ottesville+0.365
occup+0.360
 assailant+0.360
Neg logit contributions
002-0.342
003-0.316
 Stretch-0.310
 Reef-0.305
662-0.302
Token does
Token ID857
Feature activation-6.22e-02

Pos logit contributions
002+0.035
003+0.033
 Stretch+0.033
 Reef+0.032
662+0.032
Neg logit contributions
undai-0.032
ascus-0.030
ottesville-0.030
occup-0.029
 assailant-0.029
Token not
Token ID407
Feature activation+2.76e-01

Pos logit contributions
002+0.236
003+0.220
 Stretch+0.217
 Reef+0.217
662+0.212
Neg logit contributions
undai-0.212
ascus-0.199
ottesville-0.199
occup-0.196
 assailant-0.192
Token excuse
Token ID12226
Feature activation+3.85e-01

Pos logit contributions
undai+0.884
ascus+0.838
ottesville+0.837
occup+0.822
iction+0.807
Neg logit contributions
002-1.095
003-1.025
 Stretch-1.009
 Reef-1.008
662-0.987
Tokenllo
Token ID18798
Feature activation-2.05e-01

Pos logit contributions
002+0.176
003+0.164
 Stretch+0.161
 Reef+0.159
 Transparency+0.154
Neg logit contributions
undai-0.240
ottesville-0.230
occup-0.227
ascus-0.227
iction-0.226
Token said
Token ID531
Feature activation-6.52e-02

Pos logit contributions
002+0.789
003+0.738
 Reef+0.726
 Stretch+0.725
662+0.713
Neg logit contributions
undai-0.691
ascus-0.653
ottesville-0.645
occup-0.629
iction-0.616
Token.
Token ID13
Feature activation-1.93e-02

Pos logit contributions
002+0.249
003+0.233
 Stretch+0.229
 Reef+0.229
662+0.225
Neg logit contributions
undai-0.221
ascus-0.209
ottesville-0.206
occup-0.203
iction-0.197
Token "
Token ID366
Feature activation+2.21e-01

Pos logit contributions
002+0.076
003+0.071
 Stretch+0.070
 Reef+0.070
662+0.068
Neg logit contributions
undai-0.063
ascus-0.060
ottesville-0.059
occup-0.058
iction-0.056
TokenBut
Token ID1537
Feature activation+4.10e-02

Pos logit contributions
undai+0.627
occup+0.597
ottesville+0.597
ascus+0.591
iction+0.580
Neg logit contributions
002-0.903
 Stretch-0.852
003-0.848
 Reef-0.848
662-0.822
Token if
Token ID611
Feature activation+6.00e-01

Pos logit contributions
undai+0.139
ascus+0.130
ottesville+0.127
 assailant+0.126
occup+0.125
Neg logit contributions
002-0.156
003-0.146
 Stretch-0.142
 Reef-0.141
662-0.141
Token it
Token ID340
Feature activation+3.44e-02

Pos logit contributions
undai+1.847
ascus+1.724
 assailant+1.698
ottesville+1.674
 attacker+1.658
Neg logit contributions
002-2.383
003-2.224
662-2.183
 Stretch-2.159
 Reef-2.151
Token were
Token ID547
Feature activation-5.28e-01

Pos logit contributions
undai+0.123
ascus+0.116
ottesville+0.115
occup+0.113
 assailant+0.111
Neg logit contributions
002-0.125
003-0.117
 Stretch-0.115
 Reef-0.115
662-0.113
Token easy
Token ID2562
Feature activation+5.03e-02

Pos logit contributions
002+1.974
003+1.843
 Stretch+1.814
 Reef+1.811
662+1.776
Neg logit contributions
undai-1.835
ascus-1.733
ottesville-1.710
occup-1.672
iction-1.644
Token,
Token ID11
Feature activation-3.10e-01

Pos logit contributions
undai+0.176
ascus+0.166
ottesville+0.163
occup+0.160
 assailant+0.158
Neg logit contributions
002-0.187
003-0.174
 Stretch-0.172
 Reef-0.171
662-0.168
Token anybody
Token ID9599
Feature activation+3.77e-01

Pos logit contributions
002+1.158
003+1.080
 Stretch+1.056
 Reef+1.055
662+1.043
Neg logit contributions
undai-1.080
ascus-1.015
ottesville-0.995
occup-0.982
 assailant-0.976
Token satire
Token ID35704
Feature activation+3.49e-02

Pos logit contributions
002+1.151
003+1.076
 Stretch+1.064
 Reef+1.058
662+1.041
Neg logit contributions
undai-0.968
ascus-0.915
ottesville-0.902
occup-0.884
 assailant-0.868
Token.
Token ID13
Feature activation-3.21e-01

Pos logit contributions
undai+0.118
ascus+0.112
ottesville+0.111
occup+0.110
iction+0.107
Neg logit contributions
002-0.131
003-0.122
 Stretch-0.121
 Reef-0.121
662-0.118
Token Neither
Token ID16126
Feature activation+2.67e-02

Pos logit contributions
002+1.084
003+1.003
 Stretch+0.989
 Reef+0.985
662+0.964
Neg logit contributions
undai-1.223
ascus-1.163
ottesville-1.159
occup-1.136
iction-1.120
Token me
Token ID502
Feature activation+8.42e-02

Pos logit contributions
undai+0.094
ascus+0.090
ottesville+0.089
 assailant+0.088
occup+0.087
Neg logit contributions
002-0.098
003-0.090
 Stretch-0.089
 Reef-0.088
662-0.087
Token or
Token ID393
Feature activation-3.69e-01

Pos logit contributions
undai+0.304
ascus+0.290
ottesville+0.286
occup+0.282
 assailant+0.276
Neg logit contributions
002-0.301
003-0.280
 Stretch-0.279
 Reef-0.279
 Dialogue-0.269
Token my
Token ID616
Feature activation-5.41e-02

Pos logit contributions
002+1.348
003+1.255
 Stretch+1.235
 Reef+1.229
662+1.208
Neg logit contributions
undai-1.315
ascus-1.243
ottesville-1.227
occup-1.205
 assailant-1.191
Token supporters
Token ID5941
Feature activation+4.33e-01

Pos logit contributions
002+0.206
003+0.193
 Stretch+0.190
 Reef+0.189
662+0.186
Neg logit contributions
undai-0.183
ascus-0.173
ottesville-0.171
 assailant-0.170
occup-0.169
Token want
Token ID765
Feature activation+7.71e-02

Pos logit contributions
undai+1.420
ascus+1.352
ottesville+1.302
occup+1.301
 assailant+1.290
Neg logit contributions
002-1.665
003-1.554
 Stretch-1.547
 Reef-1.545
662-1.505
Token rape
Token ID7262
Feature activation+2.67e-01

Pos logit contributions
undai+0.272
ascus+0.260
ottesville+0.255
occup+0.251
 assailant+0.250
Neg logit contributions
002-0.282
003-0.262
 Stretch-0.258
 Reef-0.256
662-0.251
Token to
Token ID284
Feature activation+1.43e-01

Pos logit contributions
undai+0.911
ascus+0.881
ottesville+0.862
occup+0.848
 assailant+0.846
Neg logit contributions
002-0.986
003-0.918
 Stretch-0.917
 Reef-0.905
662-0.889
Token be
Token ID307
Feature activation+2.02e-01

Pos logit contributions
undai+0.480
ascus+0.458
ottesville+0.453
occup+0.449
iction+0.444
Neg logit contributions
002-0.545
003-0.508
 Stretch-0.497
 Reef-0.497
662-0.490
Token the
Token ID262
Feature activation-1.85e-01

Pos logit contributions
undai+0.227
ascus+0.213
ottesville+0.213
occup+0.209
 assailant+0.205
Neg logit contributions
002-0.277
003-0.260
 Stretch-0.253
 Reef-0.253
662-0.251
Token corner
Token ID5228
Feature activation-1.88e-01

Pos logit contributions
002+0.661
003+0.616
 Stretch+0.593
 Reef+0.592
662+0.587
Neg logit contributions
undai-0.671
ascus-0.639
ottesville-0.634
 assailant-0.616
occup-0.615
Token.
Token ID13
Feature activation-3.95e-02

Pos logit contributions
002+0.709
003+0.664
 Stretch+0.653
 Reef+0.653
662+0.639
Neg logit contributions
undai-0.641
ascus-0.606
ottesville-0.600
occup-0.590
 assailant-0.577
Token
Token ID198
Feature activation+6.01e-02

Pos logit contributions
002+0.146
003+0.136
 Reef+0.132
 Stretch+0.131
662+0.131
Neg logit contributions
undai-0.133
ottesville-0.128
occup-0.127
ascus-0.126
iction-0.124
Token
Token ID198
Feature activation-1.01e-02

Pos logit contributions
undai+0.171
occup+0.166
ottesville+0.164
ascus+0.162
iction+0.160
Neg logit contributions
002-0.247
003-0.232
 Stretch-0.232
 Reef-0.231
662-0.225
TokenAs
Token ID1722
Feature activation-3.47e-02

Pos logit contributions
002+0.038
 Reef+0.035
003+0.035
 Stretch+0.035
 Dialogue+0.034
Neg logit contributions
undai-0.034
occup-0.032
ottesville-0.032
ascus-0.032
iction-0.031
Token you
Token ID345
Feature activation-2.28e-01

Pos logit contributions
002+0.131
003+0.122
 Reef+0.120
 Stretch+0.118
662+0.118
Neg logit contributions
undai-0.119
ascus-0.112
ottesville-0.111
occup-0.110
iction-0.108
Token set
Token ID900
Feature activation+1.71e-01

Pos logit contributions
002+0.863
003+0.806
 Reef+0.792
 Stretch+0.789
662+0.777
Neg logit contributions
undai-0.776
ascus-0.737
ottesville-0.726
occup-0.717
iction-0.701
Token out
Token ID503
Feature activation+4.00e-01

Pos logit contributions
undai+0.553
ascus+0.519
ottesville+0.515
occup+0.513
iction+0.503
Neg logit contributions
002-0.670
003-0.627
 Reef-0.612
 Stretch-0.606
662-0.601
Token from
Token ID422
Feature activation+2.45e-02

Pos logit contributions
undai+1.303
ascus+1.229
ottesville+1.204
occup+1.203
iction+1.177
Neg logit contributions
002-1.551
003-1.459
 Stretch-1.425
 Reef-1.418
662-1.411
Token the
Token ID262
Feature activation-1.71e-01

Pos logit contributions
undai+0.089
ascus+0.084
ottesville+0.083
occup+0.082
 assailant+0.081
Neg logit contributions
002-0.087
003-0.081
 Stretch-0.078
662-0.078
 Reef-0.078
Token this
Token ID428
Feature activation+1.71e-01

Pos logit contributions
002+1.347
003+1.258
 Stretch+1.240
 Reef+1.240
662+1.216
Neg logit contributions
undai-1.246
ascus-1.181
ottesville-1.171
occup-1.139
iction-1.119
Token week
Token ID1285
Feature activation-1.35e-01

Pos logit contributions
undai+0.525
ascus+0.493
ottesville+0.485
occup+0.473
iction+0.467
Neg logit contributions
002-0.713
003-0.670
 Reef-0.659
 Stretch-0.649
662-0.645
Token would
Token ID561
Feature activation+3.17e-02

Pos logit contributions
002+0.505
003+0.472
 Stretch+0.465
 Reef+0.464
662+0.455
Neg logit contributions
undai-0.472
ascus-0.446
ottesville-0.441
occup-0.431
iction-0.423
Token be
Token ID307
Feature activation-9.40e-02

Pos logit contributions
undai+0.110
ascus+0.104
ottesville+0.103
occup+0.100
iction+0.098
Neg logit contributions
002-0.119
003-0.111
 Stretch-0.110
 Reef-0.109
662-0.107
Token his
Token ID465
Feature activation+1.22e-02

Pos logit contributions
002+0.346
003+0.323
 Reef+0.315
 Stretch+0.315
662+0.311
Neg logit contributions
undai-0.330
ascus-0.312
ottesville-0.307
occup-0.302
 assailant-0.300
Token performance
Token ID2854
Feature activation+1.39e-01

Pos logit contributions
undai+0.040
ascus+0.038
ottesville+0.037
occup+0.036
 assailant+0.036
Neg logit contributions
002-0.048
003-0.045
 Stretch-0.044
 Reef-0.044
662-0.043
Token on
Token ID319
Feature activation-4.14e-01

Pos logit contributions
undai+0.476
ascus+0.453
ottesville+0.446
occup+0.440
 assailant+0.432
Neg logit contributions
002-0.516
003-0.484
 Stretch-0.475
 Reef-0.473
662-0.466
Token the
Token ID262
Feature activation-2.12e-01

Pos logit contributions
002+1.504
003+1.403
 Reef+1.376
 Stretch+1.376
662+1.348
Neg logit contributions
undai-1.484
ascus-1.400
ottesville-1.387
occup-1.358
iction-1.331
Token road
Token ID2975
Feature activation+1.01e-01

Pos logit contributions
002+0.780
003+0.730
 Reef+0.704
 Stretch+0.700
662+0.694
Neg logit contributions
undai-0.757
ascus-0.704
ottesville-0.704
occup-0.686
 assailant-0.680
Token this
Token ID428
Feature activation+2.00e-02

Pos logit contributions
undai+0.343
ascus+0.326
ottesville+0.323
occup+0.316
iction+0.309
Neg logit contributions
002-0.385
003-0.361
 Stretch-0.354
 Reef-0.354
662-0.346
Token season
Token ID1622
Feature activation-7.00e-03

Pos logit contributions
undai+0.061
ascus+0.057
ottesville+0.056
occup+0.055
 assailant+0.054
Neg logit contributions
002-0.084
003-0.079
 Reef-0.078
 Stretch-0.077
662-0.077
Token social
Token ID1919
Feature activation+3.71e-02

Pos logit contributions
002+0.807
003+0.750
 Reef+0.730
662+0.724
 Stretch+0.724
Neg logit contributions
undai-0.845
ascus-0.805
ottesville-0.788
occup-0.783
iction-0.773
Token media
Token ID2056
Feature activation+5.78e-01

Pos logit contributions
undai+0.157
ascus+0.151
ottesville+0.149
iction+0.146
occup+0.146
Neg logit contributions
002-0.109
003-0.100
 Reef-0.098
 Stretch-0.096
662-0.095
Token,
Token ID11
Feature activation-8.83e-02

Pos logit contributions
undai+1.986
ascus+1.939
ottesville+1.887
iction+1.867
occup+1.867
Neg logit contributions
002-2.096
003-1.948
 Reef-1.902
 Stretch-1.901
662-1.885
Token and
Token ID290
Feature activation+7.42e-02

Pos logit contributions
002+0.339
003+0.317
 Stretch+0.312
 Reef+0.311
662+0.305
Neg logit contributions
undai-0.293
ascus-0.279
ottesville-0.271
occup-0.270
iction-0.267
Token it
Token ID340
Feature activation-3.23e-02

Pos logit contributions
undai+0.254
ascus+0.239
occup+0.233
 assailant+0.233
ottesville+0.232
Neg logit contributions
002-0.276
003-0.256
662-0.249
 Stretch-0.249
 Reef-0.249
Token's
Token ID338
Feature activation-9.71e-02

Pos logit contributions
002+0.121
003+0.113
 Stretch+0.112
 Reef+0.112
662+0.110
Neg logit contributions
undai-0.111
ascus-0.105
ottesville-0.103
occup-0.102
 assailant-0.100
Token a
Token ID257
Feature activation-1.01e-01

Pos logit contributions
002+0.374
003+0.349
 Stretch+0.340
 Reef+0.338
662+0.335
Neg logit contributions
undai-0.326
ascus-0.313
ottesville-0.301
occup-0.298
 assailant-0.297
Token different
Token ID1180
Feature activation+6.87e-03

Pos logit contributions
002+0.368
003+0.342
 Stretch+0.333
 Reef+0.330
662+0.330
Neg logit contributions
undai-0.361
ascus-0.342
ottesville-0.333
occup-0.329
iction-0.326
Token path
Token ID3108
Feature activation-2.38e-01

Pos logit contributions
undai+0.023
ascus+0.022
ottesville+0.021
occup+0.021
 assailant+0.021
Neg logit contributions
002-0.027
003-0.025
 Stretch-0.024
 Reef-0.024
662-0.024
Token,"
Token ID553
Feature activation-1.26e-01

Pos logit contributions
002+0.920
003+0.860
 Stretch+0.851
 Reef+0.845
662+0.832
Neg logit contributions
undai-0.792
ascus-0.748
ottesville-0.738
occup-0.729
iction-0.714
Token says
Token ID1139
Feature activation+1.97e-02

Pos logit contributions
002+0.444
003+0.412
 Reef+0.402
 Stretch+0.400
662+0.398
Neg logit contributions
undai-0.461
ascus-0.439
ottesville-0.434
occup-0.425
 assailant-0.421
Token free
Token ID1479
Feature activation+6.91e-02

Pos logit contributions
undai+0.720
ascus+0.671
 assailant+0.666
 attacker+0.664
ottesville+0.662
Neg logit contributions
002-0.758
003-0.707
 Reef-0.679
662-0.675
 Dialogue-0.675
Token agents
Token ID6554
Feature activation-1.15e-01

Pos logit contributions
undai+0.233
ottesville+0.218
ascus+0.215
occup+0.212
 assailant+0.212
Neg logit contributions
002-0.264
003-0.247
 Reef-0.242
 Stretch-0.239
 Dialogue-0.238
Token.
Token ID13
Feature activation+1.57e-02

Pos logit contributions
002+0.448
003+0.420
 Reef+0.409
 Stretch+0.407
662+0.405
Neg logit contributions
undai-0.380
ascus-0.354
ottesville-0.350
occup-0.344
 assailant-0.342
Token If
Token ID1002
Feature activation+2.14e-01

Pos logit contributions
undai+0.054
ottesville+0.052
occup+0.051
iction+0.051
ascus+0.051
Neg logit contributions
002-0.056
003-0.052
662-0.050
 Reef-0.050
 Stretch-0.050
Token they
Token ID484
Feature activation-1.94e-01

Pos logit contributions
undai+0.813
ascus+0.767
ottesville+0.765
occup+0.752
 assailant+0.740
Neg logit contributions
002-0.726
003-0.674
 Reef-0.654
 Stretch-0.652
662-0.651
Token decide
Token ID5409
Feature activation-1.26e-01

Pos logit contributions
002+0.692
003+0.645
 Reef+0.627
 Stretch+0.624
662+0.619
Neg logit contributions
undai-0.707
ascus-0.672
ottesville-0.660
occup-0.654
 assailant-0.640
Token too
Token ID1165
Feature activation-4.99e-01

Pos logit contributions
002+0.466
003+0.435
 Stretch+0.424
 Reef+0.423
662+0.419
Neg logit contributions
undai-0.444
ascus-0.419
ottesville-0.415
occup-0.403
 assailant-0.399
Token quickly
Token ID2952
Feature activation-2.82e-01

Pos logit contributions
002+2.051
003+1.929
 Stretch+1.903
 Reef+1.899
662+1.864
Neg logit contributions
undai-1.556
ascus-1.459
ottesville-1.441
occup-1.402
iction-1.374
Token,
Token ID11
Feature activation-2.87e-01

Pos logit contributions
002+1.003
003+0.932
 Stretch+0.917
 Reef+0.915
662+0.896
Neg logit contributions
undai-1.032
ascus-0.978
ottesville-0.968
occup-0.948
iction-0.931
Token they
Token ID484
Feature activation-2.77e-01

Pos logit contributions
002+1.026
003+0.955
 Reef+0.936
 Stretch+0.932
662+0.922
Neg logit contributions
undai-1.045
ascus-0.984
ottesville-0.976
occup-0.960
 assailant-0.946
Token risk
Token ID2526
Feature activation-7.05e-01

Pos logit contributions
002+1.114
003+1.048
 Stretch+1.026
 Reef+1.026
662+1.012
Neg logit contributions
undai-0.882
ascus-0.826
ottesville-0.817
occup-0.803
iction-0.788
Tokenia
Token ID544
Feature activation-4.13e-01

Pos logit contributions
002+0.166
003+0.156
 Stretch+0.155
 Reef+0.154
662+0.149
Neg logit contributions
undai-0.156
ascus-0.148
ottesville-0.145
occup-0.144
iction-0.142
Token looked
Token ID3114
Feature activation-7.10e-01

Pos logit contributions
002+1.436
003+1.331
 Stretch+1.312
 Reef+1.306
662+1.289
Neg logit contributions
undai-1.528
ascus-1.448
ottesville-1.434
occup-1.415
 assailant-1.393
Token up
Token ID510
Feature activation-7.90e-01

Pos logit contributions
002+2.679
003+2.504
 Stretch+2.469
 Reef+2.462
662+2.412
Neg logit contributions
undai-2.444
ascus-2.307
ottesville-2.280
occup-2.229
iction-2.187
Token.
Token ID13
Feature activation-5.18e-01

Pos logit contributions
002+2.776
003+2.583
 Stretch+2.543
 Reef+2.533
662+2.482
Neg logit contributions
undai-2.930
ascus-2.781
ottesville-2.748
occup-2.695
iction-2.647
Token Her
Token ID2332
Feature activation-6.16e-01

Pos logit contributions
002+1.589
003+1.455
 Stretch+1.429
 Reef+1.427
662+1.401
Neg logit contributions
undai-2.108
ascus-2.015
ottesville-2.000
occup-1.983
iction-1.949
Token eyes
Token ID2951
Feature activation-1.02e+00

Pos logit contributions
002+2.235
003+2.078
 Stretch+2.039
 Reef+2.027
662+1.998
Neg logit contributions
undai-2.216
ascus-2.110
ottesville-2.063
occup-2.044
 assailant-2.036
Token were
Token ID547
Feature activation-3.40e-01

Pos logit contributions
002+3.672
003+3.422
 Stretch+3.373
 Reef+3.361
662+3.287
Neg logit contributions
undai-3.677
ascus-3.481
ottesville-3.442
occup-3.359
iction-3.305
Token still
Token ID991
Feature activation-7.09e-01

Pos logit contributions
002+1.256
003+1.174
 Stretch+1.151
 Reef+1.149
662+1.131
Neg logit contributions
undai-1.193
ascus-1.130
ottesville-1.118
occup-1.102
 assailant-1.080
Token red
Token ID2266
Feature activation-2.53e-01

Pos logit contributions
002+2.599
003+2.425
 Stretch+2.390
 Reef+2.383
662+2.333
Neg logit contributions
undai-2.519
ascus-2.384
ottesville-2.358
occup-2.307
iction-2.264
Token from
Token ID422
Feature activation+7.41e-02

Pos logit contributions
002+0.942
003+0.884
 Stretch+0.873
 Reef+0.868
662+0.854
Neg logit contributions
undai-0.878
ascus-0.834
ottesville-0.826
occup-0.809
iction-0.794
Token cutting
Token ID7720
Feature activation+1.66e-02

Pos logit contributions
undai+0.268
ascus+0.253
ottesville+0.249
occup+0.246
 assailant+0.243
Neg logit contributions
002-0.265
003-0.246
 Stretch-0.242
 Reef-0.240
662-0.239
Token It
Token ID632
Feature activation+1.18e-01

Pos logit contributions
undai+0.525
ascus+0.502
ottesville+0.500
occup+0.491
iction+0.487
Neg logit contributions
002-0.482
003-0.447
 Reef-0.440
 Stretch-0.437
662-0.432
Token just
Token ID655
Feature activation+1.83e-02

Pos logit contributions
undai+0.388
ascus+0.367
ottesville+0.363
occup+0.358
iction+0.349
Neg logit contributions
002-0.454
 Reef-0.425
003-0.424
 Stretch-0.423
662-0.412
Token creates
Token ID8075
Feature activation+5.33e-01

Pos logit contributions
undai+0.060
ascus+0.058
ottesville+0.057
occup+0.056
iction+0.055
Neg logit contributions
002-0.070
003-0.066
 Reef-0.065
 Stretch-0.065
662-0.064
Token a
Token ID257
Feature activation+1.19e-01

Pos logit contributions
undai+1.751
ascus+1.675
ottesville+1.667
iction+1.624
 assailant+1.620
Neg logit contributions
002-1.998
003-1.865
 Reef-1.849
 Stretch-1.819
662-1.790
Token mapping
Token ID16855
Feature activation+6.69e-02

Pos logit contributions
undai+0.390
ascus+0.370
ottesville+0.365
occup+0.355
iction+0.354
Neg logit contributions
002-0.461
003-0.431
 Reef-0.424
 Stretch-0.421
662-0.415
Token onto
Token ID4291
Feature activation-4.43e-01

Pos logit contributions
undai+0.242
ascus+0.233
ottesville+0.229
occup+0.226
iction+0.226
Neg logit contributions
002-0.234
003-0.217
 Reef-0.214
 Stretch-0.213
662-0.208
Token the
Token ID262
Feature activation-3.21e-01

Pos logit contributions
002+1.615
003+1.506
 Reef+1.480
 Stretch+1.477
662+1.448
Neg logit contributions
undai-1.576
ascus-1.493
ottesville-1.477
occup-1.449
 assailant-1.426
Token data
Token ID1366
Feature activation-8.03e-02

Pos logit contributions
002+1.238
003+1.160
 Reef+1.138
 Stretch+1.136
662+1.115
Neg logit contributions
undai-1.078
ascus-1.018
ottesville-1.006
occup-0.985
 assailant-0.971
Token that
Token ID326
Feature activation-2.92e-02

Pos logit contributions
002+0.297
003+0.278
 Reef+0.275
 Stretch+0.274
662+0.266
Neg logit contributions
undai-0.280
ascus-0.265
ottesville-0.263
occup-0.257
iction-0.254
Token you
Token ID345
Feature activation+3.52e-02

Pos logit contributions
002+0.112
003+0.105
 Reef+0.103
 Stretch+0.103
662+0.101
Neg logit contributions
undai-0.097
ascus-0.092
ottesville-0.092
occup-0.090
iction-0.088
Token provide
Token ID2148
Feature activation+1.41e-01

Pos logit contributions
undai+0.107
ascus+0.101
ottesville+0.100
occup+0.098
iction+0.096
Neg logit contributions
002-0.144
 Reef-0.136
003-0.136
 Stretch-0.135
662-0.132
Token essay
Token ID14268
Feature activation+4.16e-01

Pos logit contributions
undai+0.510
ascus+0.482
ottesville+0.476
occup+0.474
 assailant+0.472
Neg logit contributions
002-0.562
003-0.521
 Stretch-0.511
 Reef-0.509
662-0.503
Token on
Token ID319
Feature activation+2.44e-01

Pos logit contributions
undai+1.450
ottesville+1.381
ascus+1.375
occup+1.368
 assailant+1.337
Neg logit contributions
002-1.497
 Reef-1.399
 Stretch-1.393
003-1.389
662-1.358
Token the
Token ID262
Feature activation-7.90e-02

Pos logit contributions
undai+0.854
occup+0.795
ascus+0.793
ottesville+0.789
 assailant+0.779
Neg logit contributions
002-0.882
003-0.821
 Stretch-0.802
662-0.799
 Reef-0.786
Token cover
Token ID3002
Feature activation-2.66e-01

Pos logit contributions
002+0.268
003+0.248
 Stretch+0.243
 Reef+0.241
662+0.240
Neg logit contributions
undai-0.301
ascus-0.283
ottesville-0.281
occup-0.278
 assailant-0.277
Token of
Token ID286
Feature activation-4.12e-01

Pos logit contributions
002+0.961
003+0.894
 Stretch+0.887
 Reef+0.884
662+0.862
Neg logit contributions
undai-0.949
ascus-0.900
ottesville-0.895
occup-0.877
 assailant-0.861
Token Harper
Token ID12686
Feature activation-5.47e-01

Pos logit contributions
002+1.370
003+1.268
 Stretch+1.243
 Reef+1.234
662+1.217
Neg logit contributions
undai-1.601
ascus-1.517
ottesville-1.498
occup-1.483
iction-1.455
Token
Token ID447
Feature activation-1.54e-01

Pos logit contributions
002+1.993
003+1.860
 Stretch+1.839
 Reef+1.824
662+1.795
Neg logit contributions
undai-1.932
ascus-1.823
ottesville-1.814
occup-1.790
iction-1.752
Token
Token ID247
Feature activation-2.16e-01

Pos logit contributions
002+0.366
003+0.329
 Stretch+0.327
 Reef+0.322
662+0.310
Neg logit contributions
undai-0.736
ascus-0.702
ottesville-0.701
occup-0.687
iction-0.684
Tokens
Token ID82
Feature activation-2.44e-01

Pos logit contributions
002+0.730
003+0.675
 Stretch+0.669
 Reef+0.663
662+0.653
Neg logit contributions
undai-0.824
ascus-0.782
ottesville-0.775
occup-0.764
iction-0.762
Token,
Token ID11
Feature activation-1.27e-01

Pos logit contributions
002+0.851
003+0.788
 Stretch+0.774
 Reef+0.767
662+0.761
Neg logit contributions
undai-0.912
ascus-0.862
ottesville-0.850
occup-0.839
iction-0.832
Token and
Token ID290
Feature activation+1.38e-01

Pos logit contributions
002+0.443
003+0.412
 Stretch+0.406
 Reef+0.403
662+0.396
Neg logit contributions
undai-0.471
ascus-0.446
ottesville-0.440
occup-0.437
iction-0.431
Token.
Token ID13
Feature activation+5.09e-02

Pos logit contributions
002+0.826
003+0.771
 Stretch+0.760
 Reef+0.758
662+0.741
Neg logit contributions
undai-0.789
ascus-0.746
ottesville-0.738
occup-0.721
iction-0.708
Token
Token ID198
Feature activation+3.60e-01

Pos logit contributions
undai+0.166
ottesville+0.156
ascus+0.156
occup+0.156
iction+0.153
Neg logit contributions
002-0.193
003-0.180
 Stretch-0.176
 Reef-0.175
662-0.175
Token
Token ID198
Feature activation+2.92e-01

Pos logit contributions
undai+0.948
occup+0.948
ottesville+0.918
iction+0.909
ascus+0.897
Neg logit contributions
002-1.505
 Stretch-1.425
 Reef-1.415
003-1.414
DAQ-1.382
TokenThe
Token ID464
Feature activation+6.59e-02

Pos logit contributions
undai+0.902
occup+0.852
ottesville+0.834
ascus+0.832
iction+0.813
Neg logit contributions
002-1.154
 Stretch-1.101
 Reef-1.093
003-1.083
 Dialogue-1.060
Token big
Token ID1263
Feature activation+4.16e-01

Pos logit contributions
undai+0.230
ascus+0.214
ottesville+0.210
occup+0.208
 assailant+0.207
Neg logit contributions
002-0.246
003-0.231
 Stretch-0.224
 Reef-0.223
662-0.222
Token hope
Token ID2911
Feature activation-7.58e-01

Pos logit contributions
undai+1.370
ascus+1.281
ottesville+1.268
occup+1.254
 assailant+1.234
Neg logit contributions
002-1.611
003-1.506
 Reef-1.462
 Stretch-1.459
662-1.457
Token is
Token ID318
Feature activation-1.91e-01

Pos logit contributions
002+2.823
003+2.636
 Stretch+2.600
 Reef+2.592
662+2.538
Neg logit contributions
undai-2.647
ascus-2.500
ottesville-2.473
occup-2.417
iction-2.371
Token that
Token ID326
Feature activation-3.43e-02

Pos logit contributions
002+0.666
003+0.619
 Stretch+0.609
 Reef+0.601
662+0.599
Neg logit contributions
undai-0.711
ascus-0.669
ottesville-0.661
occup-0.651
 assailant-0.643
Token the
Token ID262
Feature activation+1.25e-01

Pos logit contributions
002+0.128
003+0.120
 Stretch+0.117
 Reef+0.116
662+0.116
Neg logit contributions
undai-0.119
ascus-0.112
ottesville-0.111
occup-0.108
 assailant-0.108
Token country
Token ID1499
Feature activation-3.14e-02

Pos logit contributions
undai+0.424
ascus+0.395
ottesville+0.391
 assailant+0.384
occup+0.382
Neg logit contributions
002-0.471
003-0.442
 Stretch-0.430
662-0.428
 Reef-0.428
Token can
Token ID460
Feature activation-9.91e-02

Pos logit contributions
002+0.121
003+0.113
 Stretch+0.111
 Reef+0.111
662+0.109
Neg logit contributions
undai-0.106
ascus-0.099
ottesville-0.099
occup-0.097
 assailant-0.095
Token
Token ID447
Feature activation+1.78e-01

Pos logit contributions
002+0.111
003+0.103
 Reef+0.102
 Stretch+0.102
662+0.100
Neg logit contributions
undai-0.113
ascus-0.106
ottesville-0.105
occup-0.105
iction-0.102
Token
Token ID247
Feature activation+6.75e-02

Pos logit contributions
undai+0.851
ascus+0.810
occup+0.810
ottesville+0.810
iction+0.800
Neg logit contributions
002-0.387
 Stretch-0.362
003-0.349
 Dialogue-0.339
 Reef-0.338
Tokens
Token ID82
Feature activation+7.64e-02

Pos logit contributions
undai+0.267
occup+0.253
ascus+0.253
ottesville+0.251
iction+0.247
Neg logit contributions
002-0.213
 Stretch-0.197
 Reef-0.197
003-0.195
 Dialogue-0.190
Token effortlessly
Token ID42241
Feature activation-3.19e-01

Pos logit contributions
undai+0.262
ascus+0.247
ottesville+0.241
occup+0.239
 assailant+0.237
Neg logit contributions
002-0.288
003-0.268
 Stretch-0.262
 Reef-0.261
662-0.258
Token imaginative
Token ID41138
Feature activation-1.50e-01

Pos logit contributions
002+1.156
003+1.076
 Stretch+1.055
 Reef+1.051
662+1.031
Neg logit contributions
undai-1.145
ascus-1.086
ottesville-1.073
occup-1.049
iction-1.037
Token,
Token ID11
Feature activation-3.12e-01

Pos logit contributions
002+0.558
003+0.520
 Stretch+0.509
 Reef+0.507
662+0.500
Neg logit contributions
undai-0.522
ascus-0.495
ottesville-0.488
occup-0.485
 assailant-0.476
Token as
Token ID355
Feature activation-3.69e-01

Pos logit contributions
002+1.150
003+1.072
 Stretch+1.056
 Reef+1.051
662+1.029
Neg logit contributions
undai-1.101
ascus-1.042
ottesville-1.029
occup-1.016
iction-0.998
Token are
Token ID389
Feature activation-2.35e-01

Pos logit contributions
002+1.375
003+1.280
 Reef+1.265
 Stretch+1.258
662+1.241
Neg logit contributions
undai-1.285
ascus-1.203
ottesville-1.191
occup-1.180
iction-1.159
Token the
Token ID262
Feature activation-1.76e-01

Pos logit contributions
002+0.858
003+0.801
 Stretch+0.786
 Reef+0.786
662+0.771
Neg logit contributions
undai-0.837
ascus-0.788
ottesville-0.778
occup-0.771
iction-0.754
Token sweeping
Token ID18404
Feature activation-2.04e-01

Pos logit contributions
002+0.619
003+0.576
 Stretch+0.563
 Reef+0.562
662+0.553
Neg logit contributions
undai-0.647
ascus-0.612
ottesville-0.605
occup-0.597
 assailant-0.593
Token back
Token ID736
Feature activation-3.93e-01

Pos logit contributions
002+0.705
003+0.655
 Stretch+0.641
 Reef+0.639
662+0.630
Neg logit contributions
undai-0.759
ascus-0.721
ottesville-0.713
occup-0.702
 assailant-0.695
Token law
Token ID1099
Feature activation-2.76e-01

Pos logit contributions
002+0.439
003+0.410
 Stretch+0.407
 Reef+0.403
662+0.395
Neg logit contributions
undai-0.394
ascus-0.365
ottesville-0.364
occup-0.361
 assailant-0.352
Token,
Token ID11
Feature activation+2.65e-01

Pos logit contributions
002+0.998
003+0.929
 Stretch+0.921
 Reef+0.913
662+0.895
Neg logit contributions
undai-0.991
ascus-0.937
ottesville-0.926
occup-0.910
 assailant-0.895
Token the
Token ID262
Feature activation-6.76e-03

Pos logit contributions
undai+0.895
ascus+0.839
 assailant+0.826
occup+0.825
ottesville+0.818
Neg logit contributions
002-0.998
003-0.928
 Stretch-0.927
 Reef-0.907
662-0.899
Token Commission
Token ID4513
Feature activation+2.01e-02

Pos logit contributions
002+0.025
003+0.023
 Stretch+0.023
 Reef+0.023
662+0.023
Neg logit contributions
undai-0.024
ascus-0.022
 assailant-0.022
ottesville-0.022
occup-0.022
Token can
Token ID460
Feature activation-3.02e-01

Pos logit contributions
undai+0.065
ascus+0.062
ottesville+0.061
occup+0.060
 assailant+0.059
Neg logit contributions
002-0.079
003-0.074
 Stretch-0.073
 Reef-0.073
662-0.072
Token fine
Token ID3734
Feature activation-1.08e+00

Pos logit contributions
002+1.165
003+1.089
 Stretch+1.076
 Reef+1.075
662+1.051
Neg logit contributions
undai-1.013
ascus-0.959
ottesville-0.946
occup-0.930
iction-0.911
Token companies
Token ID2706
Feature activation-1.11e-01

Pos logit contributions
002+3.952
003+3.695
 Reef+3.632
 Stretch+3.628
662+3.546
Neg logit contributions
undai-3.850
ascus-3.649
ottesville-3.624
occup-3.507
iction-3.443
Token found
Token ID1043
Feature activation-3.33e-01

Pos logit contributions
002+0.436
003+0.406
 Stretch+0.406
 Reef+0.400
662+0.394
Neg logit contributions
undai-0.362
ascus-0.340
ottesville-0.331
occup-0.331
 assailant-0.328
Token guilty
Token ID6717
Feature activation-2.55e-01

Pos logit contributions
002+1.191
003+1.108
 Stretch+1.093
 Reef+1.089
662+1.066
Neg logit contributions
undai-1.217
ascus-1.151
ottesville-1.139
occup-1.117
iction-1.097
Token of
Token ID286
Feature activation-7.42e-02

Pos logit contributions
002+0.907
003+0.844
 Stretch+0.832
 Reef+0.829
662+0.811
Neg logit contributions
undai-0.935
ascus-0.887
ottesville-0.877
occup-0.860
iction-0.845
Token price
Token ID2756
Feature activation-1.42e-01

Pos logit contributions
002+0.282
003+0.263
 Stretch+0.260
 Reef+0.256
662+0.255
Neg logit contributions
undai-0.252
ascus-0.235
ottesville-0.233
occup-0.231
 assailant-0.228
Token don
Token ID836
Feature activation-6.05e-02

Pos logit contributions
002+0.853
003+0.796
 Reef+0.786
 Stretch+0.776
662+0.768
Neg logit contributions
undai-0.739
ascus-0.691
occup-0.683
ottesville-0.682
 assailant-0.669
Token
Token ID447
Feature activation-5.99e-02

Pos logit contributions
002+0.177
 Stretch+0.165
 Reef+0.163
003+0.161
 Dialogue+0.158
Neg logit contributions
undai-0.243
occup-0.239
ottesville-0.236
ascus-0.234
iction-0.234
Token
Token ID247
Feature activation+1.20e-01

Pos logit contributions
002+0.131
 Stretch+0.119
003+0.117
 Reef+0.113
 Dialogue+0.112
Neg logit contributions
undai-0.293
ottesville-0.280
ascus-0.278
occup-0.276
iction-0.276
Tokent
Token ID83
Feature activation-7.81e-02

Pos logit contributions
undai+0.369
ascus+0.343
ottesville+0.342
occup+0.338
iction+0.334
Neg logit contributions
002-0.485
 Reef-0.459
 Stretch-0.456
003-0.455
 Dialogue-0.444
Token be
Token ID307
Feature activation-1.51e-01

Pos logit contributions
002+0.296
003+0.276
 Reef+0.270
 Stretch+0.268
662+0.266
Neg logit contributions
undai-0.267
ascus-0.252
ottesville-0.248
occup-0.246
iction-0.242
Token afraid
Token ID7787
Feature activation-1.16e+00

Pos logit contributions
002+0.546
003+0.507
 Reef+0.497
 Stretch+0.496
662+0.489
Neg logit contributions
undai-0.545
ascus-0.514
ottesville-0.509
occup-0.503
iction-0.494
Token to
Token ID284
Feature activation-7.94e-01

Pos logit contributions
002+3.627
003+3.378
 Stretch+3.316
 Reef+3.296
662+3.210
Neg logit contributions
undai-4.707
ascus-4.464
ottesville-4.459
occup-4.281
iction-4.220
Token send
Token ID3758
Feature activation-3.63e-01

Pos logit contributions
002+3.051
003+2.858
 Stretch+2.829
 Reef+2.814
662+2.754
Neg logit contributions
undai-2.675
ascus-2.519
ottesville-2.495
occup-2.424
iction-2.378
Token this
Token ID428
Feature activation-2.98e-01

Pos logit contributions
002+1.424
003+1.329
 Reef+1.308
 Stretch+1.295
662+1.284
Neg logit contributions
undai-1.179
ascus-1.116
ottesville-1.098
occup-1.083
 assailant-1.081
Token post
Token ID1281
Feature activation-1.01e-01

Pos logit contributions
002+1.103
003+1.024
 Reef+1.003
 Stretch+1.003
662+0.989
Neg logit contributions
undai-1.042
ascus-0.991
ottesville-0.974
occup-0.961
 assailant-0.957
Token to
Token ID284
Feature activation-2.56e-01

Pos logit contributions
002+0.366
003+0.340
 Reef+0.337
 Stretch+0.335
662+0.329
Neg logit contributions
undai-0.355
ascus-0.339
ottesville-0.334
occup-0.331
iction-0.325
Token one
Token ID530
Feature activation+1.58e-01

Pos logit contributions
undai+0.146
ascus+0.136
ottesville+0.136
occup+0.134
 assailant+0.133
Neg logit contributions
002-0.144
003-0.134
 Reef-0.132
 Stretch-0.130
662-0.130
Token of
Token ID286
Feature activation+3.27e-01

Pos logit contributions
undai+0.536
ascus+0.513
 assailant+0.501
occup+0.499
ottesville+0.499
Neg logit contributions
002-0.588
003-0.547
 Reef-0.542
 Stretch-0.532
662-0.529
Token Lois
Token ID42879
Feature activation-5.57e-01

Pos logit contributions
undai+1.097
ottesville+1.027
ascus+1.024
occup+1.014
 assailant+0.999
Neg logit contributions
002-1.230
003-1.150
 Reef-1.122
662-1.113
 Stretch-1.112
Token G
Token ID402
Feature activation+1.52e-01

Pos logit contributions
002+1.599
003+1.462
 Stretch+1.431
 Reef+1.430
662+1.390
Neg logit contributions
undai-2.413
ascus-2.314
ottesville-2.295
occup-2.250
iction-2.216
Token.
Token ID13
Feature activation-1.92e-01

Pos logit contributions
undai+0.493
ascus+0.467
ottesville+0.465
iction+0.453
occup+0.451
Neg logit contributions
002-0.602
003-0.561
 Reef-0.561
 Stretch-0.558
662-0.544
Token Lerner
Token ID49750
Feature activation-1.18e+00

Pos logit contributions
002+0.594
003+0.550
 Reef+0.527
 Stretch+0.524
662+0.517
Neg logit contributions
undai-0.763
ascus-0.752
ottesville-0.742
occup-0.729
iction-0.717
Token
Token ID447
Feature activation-2.30e-01

Pos logit contributions
002+4.065
003+3.777
 Stretch+3.721
 Reef+3.706
662+3.615
Neg logit contributions
undai-4.478
ascus-4.245
ottesville-4.194
occup-4.097
iction-4.032
Token
Token ID247
Feature activation-2.51e-01

Pos logit contributions
002+0.615
 Reef+0.559
 Stretch+0.559
003+0.557
 Dialogue+0.536
Neg logit contributions
undai-1.026
ascus-0.982
ottesville-0.971
occup-0.966
iction-0.949
Tokens
Token ID82
Feature activation-3.10e-01

Pos logit contributions
002+0.859
 Reef+0.799
003+0.794
 Stretch+0.789
662+0.767
Neg logit contributions
undai-0.932
ascus-0.894
ottesville-0.882
occup-0.882
iction-0.858
Token apparently
Token ID5729
Feature activation-2.42e-01

Pos logit contributions
002+1.136
003+1.055
 Reef+1.042
 Stretch+1.029
662+1.009
Neg logit contributions
undai-1.097
ascus-1.052
ottesville-1.031
occup-1.020
 assailant-1.014
Token lost
Token ID2626
Feature activation-5.68e-01

Pos logit contributions
002+0.939
003+0.879
 Stretch+0.865
 Reef+0.864
662+0.846
Neg logit contributions
undai-0.804
ascus-0.763
ottesville-0.752
occup-0.736
 assailant-0.727
TokenPont
Token ID48039
Feature activation-3.65e-01

Pos logit contributions
undai+1.831
occup+1.724
ascus+1.719
ottesville+1.679
iction+1.640
Neg logit contributions
002-1.615
003-1.503
662-1.454
 Reef-1.447
 Stretch-1.438
Token and
Token ID290
Feature activation-3.74e-01

Pos logit contributions
002+1.336
003+1.247
 Stretch+1.230
 Reef+1.225
662+1.201
Neg logit contributions
undai-1.294
ascus-1.225
ottesville-1.202
occup-1.181
 assailant-1.165
Token Dow
Token ID21842
Feature activation-3.61e-01

Pos logit contributions
002+1.119
003+1.024
 Stretch+0.991
 Reef+0.981
662+0.975
Neg logit contributions
undai-1.559
ascus-1.487
occup-1.463
ottesville-1.457
 assailant-1.444
Token Chemical
Token ID24872
Feature activation-4.94e-01

Pos logit contributions
002+1.218
003+1.132
 Stretch+1.113
 Reef+1.102
662+1.082
Neg logit contributions
undai-1.392
ascus-1.322
ottesville-1.299
occup-1.277
 assailant-1.254
Token were
Token ID547
Feature activation-1.11e-01

Pos logit contributions
002+1.877
003+1.757
 Stretch+1.732
 Reef+1.723
662+1.693
Neg logit contributions
undai-1.693
ascus-1.600
ottesville-1.568
occup-1.536
iction-1.513
Token fined
Token ID22643
Feature activation-1.05e+00

Pos logit contributions
002+0.429
003+0.402
 Stretch+0.395
 Reef+0.392
662+0.385
Neg logit contributions
undai-0.371
ascus-0.348
ottesville-0.344
occup-0.339
 assailant-0.334
Token 59
Token ID7863
Feature activation+1.88e-02

Pos logit contributions
002+3.916
003+3.658
 Stretch+3.608
 Reef+3.598
662+3.519
Neg logit contributions
undai-3.653
ascus-3.450
ottesville-3.410
occup-3.334
iction-3.275
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
undai+0.057
ascus+0.054
ottesville+0.053
occup+0.052
iction+0.051
Neg logit contributions
002-0.077
 Reef-0.072
003-0.072
 Stretch-0.072
 Dialogue-0.070
Token3
Token ID18
Feature activation-1.06e-02

Pos logit contributions
002+0.433
 Reef+0.401
 Stretch+0.401
003+0.399
 Dialogue+0.384
Neg logit contributions
undai-0.549
ascus-0.527
ottesville-0.525
occup-0.517
iction-0.511
Tokenm
Token ID76
Feature activation-1.21e-02

Pos logit contributions
002+0.045
003+0.042
 Stretch+0.042
 Reef+0.042
662+0.041
Neg logit contributions
undai-0.032
ascus-0.029
ottesville-0.029
occup-0.028
iction-0.028
Token and
Token ID290
Feature activation-1.81e-01

Pos logit contributions
002+0.052
003+0.049
 Stretch+0.049
 Reef+0.049
662+0.048
Neg logit contributions
undai-0.035
ascus-0.033
ottesville-0.032
occup-0.031
iction-0.031
Tokene
Token ID68
Feature activation-9.46e-01

Pos logit contributions
002+2.963
003+2.734
 Reef+2.658
 Stretch+2.644
662+2.590
Neg logit contributions
undai-3.944
ascus-3.757
ottesville-3.740
occup-3.664
 assailant-3.607
Tokence
Token ID344
Feature activation-9.57e-01

Pos logit contributions
002+3.558
 Stretch+3.384
 Reef+3.382
003+3.291
 Dialogue+3.251
Neg logit contributions
undai-3.170
ascus-3.007
occup-2.951
ottesville-2.947
iction-2.883
Token/
Token ID14
Feature activation-1.41e+00

Pos logit contributions
002+3.372
003+3.146
 Reef+3.056
 Stretch+3.050
662+2.992
Neg logit contributions
undai-3.593
ascus-3.403
ottesville-3.367
occup-3.280
iction-3.213
Tokenedd
Token ID6048
Feature activation-5.20e-01

Pos logit contributions
002+4.812
003+4.481
662+4.293
 Stretch+4.200
 Reef+4.197
Neg logit contributions
undai-5.389
ascus-5.129
ottesville-5.093
 assailant-4.897
occup-4.884
Token75
Token ID2425
Feature activation-4.21e-01

Pos logit contributions
002+1.713
003+1.585
 Stretch+1.569
 Reef+1.563
662+1.517
Neg logit contributions
undai-2.037
ascus-1.937
ottesville-1.917
occup-1.880
iction-1.852
Token/
Token ID14
Feature activation-1.40e+00

Pos logit contributions
002+1.570
003+1.466
 Stretch+1.461
 Reef+1.453
662+1.411
Neg logit contributions
undai-1.457
ascus-1.376
ottesville-1.361
occup-1.336
iction-1.316
TokenAUT
Token ID39371
Feature activation-1.98e-01

Pos logit contributions
002+4.255
003+3.905
662+3.653
 Reef+3.645
 Stretch+3.523
Neg logit contributions
undai-5.937
ascus-5.791
ottesville-5.605
 assailant-5.459
occup-5.358
TokenOC
Token ID4503
Feature activation-7.21e-01

Pos logit contributions
002+0.580
003+0.532
 Stretch+0.528
 Reef+0.525
662+0.506
Neg logit contributions
undai-0.841
ottesville-0.801
ascus-0.800
occup-0.786
iction-0.773
TokenR
Token ID49
Feature activation+9.19e-02

Pos logit contributions
002+1.992
003+1.813
 Stretch+1.772
 Reef+1.767
662+1.716
Neg logit contributions
undai-3.225
ascus-3.091
ottesville-3.057
occup-3.000
iction-2.962
TokenOP
Token ID3185
Feature activation-1.68e-01

Pos logit contributions
undai+0.353
ascus+0.332
ottesville+0.331
occup+0.330
iction+0.326
Neg logit contributions
002-0.300
 Stretch-0.277
 Reef-0.277
003-0.276
662-0.269
Token/
Token ID14
Feature activation-7.70e-01

Pos logit contributions
002+0.618
003+0.577
 Stretch+0.569
 Reef+0.567
662+0.555
Neg logit contributions
undai-0.593
ascus-0.560
ottesville-0.555
occup-0.542
iction-0.533