TOP ACTIVATIONS
MAX = 14.331

Height : 6 3 Weight
limit : 7 R TS thr : off Frag ment thr
, 0 . 5 ) ) = 0 . 1 //
Subscribe via RSS or daily email Contact the editor about
Height ), $ SR . Width , $ SR . Height
ANT ITY OF A LC OH OL TO MAKE THE BE
app data _ full v ) { v . vertex .
beats other vendors by leaps and bounds . There are custom
appearance , genital ia , birth certificate and chromosomes one
amount " , Range ( 0 , 0 . 5 )
+= v . normal * 1 ; } The
C , Y YR DS cent ering The Garg
in New Jersey with severe birth defects caused by the Zika
app data _ full v ) { // Time component const
1994 John Lar ro qu ette 1994
: Forward Height : 6 3
ulse period " , Float ) = 1 // seconds
their children s birth , and a hungry pel
Barack Hussein Obama With low birth rate , America needs future
Why 1910 ? The birth year of Akira Kuro s

MIN ACTIVATIONS
MIN = -14.934

ago when se ared a hi was a trend , they
there , waiting in the back of an SUV , wearing
Hundreds streamed down the a is les for the altar call
salt , pepper and chill i by tasting .
1 2 3 4 5 6 7 8 9 10 11
awesome grappling hook aw es omen ess ! Having done any
stop awesome grappling hook aw es omen ess ! Having done
_ ev ans 12 19 / Inst agram Now
=" Phone List Ctrl "> < ul > < li ng
they streamed down the a is les , this time to
a grid : void V ort on Sim ::
you credit for your aw es omen ess .
credit for your aw es omen ess . If
wheelchair ( Figure 2 A , [ Action Junior 3 ,
. A voice in the back of my head , probably
her self as someone he / she is not through acts
's Chicago - based he i ress Beat rice Joyce Ke
the world . ( Wa ub ges hig Rice / CBC
he used every dirty trick he could think of to secure
in Boston . ( Wa ub ges hig Rice / CBC

INTERVAL 7.015 - 14.331
CONTAINS 0.204%

re closed now ! come get your kids !
ve been there for almost 12 hours as I
с р о с ь о�
Offic iers et les F ond ateurs cher cher ont un
via the ix g be driver for speeds up to

INTERVAL -0.302 - 7.015
CONTAINS 56.291%

logs . To see the logs for the function test for
along , my dear , come along , it will pass
year . Civil Vessel s N uclear
technology , as political data wizards like to say , has
who have never let worries of appearing tedious stand in the

INTERVAL -7.618 - -0.302
CONTAINS 43.393%

. Again , the United States did not raise interest rates
guns are carried in America , and both actually expand the
We 're looking into two other scenarios that may allow us
statistics and think : " Well , that seems like a
. Furthermore , what these theorists ignore entirely is that the

INTERVAL -14.934 - -7.618
CONTAINS 0.112%

stop awesome grappling hook aw es omen ess ! Having done
Wa ub ges hig Rice / CBC ) Insp
. w bur . org / 2015 / 08 / 11
Av arg ues - We ber ( Un ivers ité de
grown from a single congregation to embrace millions . Today Br
TokenHeight
Token ID23106
Feature activation+6.89e+00

Pos logit contributions
arenthood+2.657
udeb+2.266
eve+2.222
atism+2.213
 Commit+2.153
Neg logit contributions
hots-6.599
 Scor-6.001
gang-5.940
hs-5.880
onga-5.874
Token:
Token ID25
Feature activation+1.15e+01

Pos logit contributions
arenthood+3.301
atism+2.920
"},+2.820
utenberg+2.769
emet+2.751
Neg logit contributions
hots-6.307
hs-5.647
 Scor-5.531
gang-5.522
onga-5.503
Token 6
Token ID718
Feature activation+9.37e+00

Pos logit contributions
arenthood+4.957
Position+4.400
atism+4.361
}"+4.312
"},+4.282
Neg logit contributions
hots-10.610
heid-9.287
hs-9.215
onga-9.159
gang-9.124
Token
Token ID447
Feature activation+1.33e+00

Pos logit contributions
arenthood+4.830
atism+4.408
emet+4.277
"},+4.271
eve+4.265
Neg logit contributions
hots-7.979
 Scor-6.897
gang-6.880
onga-6.870
hs-6.662
Token
Token ID247
Feature activation+1.01e+01

Pos logit contributions
arenthood+1.144
atism+1.084
eve+1.052
udeb+1.036
emet+1.033
Neg logit contributions
hots-0.762
gang-0.638
onga-0.628
 Scor-0.626
hs-0.606
Token3
Token ID18
Feature activation+1.43e+01

Pos logit contributions
arenthood+5.754
"},+5.397
}"+5.354
 Nept+5.336
atism+5.261
Neg logit contributions
hots-7.658
gang-6.709
 Scor-6.634
onga-6.501
hs-6.324
Token
Token ID447
Feature activation+9.00e-01

Pos logit contributions
arenthood+7.908
"},+7.035
}"+7.009
atism+6.982
ativity+6.856
Neg logit contributions
hots-10.925
gang-9.634
 Scor-9.543
hs-9.318
onga-9.297
Token
Token ID251
Feature activation+1.03e+01

Pos logit contributions
arenthood+0.755
atism+0.709
eve+0.687
udeb+0.681
emet+0.680
Neg logit contributions
hots-0.540
gang-0.448
 Scor-0.443
onga-0.443
hs-0.429
Token
Token ID198
Feature activation+4.66e+00

Pos logit contributions
arenthood+5.835
}"+5.371
 Nept+5.332
"},+5.279
atism+5.257
Neg logit contributions
hots-7.963
gang-7.021
 Scor-6.782
onga-6.772
hs-6.604
Token
Token ID198
Feature activation+9.02e+00

Pos logit contributions
arenthood+2.686
eve+2.436
atism+2.401
"},+2.361
udeb+2.359
Neg logit contributions
hots-3.858
onga-3.390
gang-3.358
 Scor-3.347
��-3.319
TokenWeight
Token ID25844
Feature activation+5.58e+00

Pos logit contributions
arenthood+4.077
Position+3.524
eve+3.495
atism+3.483
}"+3.447
Neg logit contributions
hots-8.365
 Scor-7.438
onga-7.406
gang-7.302
 waitress-7.277
Token limit
Token ID4179
Feature activation+3.35e+00

Pos logit contributions
hots+0.687
gang+0.603
 Scor+0.596
hs+0.588
onga+0.588
Neg logit contributions
arenthood-0.508
atism-0.468
udeb-0.455
eve-0.454
emet-0.451
Token:
Token ID25
Feature activation+8.05e+00

Pos logit contributions
arenthood+1.683
atism+1.490
eve+1.479
udeb+1.468
emet+1.440
Neg logit contributions
hots-3.051
gang-2.709
 Scor-2.705
onga-2.701
hs-2.629
Token7
Token ID22
Feature activation-1.97e+00

Pos logit contributions
arenthood+4.163
atism+3.772
eve+3.731
udeb+3.706
emet+3.661
Neg logit contributions
hots-6.784
onga-6.038
 Scor-6.027
gang-5.990
hs-5.825
Token R
Token ID371
Feature activation+3.36e+00

Pos logit contributions
hots+1.211
gang+1.024
 Scor+1.009
hs+1.002
onga+0.999
Neg logit contributions
arenthood-1.604
atism-1.509
udeb-1.483
emet-1.469
eve-1.462
TokenTS
Token ID4694
Feature activation+5.64e+00

Pos logit contributions
arenthood+1.990
atism+1.846
udeb+1.795
emet+1.755
ativity+1.751
Neg logit contributions
hots-2.768
gang-2.474
 Scor-2.452
onga-2.416
 Prohibition-2.343
Token thr
Token ID5636
Feature activation+1.40e+01

Pos logit contributions
arenthood+2.779
atism+2.577
eve+2.456
emet+2.426
udeb+2.395
Neg logit contributions
hots-5.089
gang-4.543
onga-4.501
 Scor-4.450
hs-4.324
Token:
Token ID25
Feature activation+4.62e+00

Pos logit contributions
arenthood+4.393
"},+3.796
eve+3.713
}"+3.624
udeb+3.617
Neg logit contributions
hots-13.342
��-13.021
 looph-12.578
 comr-12.444
 waitress-12.279
Tokenoff
Token ID2364
Feature activation+1.75e-02

Pos logit contributions
arenthood+3.488
eve+3.382
udeb+3.330
atism+3.298
emet+3.213
Neg logit contributions
hots-2.792
 Scor-2.485
onga-2.365
 Prohibition-2.363
gang-2.339
Token Frag
Token ID24229
Feature activation+9.29e-01

Pos logit contributions
arenthood+0.011
atism+0.010
udeb+0.010
emet+0.010
eve+0.010
Neg logit contributions
hots-0.014
gang-0.012
onga-0.012
hs-0.012
 Scor-0.012
Tokenment
Token ID434
Feature activation-3.50e-01

Pos logit contributions
arenthood+0.808
atism+0.766
udeb+0.755
emet+0.753
eve+0.751
Neg logit contributions
hots-0.516
 Scor-0.421
gang-0.417
onga-0.414
hs-0.404
Token thr
Token ID5636
Feature activation+9.08e+00

Pos logit contributions
hots+0.284
gang+0.251
onga+0.247
 Scor+0.247
hs+0.245
Neg logit contributions
arenthood-0.216
atism-0.200
udeb-0.194
emet-0.192
eve-0.191
Token,
Token ID837
Feature activation+2.86e+00

Pos logit contributions
arenthood+3.790
eve+3.399
 ][+3.366
00007+3.116
 Commit+3.023
Neg logit contributions
hots-12.725
��-11.507
onga-11.369
 looph-11.043
 Scor-11.010
Token 0
Token ID657
Feature activation+5.91e+00

Pos logit contributions
arenthood+1.375
atism+1.224
eve+1.218
udeb+1.210
emet+1.181
Neg logit contributions
hots-2.669
gang-2.386
onga-2.377
 Scor-2.327
hs-2.289
Token.
Token ID13
Feature activation+4.95e+00

Pos logit contributions
arenthood+3.336
udeb+3.042
eve+3.033
emet+2.938
atism+2.930
Neg logit contributions
hots-4.923
onga-4.340
 Scor-4.265
gang-4.254
��-4.145
Token5
Token ID20
Feature activation+2.68e+00

Pos logit contributions
arenthood+2.963
eve+2.724
udeb+2.689
emet+2.641
atism+2.638
Neg logit contributions
hots-4.046
onga-3.487
gang-3.422
 Scor-3.418
hs-3.314
Token )
Token ID1267
Feature activation+9.03e+00

Pos logit contributions
arenthood+1.350
udeb+1.187
eve+1.181
atism+1.177
emet+1.176
Neg logit contributions
hots-2.480
gang-2.214
onga-2.189
 Scor-2.175
hs-2.137
Token )
Token ID1267
Feature activation+1.34e+01

Pos logit contributions
arenthood+3.538
eve+3.175
 Commit+2.916
emet+2.898
 Nept+2.879
Neg logit contributions
hots-8.941
gang-8.013
 Scor-7.915
onga-7.888
��-7.779
Token =
Token ID796
Feature activation+6.46e+00

Pos logit contributions
arenthood+4.292
 Commit+3.886
 ][+3.775
eve+3.770
 Nept+3.643
Neg logit contributions
hots-13.065
��-11.762
 Scor-11.525
 looph-11.469
gang-11.447
Token 0
Token ID657
Feature activation+9.03e+00

Pos logit contributions
arenthood+2.609
atism+2.375
eve+2.323
udeb+2.235
 Nept+2.227
Neg logit contributions
hots-6.216
gang-5.697
onga-5.563
 Scor-5.488
SPONSORED-5.478
Token.
Token ID13
Feature activation+2.74e+00

Pos logit contributions
arenthood+4.538
eve+4.093
udeb+4.077
 Nept+3.966
 ][+3.950
Neg logit contributions
hots-7.779
onga-6.951
��-6.911
 Scor-6.694
gang-6.671
Token1
Token ID16
Feature activation+6.77e+00

Pos logit contributions
arenthood+1.864
udeb+1.708
atism+1.700
eve+1.692
emet+1.657
Neg logit contributions
hots-2.058
 Scor-1.740
gang-1.739
onga-1.735
hs-1.678
Token //
Token ID3373
Feature activation-1.96e+00

Pos logit contributions
arenthood+4.218
eve+3.860
atism+3.852
emet+3.783
udeb+3.765
Neg logit contributions
hots-5.143
onga-4.578
gang-4.434
 Scor-4.320
SPONSORED-4.293
Token
Token ID198
Feature activation+6.11e-01

Pos logit contributions
hots+1.668
gang+1.444
 Scor+1.420
hs+1.419
onga+1.410
Neg logit contributions
arenthood-1.722
atism-1.613
udeb-1.579
emet-1.564
eve-1.545
TokenSubscribe
Token ID27125
Feature activation+7.05e+00

Pos logit contributions
arenthood+0.411
atism+0.378
udeb+0.374
eve+0.368
emet+0.368
Neg logit contributions
hots-0.464
gang-0.403
 Scor-0.401
onga-0.398
hs-0.395
Token via
Token ID2884
Feature activation+2.59e+00

Pos logit contributions
arenthood+4.078
atism+3.697
udeb+3.646
"},+3.613
emet+3.591
Neg logit contributions
hots-5.685
gang-5.077
onga-4.964
hs-4.890
 Scor-4.762
Token RSS
Token ID25012
Feature activation+3.24e+00

Pos logit contributions
arenthood+1.458
atism+1.327
udeb+1.308
emet+1.292
eve+1.285
Neg logit contributions
hots-2.231
gang-1.984
hs-1.955
onga-1.948
 Scor-1.933
Token or
Token ID393
Feature activation+7.19e+00

Pos logit contributions
arenthood+1.990
atism+1.835
udeb+1.791
emet+1.778
eve+1.741
Neg logit contributions
hots-2.594
gang-2.287
hs-2.267
onga-2.250
 Scor-2.238
Token daily
Token ID4445
Feature activation+1.32e+01

Pos logit contributions
arenthood+4.098
udeb+3.770
 Nept+3.686
"},+3.674
emet+3.640
Neg logit contributions
hots-5.762
gang-5.190
onga-5.168
hs-5.152
zb-4.904
Token email
Token ID3053
Feature activation+4.89e+00

Pos logit contributions
arenthood+7.226
udeb+6.709
emet+6.438
 Commit+6.405
atism+6.386
Neg logit contributions
hots-9.574
gang-8.812
onga-8.630
hs-8.577
��-8.322
Token Contact
Token ID14039
Feature activation+3.03e-01

Pos logit contributions
arenthood+3.003
atism+2.730
udeb+2.652
emet+2.630
eve+2.614
Neg logit contributions
hots-3.855
gang-3.435
onga-3.404
hs-3.345
 Scor-3.309
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
arenthood+0.196
atism+0.181
udeb+0.177
emet+0.175
eve+0.174
Neg logit contributions
hots-0.237
gang-0.208
 Scor-0.205
onga-0.204
hs-0.204
Token editor
Token ID5464
Feature activation+5.78e-02

Pos logit contributions
arenthood+1.056
atism+0.960
udeb+0.941
eve+0.932
emet+0.930
Neg logit contributions
hots-1.415
gang-1.251
onga-1.228
 Scor-1.223
hs-1.217
Token about
Token ID546
Feature activation+3.69e+00

Pos logit contributions
arenthood+0.037
atism+0.034
udeb+0.033
emet+0.033
eve+0.033
Neg logit contributions
hots-0.046
gang-0.040
onga-0.039
 Scor-0.039
hs-0.039
TokenHeight
Token ID23106
Feature activation+7.20e+00

Pos logit contributions
arenthood+1.142
atism+1.031
udeb+1.024
emet+0.995
eve+0.989
Neg logit contributions
hots-2.085
gang-1.882
onga-1.875
 Scor-1.870
hs-1.806
Token),
Token ID828
Feature activation+1.57e+00

Pos logit contributions
arenthood+4.925
emet+4.544
atism+4.521
udeb+4.464
eve+4.423
Neg logit contributions
hots-5.087
gang-4.370
 Scor-4.317
onga-4.291
hs-4.118
Token$
Token ID3
Feature activation-1.23e+00

Pos logit contributions
arenthood+1.073
atism+0.998
udeb+0.978
emet+0.970
eve+0.962
Neg logit contributions
hots-1.170
gang-1.015
 Scor-1.005
onga-0.998
hs-0.993
TokenSR
Token ID12562
Feature activation+7.18e+00

Pos logit contributions
hots+0.872
gang+0.753
hs+0.742
 Scor+0.737
onga+0.736
Neg logit contributions
arenthood-0.894
atism-0.834
udeb-0.818
emet-0.809
eve-0.805
Token.
Token ID13
Feature activation+6.62e+00

Pos logit contributions
arenthood+3.718
udeb+3.482
"},+3.356
}"+3.310
eve+3.307
Neg logit contributions
hots-6.149
��-5.508
onga-5.459
 Scor-5.369
gang-5.365
TokenWidth
Token ID30916
Feature activation+1.31e+01

Pos logit contributions
arenthood+2.931
udeb+2.594
atism+2.591
emet+2.512
eve+2.495
Neg logit contributions
hots-6.306
gang-5.708
 Scor-5.679
onga-5.667
hs-5.449
Token,
Token ID11
Feature activation+2.99e-01

Pos logit contributions
arenthood+6.856
atism+6.182
emet+6.083
eve+6.056
udeb+5.985
Neg logit contributions
hots-10.650
gang-9.443
 Scor-9.309
onga-9.132
hs-9.019
Token$
Token ID3
Feature activation-1.84e+00

Pos logit contributions
arenthood+0.195
atism+0.180
udeb+0.179
eve+0.176
emet+0.176
Neg logit contributions
hots-0.231
 Scor-0.201
gang-0.201
onga-0.199
hs-0.196
TokenSR
Token ID12562
Feature activation+2.88e+00

Pos logit contributions
hots+1.271
gang+1.094
 Scor+1.076
onga+1.073
hs+1.072
Neg logit contributions
arenthood-1.360
atism-1.271
udeb-1.246
emet-1.234
eve-1.227
Token.
Token ID13
Feature activation+4.84e+00

Pos logit contributions
arenthood+1.755
udeb+1.610
atism+1.588
eve+1.579
emet+1.551
Neg logit contributions
hots-2.318
onga-2.038
 Scor-2.020
gang-2.014
hs-1.953
TokenHeight
Token ID23106
Feature activation+4.23e+00

Pos logit contributions
arenthood+1.807
udeb+1.563
}"+1.480
atism+1.478
"},+1.476
Neg logit contributions
hots-4.951
onga-4.545
gang-4.540
 Scor-4.494
��-4.374
TokenANT
Token ID8643
Feature activation+9.36e-01

Pos logit contributions
hots+0.897
gang+0.774
 Scor+0.761
onga+0.759
hs+0.758
Neg logit contributions
arenthood-0.934
atism-0.872
udeb-0.855
emet-0.847
eve-0.842
TokenITY
Token ID9050
Feature activation+1.32e+00

Pos logit contributions
arenthood+0.714
atism+0.665
udeb+0.656
emet+0.648
eve+0.644
Neg logit contributions
hots-0.629
gang-0.537
onga-0.528
 Scor-0.527
hs-0.523
Token OF
Token ID3963
Feature activation-2.40e+00

Pos logit contributions
arenthood+0.959
atism+0.885
udeb+0.874
emet+0.865
eve+0.863
Neg logit contributions
hots-0.921
gang-0.799
onga-0.792
hs-0.772
 Scor-0.760
Token A
Token ID317
Feature activation-2.86e+00

Pos logit contributions
hots+1.687
gang+1.457
 Scor+1.437
onga+1.428
hs+1.428
Neg logit contributions
arenthood-1.740
atism-1.625
udeb-1.593
emet-1.577
eve-1.567
TokenLC
Token ID5639
Feature activation-1.72e+00

Pos logit contributions
hots+1.993
gang+1.721
 Scor+1.698
hs+1.686
onga+1.685
Neg logit contributions
arenthood-2.095
atism-1.961
udeb-1.917
emet-1.900
eve-1.888
TokenOH
Token ID12096
Feature activation+1.31e+01

Pos logit contributions
hots+0.981
gang+0.819
 Scor+0.804
onga+0.797
hs+0.797
Neg logit contributions
arenthood-1.476
atism-1.395
udeb-1.371
emet-1.358
eve-1.352
TokenOL
Token ID3535
Feature activation-1.27e+00

Pos logit contributions
arenthood+6.667
 Commit+5.935
 Nept+5.910
udeb+5.901
"},+5.661
Neg logit contributions
hots-11.071
hs-9.806
��-9.560
onga-9.393
heid-9.332
Token TO
Token ID5390
Feature activation-2.67e+00

Pos logit contributions
hots+0.903
gang+0.780
onga+0.766
 Scor+0.763
hs+0.762
Neg logit contributions
arenthood-0.923
atism-0.859
udeb-0.843
emet-0.836
eve-0.830
Token MAKE
Token ID39134
Feature activation-3.81e+00

Pos logit contributions
hots+1.926
gang+1.675
 Scor+1.653
onga+1.644
hs+1.641
Neg logit contributions
arenthood-1.885
atism-1.759
udeb-1.719
emet-1.702
eve-1.692
Token THE
Token ID3336
Feature activation-3.71e+00

Pos logit contributions
hots+2.704
gang+2.338
 Scor+2.330
hs+2.301
onga+2.291
Neg logit contributions
arenthood-2.729
atism-2.567
udeb-2.496
emet-2.481
eve-2.455
Token BE
Token ID9348
Feature activation+2.08e+00

Pos logit contributions
hots+2.543
gang+2.189
 Scor+2.163
hs+2.145
onga+2.143
Neg logit contributions
arenthood-2.754
atism-2.579
udeb-2.523
emet-2.502
eve-2.485
Token app
Token ID598
Feature activation-2.47e+00

Pos logit contributions
arenthood+1.816
atism+1.699
eve+1.644
udeb+1.637
emet+1.636
Neg logit contributions
hots-2.223
gang-1.954
onga-1.928
 Scor-1.910
hs-1.879
Tokendata
Token ID7890
Feature activation-1.22e+00

Pos logit contributions
hots+1.012
gang+0.782
hs+0.748
onga+0.738
 Scor+0.732
Neg logit contributions
arenthood-2.514
atism-2.396
udeb-2.360
emet-2.343
eve-2.328
Token _
Token ID4808
Feature activation-2.83e-02

Pos logit contributions
hots+0.947
gang+0.829
 Scor+0.818
onga+0.815
hs+0.814
Neg logit contributions
arenthood-0.799
atism-0.740
udeb-0.723
emet-0.716
eve-0.711
Token full
Token ID1336
Feature activation+1.26e+00

Pos logit contributions
hots+0.020
gang+0.018
 Scor+0.017
onga+0.017
hs+0.017
Neg logit contributions
arenthood-0.020
atism-0.019
udeb-0.018
emet-0.018
eve-0.018
Token v
Token ID410
Feature activation+2.39e+00

Pos logit contributions
arenthood+0.950
atism+0.891
udeb+0.874
emet+0.869
eve+0.865
Neg logit contributions
hots-0.848
gang-0.721
 Scor-0.713
onga-0.707
hs-0.697
Token )
Token ID1267
Feature activation+1.28e+01

Pos logit contributions
arenthood+1.224
atism+1.085
udeb+1.056
emet+1.045
eve+1.045
Neg logit contributions
hots-2.198
gang-1.964
 Scor-1.939
onga-1.931
hs-1.878
Token {
Token ID1391
Feature activation-1.49e+00

Pos logit contributions
arenthood+5.060
eve+4.448
 mars+4.179
 Commit+4.081
utenberg+4.069
Neg logit contributions
hots-12.052
SPONSORED-10.828
 Scor-10.804
gang-10.730
��-10.681
Token v
Token ID410
Feature activation+8.17e+00

Pos logit contributions
hots+0.886
gang+0.744
 Scor+0.732
onga+0.728
hs+0.727
Neg logit contributions
arenthood-1.248
atism-1.175
udeb-1.156
emet-1.146
eve-1.138
Token.
Token ID764
Feature activation+6.43e+00

Pos logit contributions
arenthood+4.077
udeb+3.696
atism+3.603
eve+3.566
 Nept+3.494
Neg logit contributions
hots-7.160
onga-6.267
��-6.264
 Scor-6.226
gang-6.197
Token vertex
Token ID37423
Feature activation+5.91e+00

Pos logit contributions
arenthood+4.227
atism+4.009
eve+3.909
udeb+3.807
 mars+3.801
Neg logit contributions
hots-4.850
gang-4.224
onga-4.084
 Scor-4.067
hs-3.960
Token.
Token ID764
Feature activation+8.68e+00

Pos logit contributions
arenthood+3.235
atism+2.972
eve+2.950
udeb+2.925
emet+2.845
Neg logit contributions
hots-5.039
onga-4.389
gang-4.359
 Scor-4.347
SPONSORED-4.182
Token beats
Token ID17825
Feature activation+2.02e+00

Pos logit contributions
arenthood+0.745
atism+0.693
eve+0.664
udeb+0.664
emet+0.660
Neg logit contributions
hots-0.969
gang-0.858
onga-0.842
hs-0.840
 Scor-0.828
Token other
Token ID584
Feature activation+7.27e-01

Pos logit contributions
arenthood+1.305
atism+1.212
emet+1.198
eve+1.194
udeb+1.182
Neg logit contributions
hots-1.539
gang-1.373
onga-1.341
hs-1.334
 Scor-1.297
Token vendors
Token ID17192
Feature activation+6.30e-01

Pos logit contributions
arenthood+0.468
atism+0.431
eve+0.423
udeb+0.422
emet+0.421
Neg logit contributions
hots-0.566
gang-0.499
onga-0.490
hs-0.490
 Scor-0.481
Token by
Token ID416
Feature activation+1.48e+00

Pos logit contributions
arenthood+0.421
atism+0.391
emet+0.383
udeb+0.380
eve+0.379
Neg logit contributions
hots-0.469
gang-0.415
onga-0.408
hs-0.404
 Scor-0.403
Token leaps
Token ID37312
Feature activation-1.88e+00

Pos logit contributions
arenthood+0.975
atism+0.908
emet+0.885
eve+0.880
udeb+0.879
Neg logit contributions
hots-1.119
gang-0.992
onga-0.962
hs-0.957
 Scor-0.956
Token and
Token ID290
Feature activation+1.28e+01

Pos logit contributions
hots+1.249
gang+1.059
 Scor+1.037
hs+1.035
onga+1.033
Neg logit contributions
arenthood-1.449
atism-1.371
udeb-1.349
emet-1.333
eve-1.312
Token bounds
Token ID22303
Feature activation+2.11e+00

Pos logit contributions
arenthood+3.765
 mars+3.762
 twists+3.463
eve+3.448
atism+3.244
Neg logit contributions
hots-12.540
��-12.382
gang-12.089
onga-11.707
 Scor-11.503
Token.
Token ID13
Feature activation+4.43e-01

Pos logit contributions
arenthood+1.354
atism+1.242
eve+1.218
emet+1.215
udeb+1.208
Neg logit contributions
hots-1.621
gang-1.447
 Scor-1.411
onga-1.406
hs-1.393
Token There
Token ID1318
Feature activation-1.39e+00

Pos logit contributions
arenthood+0.297
atism+0.274
eve+0.270
udeb+0.269
emet+0.267
Neg logit contributions
hots-0.335
gang-0.292
onga-0.288
hs-0.284
 Scor-0.280
Token are
Token ID389
Feature activation+9.77e-01

Pos logit contributions
hots+1.026
gang+0.893
 Scor+0.879
onga+0.877
hs+0.875
Neg logit contributions
arenthood-0.966
atism-0.899
udeb-0.881
emet-0.872
eve-0.866
Token custom
Token ID2183
Feature activation-4.62e+00

Pos logit contributions
arenthood+0.639
atism+0.595
eve+0.583
emet+0.580
udeb+0.579
Neg logit contributions
hots-0.742
gang-0.655
onga-0.640
hs-0.635
 Scor-0.634
Token appearance
Token ID5585
Feature activation+2.06e+00

Pos logit contributions
arenthood+0.193
atism+0.180
udeb+0.174
emet+0.173
eve+0.172
Neg logit contributions
hots-0.208
gang-0.180
 Scor-0.177
hs-0.177
onga-0.177
Token,
Token ID11
Feature activation-3.27e+00

Pos logit contributions
arenthood+1.442
atism+1.341
ativity+1.289
emet+1.277
udeb+1.274
Neg logit contributions
hots-1.515
gang-1.320
onga-1.308
 Scor-1.283
hs-1.274
Token genital
Token ID24678
Feature activation+5.56e-01

Pos logit contributions
hots+2.389
gang+2.079
 Scor+2.050
hs+2.041
onga+2.039
Neg logit contributions
arenthood-2.262
atism-2.107
udeb-2.080
emet-2.060
eve-2.046
Tokenia
Token ID544
Feature activation+4.47e+00

Pos logit contributions
arenthood+0.437
atism+0.413
emet+0.397
udeb+0.396
eve+0.395
Neg logit contributions
hots-0.360
gang-0.306
 Scor-0.300
onga-0.300
hs-0.298
Token,
Token ID11
Feature activation+2.33e+00

Pos logit contributions
arenthood+2.980
atism+2.750
ativity+2.625
emet+2.588
eve+2.587
Neg logit contributions
hots-3.401
gang-3.005
onga-2.953
 Scor-2.925
hs-2.906
Token birth
Token ID4082
Feature activation+1.27e+01

Pos logit contributions
arenthood+1.620
atism+1.493
udeb+1.439
emet+1.436
ativity+1.425
Neg logit contributions
hots-1.735
gang-1.499
 Scor-1.479
onga-1.477
hs-1.471
Token certificate
Token ID10703
Feature activation+1.99e+00

Pos logit contributions
arenthood+7.321
atism+6.244
eve+6.184
ativity+6.090
"},+5.940
Neg logit contributions
hots-10.086
 Scor-8.787
onga-8.624
zb-8.438
gang-8.390
Token and
Token ID290
Feature activation+1.79e+00

Pos logit contributions
arenthood+1.353
atism+1.242
emet+1.201
eve+1.197
udeb+1.196
Neg logit contributions
hots-1.501
gang-1.313
onga-1.287
 Scor-1.282
hs-1.276
Token chromosomes
Token ID42742
Feature activation+1.94e+00

Pos logit contributions
arenthood+1.193
atism+1.091
udeb+1.054
emet+1.053
eve+1.045
Neg logit contributions
hots-1.375
gang-1.195
onga-1.183
 Scor-1.177
hs-1.177
Token
Token ID960
Feature activation+4.18e+00

Pos logit contributions
arenthood+1.421
atism+1.313
udeb+1.275
emet+1.269
eve+1.259
Neg logit contributions
hots-1.365
gang-1.187
onga-1.165
 Scor-1.155
hs-1.152
Tokenone
Token ID505
Feature activation-2.32e-02

Pos logit contributions
arenthood+2.899
atism+2.727
udeb+2.653
eve+2.642
emet+2.609
Neg logit contributions
hots-2.993
 Scor-2.636
onga-2.549
gang-2.543
hs-2.501
Token amount
Token ID2033
Feature activation+4.66e+00

Pos logit contributions
arenthood+1.431
atism+1.292
udeb+1.192
emet+1.189
"},+1.168
Neg logit contributions
hots-3.712
gang-3.348
 Scor-3.325
onga-3.248
hs-3.237
Token"
Token ID1
Feature activation+8.30e+00

Pos logit contributions
arenthood+2.064
atism+1.840
"},+1.789
udeb+1.767
emet+1.758
Neg logit contributions
hots-4.502
gang-4.038
onga-4.016
 Scor-3.952
hs-3.895
Token,
Token ID837
Feature activation+4.55e+00

Pos logit contributions
arenthood+2.884
atism+2.448
emet+2.424
 ][+2.339
 Nept+2.298
Neg logit contributions
hots-8.611
gang-7.567
onga-7.553
SPONSORED-7.543
 Scor-7.480
Token Range
Token ID13667
Feature activation+7.09e+00

Pos logit contributions
arenthood+2.903
atism+2.733
emet+2.683
udeb+2.673
eve+2.656
Neg logit contributions
hots-3.397
gang-2.990
onga-2.847
la-2.824
heid-2.823
Token (
Token ID357
Feature activation+1.04e+01

Pos logit contributions
arenthood+4.351
eve+4.050
emet+4.017
atism+3.993
udeb+3.988
Neg logit contributions
hots-5.451
onga-4.638
gang-4.631
 Scor-4.588
��-4.520
Token 0
Token ID657
Feature activation+1.22e+01

Pos logit contributions
arenthood+3.326
atism+2.995
eve+2.991
udeb+2.989
 ][+2.880
Neg logit contributions
hots-10.256
gang-9.507
��-9.382
onga-9.378
SPONSORED-9.157
Token,
Token ID837
Feature activation+2.86e+00

Pos logit contributions
arenthood+3.790
eve+3.399
 ][+3.366
00007+3.116
 Commit+3.023
Neg logit contributions
hots-12.725
��-11.507
onga-11.369
 looph-11.043
 Scor-11.010
Token 0
Token ID657
Feature activation+5.91e+00

Pos logit contributions
arenthood+1.375
atism+1.224
eve+1.218
udeb+1.210
emet+1.181
Neg logit contributions
hots-2.669
gang-2.386
onga-2.377
 Scor-2.327
hs-2.289
Token.
Token ID13
Feature activation+4.95e+00

Pos logit contributions
arenthood+3.336
udeb+3.042
eve+3.033
emet+2.938
atism+2.930
Neg logit contributions
hots-4.923
onga-4.340
 Scor-4.265
gang-4.254
��-4.145
Token5
Token ID20
Feature activation+2.68e+00

Pos logit contributions
arenthood+2.963
eve+2.724
udeb+2.689
emet+2.641
atism+2.638
Neg logit contributions
hots-4.046
onga-3.487
gang-3.422
 Scor-3.418
hs-3.314
Token )
Token ID1267
Feature activation+9.03e+00

Pos logit contributions
arenthood+1.350
udeb+1.187
eve+1.181
atism+1.177
emet+1.176
Neg logit contributions
hots-2.480
gang-2.214
onga-2.189
 Scor-2.175
hs-2.137
Token +=
Token ID15853
Feature activation-3.29e+00

Pos logit contributions
arenthood+3.645
atism+3.334
utenberg+3.311
udeb+3.284
emet+3.261
Neg logit contributions
hots-3.653
 Scor-3.149
gang-3.097
SPONSORED-3.008
hs-2.951
Token v
Token ID410
Feature activation+5.80e+00

Pos logit contributions
hots+1.870
gang+1.564
 Scor+1.543
hs+1.542
onga+1.528
Neg logit contributions
arenthood-2.814
atism-2.642
udeb-2.609
emet-2.585
eve-2.559
Token.
Token ID764
Feature activation+6.41e+00

Pos logit contributions
arenthood+3.188
udeb+2.863
atism+2.850
eve+2.838
emet+2.743
Neg logit contributions
hots-4.928
onga-4.356
 Scor-4.287
gang-4.284
��-4.200
Token normal
Token ID3487
Feature activation+7.33e+00

Pos logit contributions
arenthood+3.904
atism+3.700
eve+3.499
udeb+3.489
emet+3.455
Neg logit contributions
hots-5.150
gang-4.555
onga-4.388
 Scor-4.385
hs-4.330
Token *
Token ID1635
Feature activation-1.35e+00

Pos logit contributions
arenthood+4.585
eve+4.238
udeb+4.195
atism+4.150
 Commit+4.085
Neg logit contributions
hots-5.748
gang-4.833
onga-4.822
 Scor-4.710
��-4.596
Token 1
Token ID352
Feature activation+1.19e+01

Pos logit contributions
hots+0.949
gang+0.818
 Scor+0.803
onga+0.801
hs+0.798
Neg logit contributions
arenthood-0.985
atism-0.920
udeb-0.900
emet-0.891
eve-0.889
Token ;
Token ID2162
Feature activation+6.81e+00

Pos logit contributions
arenthood+4.331
eve+3.781
udeb+3.655
 Commit+3.562
 Nept+3.535
Neg logit contributions
hots-11.694
onga-10.521
��-10.454
 Scor-10.343
gang-10.264
Token }
Token ID1782
Feature activation-2.90e+00

Pos logit contributions
arenthood+2.069
atism+1.669
udeb+1.634
eve+1.604
 Nept+1.588
Neg logit contributions
hots-7.478
onga-6.770
gang-6.735
 Scor-6.648
hs-6.565
Token
Token ID198
Feature activation+1.94e+00

Pos logit contributions
hots+1.914
hs+1.617
 Scor+1.613
gang+1.612
onga+1.593
Neg logit contributions
arenthood-2.220
atism-2.091
udeb-2.052
emet-2.025
ativity-1.995
Token
Token ID198
Feature activation+2.15e+00

Pos logit contributions
arenthood+1.246
atism+1.140
eve+1.131
udeb+1.123
emet+1.109
Neg logit contributions
hots-1.513
gang-1.320
onga-1.316
 Scor-1.311
hs-1.271
TokenThe
Token ID464
Feature activation+2.31e+00

Pos logit contributions
arenthood+1.404
atism+1.308
udeb+1.295
eve+1.283
emet+1.275
Neg logit contributions
hots-1.632
 Scor-1.436
gang-1.432
onga-1.406
hs-1.390
Token C
Token ID327
Feature activation+3.63e+00

Pos logit contributions
arenthood+1.916
atism+1.786
udeb+1.726
eve+1.711
emet+1.709
Neg logit contributions
hots-2.402
gang-2.083
onga-2.074
 Scor-2.037
hs-2.036
Token,
Token ID11
Feature activation-1.43e+00

Pos logit contributions
arenthood+2.305
atism+2.141
emet+2.090
udeb+2.057
eve+2.053
Neg logit contributions
hots-2.859
gang-2.475
 Scor-2.454
onga-2.448
hs-2.432
Token Y
Token ID575
Feature activation+7.87e+00

Pos logit contributions
hots+0.847
gang+0.709
 Scor+0.695
onga+0.693
hs+0.691
Neg logit contributions
arenthood-1.202
atism-1.133
udeb-1.114
emet-1.104
eve-1.098
TokenYR
Token ID38162
Feature activation+3.36e+00

Pos logit contributions
arenthood+5.163
emet+4.648
eve+4.621
udeb+4.603
atism+4.597
Neg logit contributions
hots-5.710
 Scor-4.991
gang-4.894
hs-4.785
heid-4.768
Token DS
Token ID17400
Feature activation+4.11e+00

Pos logit contributions
arenthood+2.304
atism+2.119
udeb+2.062
emet+2.061
eve+2.020
Neg logit contributions
hots-2.490
gang-2.137
onga-2.114
 Scor-2.104
hs-2.102
Token cent
Token ID1247
Feature activation+1.19e+01

Pos logit contributions
arenthood+2.691
atism+2.469
emet+2.412
udeb+2.408
eve+2.387
Neg logit contributions
hots-3.141
gang-2.702
 Scor-2.679
onga-2.676
hs-2.641
Tokenering
Token ID1586
Feature activation+3.30e+00

Pos logit contributions
arenthood+7.112
emet+6.546
atism+6.535
eve+6.364
udeb+6.168
Neg logit contributions
hots-8.736
gang-7.440
 Scor-7.381
onga-7.322
 Prohibition-7.275
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
arenthood+2.145
atism+1.996
emet+1.930
eve+1.908
ativity+1.900
Neg logit contributions
hots-2.527
gang-2.201
 Scor-2.189
onga-2.189
hs-2.172
Token
Token ID198
Feature activation-6.11e-01

Pos logit contributions
hots+0.956
gang+0.828
 Scor+0.816
onga+0.813
hs+0.811
Neg logit contributions
arenthood-0.941
atism-0.876
udeb-0.859
emet-0.850
eve-0.845
TokenThe
Token ID464
Feature activation+1.31e+00

Pos logit contributions
hots+0.477
gang+0.417
 Scor+0.414
onga+0.412
hs+0.410
Neg logit contributions
arenthood-0.397
atism-0.365
udeb-0.360
eve-0.355
emet-0.354
Token Garg
Token ID39013
Feature activation+2.21e+00

Pos logit contributions
arenthood+0.795
atism+0.731
udeb+0.723
emet+0.710
eve+0.704
Neg logit contributions
hots-1.072
gang-0.940
hs-0.933
onga-0.928
 Scor-0.916
Token in
Token ID287
Feature activation-3.69e-01

Pos logit contributions
arenthood+5.339
eve+4.799
emet+4.722
 mars+4.714
atism+4.592
Neg logit contributions
hots-7.768
gang-7.126
hs-6.775
 Scor-6.725
��-6.689
Token New
Token ID968
Feature activation+5.53e-01

Pos logit contributions
hots+0.263
gang+0.229
hs+0.223
onga+0.222
 Scor+0.221
Neg logit contributions
arenthood-0.264
atism-0.246
eve-0.239
emet-0.239
udeb-0.239
Token Jersey
Token ID8221
Feature activation+3.19e+00

Pos logit contributions
arenthood+0.399
atism+0.371
emet+0.361
eve+0.361
udeb+0.360
Neg logit contributions
hots-0.390
gang-0.338
hs-0.332
 Scor-0.331
onga-0.328
Token with
Token ID351
Feature activation+5.15e+00

Pos logit contributions
arenthood+2.106
atism+1.914
eve+1.871
emet+1.856
udeb+1.845
Neg logit contributions
hots-2.429
gang-2.158
hs-2.099
 Scor-2.084
onga-2.075
Token severe
Token ID6049
Feature activation+9.47e-01

Pos logit contributions
arenthood+3.296
atism+3.022
emet+3.005
eve+2.982
 Nept+2.940
Neg logit contributions
hots-3.864
gang-3.447
onga-3.314
hs-3.291
heid-3.255
Token birth
Token ID4082
Feature activation+1.18e+01

Pos logit contributions
arenthood+0.650
atism+0.608
eve+0.596
emet+0.588
udeb+0.582
Neg logit contributions
hots-0.703
gang-0.603
onga-0.591
hs-0.590
 Scor-0.582
Token defects
Token ID22448
Feature activation+1.87e+00

Pos logit contributions
arenthood+1.879
eve+1.491
 mars+1.308
emet+1.159
atism+1.148
Neg logit contributions
hots-13.931
��-12.983
 Scor-12.818
onga-12.636
zb-12.586
Token caused
Token ID4073
Feature activation+4.39e+00

Pos logit contributions
arenthood+1.217
atism+1.111
udeb+1.093
eve+1.091
emet+1.086
Neg logit contributions
hots-1.428
gang-1.274
onga-1.250
hs-1.245
 Scor-1.238
Token by
Token ID416
Feature activation+1.19e+00

Pos logit contributions
arenthood+2.795
atism+2.592
emet+2.506
udeb+2.501
eve+2.491
Neg logit contributions
hots-3.442
gang-3.024
 Scor-2.986
onga-2.974
hs-2.956
Token the
Token ID262
Feature activation+1.68e+00

Pos logit contributions
arenthood+0.769
atism+0.711
emet+0.694
eve+0.692
udeb+0.683
Neg logit contributions
hots-0.921
gang-0.803
hs-0.789
onga-0.788
 Scor-0.780
Token Zika
Token ID30861
Feature activation-3.57e-01

Pos logit contributions
arenthood+1.112
atism+1.029
emet+0.991
eve+0.989
 Nept+0.979
Neg logit contributions
hots-1.305
gang-1.121
hs-1.111
onga-1.111
 Scor-1.084
Token app
Token ID598
Feature activation-1.70e+00

Pos logit contributions
arenthood+2.019
atism+1.903
eve+1.850
emet+1.834
udeb+1.819
Neg logit contributions
hots-2.596
gang-2.268
onga-2.241
 Scor-2.221
hs-2.179
Tokendata
Token ID7890
Feature activation-9.72e-01

Pos logit contributions
hots+0.723
gang+0.560
 Scor+0.541
onga+0.538
hs+0.538
Neg logit contributions
arenthood-1.716
atism-1.634
udeb-1.611
emet-1.599
eve-1.592
Token _
Token ID4808
Feature activation-1.04e+00

Pos logit contributions
hots+0.635
gang+0.532
onga+0.527
 Scor+0.522
hs+0.521
Neg logit contributions
arenthood-0.761
atism-0.713
udeb-0.697
emet-0.697
eve-0.694
Token full
Token ID1336
Feature activation+6.64e-01

Pos logit contributions
hots+0.747
gang+0.645
 Scor+0.636
onga+0.635
hs+0.630
Neg logit contributions
arenthood-0.739
atism-0.689
udeb-0.673
emet-0.668
eve-0.664
Token v
Token ID410
Feature activation+2.21e+00

Pos logit contributions
arenthood+0.514
atism+0.484
udeb+0.475
eve+0.472
emet+0.471
Neg logit contributions
hots-0.439
gang-0.371
onga-0.363
 Scor-0.360
hs-0.355
Token )
Token ID1267
Feature activation+1.17e+01

Pos logit contributions
arenthood+1.119
atism+0.988
udeb+0.970
eve+0.953
emet+0.948
Neg logit contributions
hots-2.043
gang-1.821
onga-1.802
 Scor-1.798
hs-1.740
Token {
Token ID1391
Feature activation+1.36e+00

Pos logit contributions
arenthood+4.242
eve+3.724
 ][+3.488
 Commit+3.426
}"+3.381
Neg logit contributions
hots-11.455
��-10.380
onga-10.240
 Scor-10.219
zb-10.207
Token //
Token ID3373
Feature activation-1.42e+00

Pos logit contributions
arenthood+1.058
atism+0.993
udeb+0.972
emet+0.964
eve+0.960
Neg logit contributions
hots-0.887
gang-0.757
 Scor-0.741
onga-0.741
hs-0.740
Token Time
Token ID3862
Feature activation+8.85e-01

Pos logit contributions
hots+1.049
gang+0.912
 Scor+0.908
onga+0.905
hs+0.898
Neg logit contributions
arenthood-0.983
atism-0.911
udeb-0.903
emet-0.887
eve-0.876
Token component
Token ID7515
Feature activation+4.41e+00

Pos logit contributions
arenthood+0.598
atism+0.556
udeb+0.543
emet+0.540
eve+0.535
Neg logit contributions
hots-0.676
gang-0.583
onga-0.576
 Scor-0.569
hs-0.568
Token const
Token ID1500
Feature activation-2.18e-01

Pos logit contributions
arenthood+2.171
atism+1.963
eve+1.907
 Nept+1.885
ativity+1.854
Neg logit contributions
hots-4.048
gang-3.624
onga-3.572
 Scor-3.504
zb-3.498
Token
Token ID198
Feature activation-2.46e+00

Pos logit contributions
hots+0.162
gang+0.140
 Scor+0.138
onga+0.138
hs+0.138
Neg logit contributions
arenthood-0.158
atism-0.147
udeb-0.144
emet-0.142
eve-0.142
Token
Token ID198
Feature activation+9.21e-01

Pos logit contributions
hots+1.689
gang+1.464
hs+1.442
 Scor+1.433
onga+1.422
Neg logit contributions
arenthood-1.822
atism-1.713
udeb-1.675
emet-1.658
ativity-1.633
Token1994
Token ID22666
Feature activation-4.29e+00

Pos logit contributions
arenthood+0.710
atism+0.655
udeb+0.651
eve+0.637
emet+0.636
Neg logit contributions
hots-0.611
hs-0.515
onga-0.514
gang-0.513
 Scor-0.511
Token John
Token ID1757
Feature activation-1.59e-01

Pos logit contributions
hots+3.390
 Scor+3.000
gang+2.999
hs+2.939
onga+2.908
Neg logit contributions
arenthood-2.715
atism-2.526
udeb-2.470
emet-2.423
eve-2.395
Token Lar
Token ID25577
Feature activation+2.62e+00

Pos logit contributions
hots+0.114
gang+0.099
 Scor+0.097
onga+0.097
hs+0.097
Neg logit contributions
arenthood-0.114
atism-0.106
udeb-0.104
emet-0.103
eve-0.102
Tokenro
Token ID305
Feature activation+1.16e+01

Pos logit contributions
arenthood+1.906
atism+1.769
udeb+1.762
eve+1.761
emet+1.725
Neg logit contributions
hots-1.830
 Scor-1.559
gang-1.545
onga-1.500
hs-1.496
Tokenqu
Token ID421
Feature activation+1.36e+00

Pos logit contributions
eve+6.938
arenthood+6.618
berto+6.411
utenberg+6.410
"},+6.274
Neg logit contributions
hots-8.150
 Prohibition-7.340
 Scor-7.328
 waitress-7.220
��-7.126
Tokenette
Token ID5857
Feature activation-1.71e+00

Pos logit contributions
arenthood+0.893
atism+0.819
emet+0.816
eve+0.806
udeb+0.788
Neg logit contributions
hots-1.056
gang-0.929
 Scor-0.928
hs-0.898
onga-0.898
Token
Token ID198
Feature activation-3.85e+00

Pos logit contributions
hots+1.191
gang+1.036
 Scor+1.023
onga+1.008
hs+1.008
Neg logit contributions
arenthood-1.245
atism-1.170
udeb-1.156
emet-1.143
eve-1.128
Token
Token ID198
Feature activation-1.71e-01

Pos logit contributions
hots+2.535
gang+2.196
hs+2.174
 Scor+2.139
la+2.113
Neg logit contributions
arenthood-2.948
atism-2.790
udeb-2.724
emet-2.698
ativity-2.666
Token1994
Token ID22666
Feature activation-3.23e+00

Pos logit contributions
hots+0.105
gang+0.089
 Scor+0.087
onga+0.087
hs+0.087
Neg logit contributions
arenthood-0.140
atism-0.132
udeb-0.129
emet-0.128
eve-0.128
Token:
Token ID25
Feature activation+6.26e+00

Pos logit contributions
arenthood+0.713
atism+0.653
udeb+0.627
ativity+0.623
eve+0.622
Neg logit contributions
hots-1.066
gang-0.949
onga-0.933
hs-0.930
 Scor-0.928
Token Forward
Token ID19530
Feature activation-1.79e+00

Pos logit contributions
arenthood+3.889
atism+3.674
 Commit+3.598
udeb+3.552
eve+3.528
Neg logit contributions
hots-4.712
gang-4.127
onga-4.093
hs-4.057
heid-3.931
Token
Token ID198
Feature activation+3.21e+00

Pos logit contributions
hots+1.281
gang+1.108
 Scor+1.093
onga+1.088
hs+1.086
Neg logit contributions
arenthood-1.281
atism-1.195
udeb-1.172
emet-1.160
eve-1.150
Token
Token ID198
Feature activation+6.65e+00

Pos logit contributions
arenthood+1.956
eve+1.775
atism+1.766
udeb+1.741
"},+1.706
Neg logit contributions
hots-2.588
onga-2.258
gang-2.249
 Scor-2.242
hs-2.164
TokenHeight
Token ID23106
Feature activation+6.89e+00

Pos logit contributions
arenthood+2.657
udeb+2.266
eve+2.222
atism+2.213
 Commit+2.153
Neg logit contributions
hots-6.599
 Scor-6.001
gang-5.940
hs-5.880
onga-5.874
Token:
Token ID25
Feature activation+1.15e+01

Pos logit contributions
arenthood+3.301
atism+2.920
"},+2.820
utenberg+2.769
emet+2.751
Neg logit contributions
hots-6.307
hs-5.647
 Scor-5.531
gang-5.522
onga-5.503
Token 6
Token ID718
Feature activation+9.37e+00

Pos logit contributions
arenthood+4.957
Position+4.400
atism+4.361
}"+4.312
"},+4.282
Neg logit contributions
hots-10.610
heid-9.287
hs-9.215
onga-9.159
gang-9.124
Token
Token ID447
Feature activation+1.33e+00

Pos logit contributions
arenthood+4.830
atism+4.408
emet+4.277
"},+4.271
eve+4.265
Neg logit contributions
hots-7.979
 Scor-6.897
gang-6.880
onga-6.870
hs-6.662
Token
Token ID247
Feature activation+1.01e+01

Pos logit contributions
arenthood+1.144
atism+1.084
eve+1.052
udeb+1.036
emet+1.033
Neg logit contributions
hots-0.762
gang-0.638
onga-0.628
 Scor-0.626
hs-0.606
Token3
Token ID18
Feature activation+1.43e+01

Pos logit contributions
arenthood+5.754
"},+5.397
}"+5.354
 Nept+5.336
atism+5.261
Neg logit contributions
hots-7.658
gang-6.709
 Scor-6.634
onga-6.501
hs-6.324
Token
Token ID447
Feature activation+9.00e-01

Pos logit contributions
arenthood+7.908
"},+7.035
}"+7.009
atism+6.982
ativity+6.856
Neg logit contributions
hots-10.925
gang-9.634
 Scor-9.543
hs-9.318
onga-9.297
Tokenulse
Token ID9615
Feature activation+1.77e+00

Pos logit contributions
hots+2.219
gang+1.844
onga+1.811
hs+1.793
 Scor+1.776
Neg logit contributions
arenthood-3.493
atism-3.311
udeb-3.270
emet-3.226
eve-3.205
Token period
Token ID2278
Feature activation+4.25e+00

Pos logit contributions
arenthood+1.209
atism+1.133
udeb+1.082
eve+1.078
emet+1.077
Neg logit contributions
hots-1.338
gang-1.168
 Scor-1.139
onga-1.123
hs-1.118
Token"
Token ID1
Feature activation+7.23e+00

Pos logit contributions
arenthood+2.464
atism+2.259
udeb+2.204
"},+2.182
eve+2.180
Neg logit contributions
hots-3.552
gang-3.141
onga-3.097
 Scor-3.064
hs-2.982
Token,
Token ID837
Feature activation+4.06e+00

Pos logit contributions
arenthood+2.780
atism+2.361
eve+2.353
udeb+2.315
 ][+2.249
Neg logit contributions
hots-7.327
onga-6.534
gang-6.501
 Scor-6.440
zb-6.282
Token Float
Token ID48436
Feature activation+2.95e+00

Pos logit contributions
arenthood+2.023
eve+1.910
atism+1.902
udeb+1.861
 Nept+1.835
Neg logit contributions
hots-3.652
gang-3.223
onga-3.118
hs-3.095
heid-3.076
Token )
Token ID1267
Feature activation+1.14e+01

Pos logit contributions
arenthood+1.513
udeb+1.343
atism+1.341
eve+1.314
emet+1.299
Neg logit contributions
hots-2.693
gang-2.381
onga-2.372
 Scor-2.359
hs-2.308
Token =
Token ID796
Feature activation+2.80e+00

Pos logit contributions
arenthood+3.995
}"+3.487
 ][+3.475
eve+3.375
 Commit+3.331
Neg logit contributions
hots-11.074
��-10.208
 looph-10.018
 comr-9.815
gang-9.794
Token 1
Token ID352
Feature activation+4.74e+00

Pos logit contributions
arenthood+1.826
atism+1.686
eve+1.662
udeb+1.644
 Nept+1.621
Neg logit contributions
hots-2.134
gang-1.865
 Scor-1.821
onga-1.810
hs-1.778
Token //
Token ID3373
Feature activation-3.49e+00

Pos logit contributions
arenthood+3.233
eve+2.932
atism+2.932
udeb+2.930
emet+2.896
Neg logit contributions
hots-3.458
onga-3.031
gang-2.966
 Scor-2.900
hs-2.832
Token seconds
Token ID4201
Feature activation+3.03e+00

Pos logit contributions
hots+2.099
gang+1.749
hs+1.733
 Scor+1.722
onga+1.711
Neg logit contributions
arenthood-2.902
atism-2.751
udeb-2.695
emet-2.664
eve-2.648
Token
Token ID198
Feature activation+1.44e+00

Pos logit contributions
arenthood+2.043
atism+1.903
eve+1.860
udeb+1.852
emet+1.843
Neg logit contributions
hots-2.237
gang-1.969
onga-1.912
 Scor-1.905
hs-1.899
Token their
Token ID511
Feature activation+3.02e+00

Pos logit contributions
arenthood+0.968
atism+0.900
udeb+0.875
emet+0.870
eve+0.869
Neg logit contributions
hots-1.012
gang-0.882
onga-0.865
hs-0.862
 Scor-0.862
Token children
Token ID1751
Feature activation+5.34e+00

Pos logit contributions
arenthood+2.053
atism+1.908
udeb+1.855
emet+1.836
eve+1.833
Neg logit contributions
hots-2.263
gang-1.953
onga-1.934
hs-1.916
 Scor-1.902
Token
Token ID447
Feature activation-4.40e-01

Pos logit contributions
arenthood+3.502
atism+3.166
eve+3.103
emet+3.090
udeb+3.084
Neg logit contributions
hots-4.034
gang-3.529
hs-3.417
onga-3.414
 Scor-3.379
Token
Token ID247
Feature activation+3.21e+00

Pos logit contributions
hots+0.250
gang+0.208
 Scor+0.205
onga+0.204
hs+0.200
Neg logit contributions
arenthood-0.382
atism-0.359
udeb-0.352
eve-0.350
emet-0.348
Tokens
Token ID82
Feature activation+1.50e-01

Pos logit contributions
arenthood+2.218
atism+2.034
eve+1.983
udeb+1.973
emet+1.965
Neg logit contributions
hots-2.347
gang-2.056
onga-2.025
 Scor-2.011
hs-1.998
Token birth
Token ID4082
Feature activation+1.14e+01

Pos logit contributions
arenthood+0.103
atism+0.095
udeb+0.093
emet+0.092
eve+0.092
Neg logit contributions
hots-0.112
gang-0.098
 Scor-0.096
onga-0.096
hs-0.096
Token,
Token ID11
Feature activation+7.20e-01

Pos logit contributions
arenthood+7.147
eve+6.489
emet+6.163
atism+6.093
ativity+5.968
Neg logit contributions
hots-8.328
 Scor-7.301
onga-7.244
gang-7.100
heid-6.944
Token and
Token ID290
Feature activation+3.24e+00

Pos logit contributions
arenthood+0.509
atism+0.470
udeb+0.460
emet+0.456
eve+0.455
Neg logit contributions
hots-0.524
gang-0.454
onga-0.446
 Scor-0.445
hs-0.445
Token a
Token ID257
Feature activation+7.15e-01

Pos logit contributions
arenthood+2.137
atism+1.956
eve+1.882
udeb+1.877
emet+1.876
Neg logit contributions
hots-2.496
gang-2.178
onga-2.161
hs-2.145
 Scor-2.123
Token hungry
Token ID14720
Feature activation-3.11e+00

Pos logit contributions
arenthood+0.473
atism+0.437
udeb+0.429
emet+0.424
eve+0.422
Neg logit contributions
hots-0.552
gang-0.480
onga-0.474
 Scor-0.470
hs-0.468
Token pel
Token ID16176
Feature activation-1.98e+00

Pos logit contributions
hots+2.342
gang+2.058
 Scor+2.039
hs+2.019
onga+2.019
Neg logit contributions
arenthood-2.085
atism-1.941
udeb-1.902
emet-1.874
eve-1.861
Token Barack
Token ID8732
Feature activation-1.76e+00

Pos logit contributions
hots+1.187
gang+1.029
 Scor+1.014
hs+1.009
onga+1.008
Neg logit contributions
arenthood-1.139
atism-1.062
udeb-1.044
emet-1.030
eve-1.025
Token Hussein
Token ID22983
Feature activation-2.92e+00

Pos logit contributions
hots+0.708
gang+0.537
 Scor+0.520
onga+0.518
hs+0.516
Neg logit contributions
arenthood-1.805
atism-1.719
udeb-1.696
emet-1.687
eve-1.677
Token Obama
Token ID2486
Feature activation+2.68e-01

Pos logit contributions
hots+2.007
gang+1.739
 Scor+1.714
hs+1.699
onga+1.698
Neg logit contributions
arenthood-2.159
atism-2.023
udeb-1.989
eve-1.959
emet-1.959
TokenWith
Token ID3152
Feature activation+3.44e+00

Pos logit contributions
arenthood+0.170
atism+0.156
emet+0.153
udeb+0.152
eve+0.150
Neg logit contributions
hots-0.215
gang-0.188
onga-0.186
hs-0.186
 Scor-0.186
Token low
Token ID1877
Feature activation+2.23e+00

Pos logit contributions
arenthood+2.484
emet+2.229
atism+2.198
eve+2.195
udeb+2.180
Neg logit contributions
hots-2.438
gang-2.157
hs-2.103
onga-2.075
la-2.041
Token birth
Token ID4082
Feature activation+1.12e+01

Pos logit contributions
arenthood+1.562
atism+1.448
udeb+1.415
emet+1.407
eve+1.396
Neg logit contributions
hots-1.625
gang-1.411
onga-1.387
hs-1.386
 Scor-1.385
Token rate
Token ID2494
Feature activation+1.25e+00

Pos logit contributions
arenthood+6.440
ception+6.363
 mars+6.082
eve+5.995
emet+5.952
Neg logit contributions
hots-7.837
SPONSORED-7.414
 Scor-7.306
onga-7.202
oused-7.145
Token,
Token ID11
Feature activation+5.43e+00

Pos logit contributions
arenthood+0.727
atism+0.662
emet+0.657
 Nept+0.635
ativity+0.629
Neg logit contributions
hots-1.040
gang-0.932
onga-0.918
SPONSORED-0.905
hs-0.901
Token America
Token ID2253
Feature activation+3.57e+00

Pos logit contributions
arenthood+3.444
atism+3.140
ativity+3.127
udeb+3.072
emet+3.042
Neg logit contributions
hots-4.217
gang-3.807
heid-3.622
 Scor-3.552
onga-3.551
Token needs
Token ID2476
Feature activation+1.99e+00

Pos logit contributions
arenthood+1.927
ativity+1.775
eve+1.774
emet+1.757
udeb+1.755
Neg logit contributions
hots-3.038
heid-2.617
 Scor-2.615
hs-2.609
��-2.600
Token future
Token ID2003
Feature activation-1.58e+00

Pos logit contributions
arenthood+1.430
atism+1.331
udeb+1.311
emet+1.292
eve+1.283
Neg logit contributions
hots-1.415
gang-1.226
 Scor-1.207
onga-1.205
hs-1.200
Token
Token ID198
Feature activation+3.25e+00

Pos logit contributions
arenthood+0.692
atism+0.635
eve+0.625
udeb+0.625
emet+0.617
Neg logit contributions
hots-0.799
gang-0.694
onga-0.690
 Scor-0.689
hs-0.674
TokenWhy
Token ID5195
Feature activation+9.01e-01

Pos logit contributions
arenthood+2.184
atism+2.018
udeb+1.985
eve+1.978
emet+1.955
Neg logit contributions
hots-2.420
gang-2.092
 Scor-2.083
onga-2.053
hs-2.049
Token 1910
Token ID31953
Feature activation+3.27e+00

Pos logit contributions
arenthood+0.618
atism+0.577
udeb+0.559
eve+0.555
emet+0.554
Neg logit contributions
hots-0.668
gang-0.578
hs-0.571
 Scor-0.570
onga-0.566
Token?
Token ID30
Feature activation+7.12e-01

Pos logit contributions
arenthood+2.175
atism+2.023
eve+1.946
udeb+1.945
emet+1.944
Neg logit contributions
hots-2.472
gang-2.145
 Scor-2.109
onga-2.107
hs-2.086
Token The
Token ID383
Feature activation+2.50e-01

Pos logit contributions
arenthood+0.484
atism+0.450
udeb+0.435
emet+0.433
eve+0.432
Neg logit contributions
hots-0.537
gang-0.465
onga-0.456
hs-0.456
 Scor-0.451
Token birth
Token ID4082
Feature activation+1.12e+01

Pos logit contributions
arenthood+0.155
atism+0.143
emet+0.138
udeb+0.138
eve+0.137
Neg logit contributions
hots-0.203
gang-0.178
onga-0.175
hs-0.175
 Scor-0.174
Token year
Token ID614
Feature activation+4.79e+00

Pos logit contributions
arenthood+6.565
eve+5.894
atism+5.887
utenberg+5.691
ativity+5.676
Neg logit contributions
hots-8.877
onga-7.683
 Scor-7.605
gang-7.534
hs-7.419
Token of
Token ID286
Feature activation+6.18e-01

Pos logit contributions
arenthood+3.035
atism+2.864
eve+2.754
ativity+2.721
emet+2.704
Neg logit contributions
hots-3.732
gang-3.270
onga-3.213
 Scor-3.185
hs-3.180
Token Akira
Token ID46910
Feature activation-3.49e+00

Pos logit contributions
arenthood+0.423
atism+0.396
emet+0.384
udeb+0.382
eve+0.381
Neg logit contributions
hots-0.460
gang-0.398
hs-0.391
onga-0.391
 Scor-0.388
Token Kuro
Token ID25796
Feature activation-1.44e+00

Pos logit contributions
hots+2.060
gang+1.724
 Scor+1.693
onga+1.684
hs+1.682
Neg logit contributions
arenthood-2.938
atism-2.769
udeb-2.723
emet-2.699
eve-2.686
Tokens
Token ID82
Feature activation-4.99e+00

Pos logit contributions
hots+1.082
gang+0.942
 Scor+0.934
onga+0.933
hs+0.922
Neg logit contributions
arenthood-0.962
atism-0.900
udeb-0.873
eve-0.871
emet-0.868
Token ago
Token ID2084
Feature activation-1.95e+00

Pos logit contributions
hots+2.631
gang+2.136
 Scor+2.084
onga+2.080
hs+2.075
Neg logit contributions
arenthood-4.675
atism-4.418
udeb-4.361
emet-4.324
eve-4.269
Token when
Token ID618
Feature activation-3.41e-01

Pos logit contributions
hots+1.464
gang+1.275
 Scor+1.256
onga+1.253
hs+1.251
Neg logit contributions
arenthood-1.326
atism-1.229
udeb-1.203
emet-1.193
eve-1.185
Token se
Token ID384
Feature activation+4.23e-01

Pos logit contributions
hots+0.248
gang+0.212
onga+0.211
hs+0.210
 Scor+0.210
Neg logit contributions
arenthood-0.241
atism-0.222
udeb-0.218
emet-0.217
eve-0.217
Tokenared
Token ID1144
Feature activation-1.42e+00

Pos logit contributions
arenthood+0.283
atism+0.265
udeb+0.257
emet+0.256
eve+0.254
Neg logit contributions
hots-0.322
 Scor-0.279
gang-0.276
onga-0.275
hs-0.274
Token a
Token ID257
Feature activation-2.25e+00

Pos logit contributions
hots+1.079
gang+0.940
onga+0.927
 Scor+0.925
hs+0.923
Neg logit contributions
arenthood-0.953
atism-0.891
udeb-0.863
emet-0.860
eve-0.856
Tokenhi
Token ID5303
Feature activation-1.49e+01

Pos logit contributions
hots+1.644
gang+1.428
 Scor+1.406
onga+1.402
hs+1.400
Neg logit contributions
arenthood-1.570
atism-1.461
udeb-1.431
emet-1.417
eve-1.408
Token was
Token ID373
Feature activation-3.79e+00

Pos logit contributions
hots+10.006
gang+8.862
hs+8.811
onga+8.670
la+8.599
Neg logit contributions
arenthood-9.962
atism-8.973
udeb-8.933
ativity-8.847
eve-8.816
Token a
Token ID257
Feature activation-4.98e+00

Pos logit contributions
hots+2.777
gang+2.411
 Scor+2.377
hs+2.366
onga+2.363
Neg logit contributions
arenthood-2.652
atism-2.469
udeb-2.420
emet-2.391
eve-2.379
Token trend
Token ID5182
Feature activation-2.74e-01

Pos logit contributions
hots+3.821
gang+3.349
 Scor+3.306
hs+3.299
onga+3.282
Neg logit contributions
arenthood-3.283
atism-3.043
udeb-2.977
emet-2.935
eve-2.919
Token,
Token ID11
Feature activation-1.98e-01

Pos logit contributions
hots+0.206
onga+0.181
gang+0.180
hs+0.177
 Scor+0.176
Neg logit contributions
arenthood-0.183
atism-0.169
emet-0.167
udeb-0.167
eve-0.165
Token they
Token ID484
Feature activation+1.07e+00

Pos logit contributions
hots+0.153
gang+0.132
onga+0.131
hs+0.130
 Scor+0.130
Neg logit contributions
arenthood-0.130
atism-0.120
udeb-0.118
emet-0.118
eve-0.117
Token there
Token ID612
Feature activation-1.52e+00

Pos logit contributions
arenthood+0.777
atism+0.719
eve+0.698
udeb+0.693
emet+0.689
Neg logit contributions
hots-0.977
onga-0.852
gang-0.851
 Scor-0.835
hs-0.831
Token,
Token ID11
Feature activation-3.79e-01

Pos logit contributions
hots+1.132
gang+0.985
 Scor+0.971
onga+0.968
hs+0.967
Neg logit contributions
arenthood-1.043
atism-0.970
udeb-0.949
emet-0.940
eve-0.934
Token waiting
Token ID4953
Feature activation-2.14e+00

Pos logit contributions
hots+0.292
gang+0.256
onga+0.252
 Scor+0.250
hs+0.250
Neg logit contributions
arenthood-0.250
atism-0.232
udeb-0.227
emet-0.225
eve-0.223
Token in
Token ID287
Feature activation-7.82e-01

Pos logit contributions
hots+1.602
gang+1.397
 Scor+1.379
hs+1.371
onga+1.371
Neg logit contributions
arenthood-1.452
atism-1.351
udeb-1.324
emet-1.308
eve-1.298
Token the
Token ID262
Feature activation-2.74e+00

Pos logit contributions
hots+0.695
gang+0.619
 Scor+0.611
onga+0.610
hs+0.609
Neg logit contributions
arenthood-0.425
atism-0.388
udeb-0.377
emet-0.372
eve-0.369
Token back
Token ID736
Feature activation-1.27e+01

Pos logit contributions
hots+2.085
gang+1.828
 Scor+1.803
hs+1.789
onga+1.789
Neg logit contributions
arenthood-1.836
atism-1.702
udeb-1.663
emet-1.645
eve-1.631
Token of
Token ID286
Feature activation-3.90e+00

Pos logit contributions
hots+8.136
gang+7.439
seat+7.342
hs+7.059
 Scor+6.946
Neg logit contributions
arenthood-8.911
atism-8.478
agall-8.217
udeb-8.121
emet-7.956
Token an
Token ID281
Feature activation-2.31e+00

Pos logit contributions
hots+2.703
gang+2.356
 Scor+2.328
onga+2.281
hs+2.274
Neg logit contributions
arenthood-2.851
atism-2.663
udeb-2.616
emet-2.572
eve-2.555
Token SUV
Token ID26763
Feature activation-3.09e+00

Pos logit contributions
hots+1.836
gang+1.616
 Scor+1.593
onga+1.587
hs+1.586
Neg logit contributions
arenthood-1.464
atism-1.351
udeb-1.321
emet-1.306
eve-1.295
Token,
Token ID11
Feature activation-1.54e+00

Pos logit contributions
hots+2.247
gang+1.955
 Scor+1.936
onga+1.917
hs+1.917
Neg logit contributions
arenthood-2.159
atism-2.015
udeb-1.975
emet-1.945
eve-1.933
Token wearing
Token ID5762
Feature activation-1.00e+00

Pos logit contributions
hots+1.168
gang+1.020
 Scor+1.003
onga+1.002
hs+1.000
Neg logit contributions
arenthood-1.037
atism-0.962
udeb-0.941
emet-0.932
eve-0.926
Token Hundreds
Token ID32636
Feature activation-1.87e-01

Pos logit contributions
arenthood+0.470
atism+0.432
udeb+0.422
emet+0.420
eve+0.419
Neg logit contributions
hots-0.520
gang-0.451
onga-0.445
hs-0.441
 Scor-0.438
Token streamed
Token ID35377
Feature activation+3.86e+00

Pos logit contributions
hots+0.143
gang+0.126
 Scor+0.124
onga+0.124
hs+0.123
Neg logit contributions
arenthood-0.124
atism-0.115
udeb-0.113
emet-0.112
eve-0.111
Token down
Token ID866
Feature activation-7.91e-01

Pos logit contributions
arenthood+2.304
atism+2.156
eve+2.086
emet+2.075
 Nept+2.036
Neg logit contributions
hots-3.063
onga-2.730
gang-2.719
hs-2.643
 Scor-2.638
Token the
Token ID262
Feature activation-2.84e-01

Pos logit contributions
hots+0.576
gang+0.499
onga+0.493
 Scor+0.492
hs+0.490
Neg logit contributions
arenthood-0.556
atism-0.517
udeb-0.504
emet-0.502
eve-0.499
Token a
Token ID257
Feature activation-7.27e-01

Pos logit contributions
hots+0.212
gang+0.185
onga+0.182
hs+0.182
 Scor+0.181
Neg logit contributions
arenthood-0.194
atism-0.181
emet-0.176
udeb-0.176
eve-0.175
Tokenis
Token ID271
Feature activation-1.26e+01

Pos logit contributions
hots+0.553
gang+0.482
 Scor+0.475
onga+0.471
hs+0.469
Neg logit contributions
arenthood-0.486
atism-0.451
emet-0.442
udeb-0.442
eve-0.439
Tokenles
Token ID829
Feature activation-1.76e+00

Pos logit contributions
hots+6.301
hs+5.700
la+5.700
onga+5.408
gang+5.279
Neg logit contributions
arenthood-10.659
atism-10.279
eve-9.945
udeb-9.933
utenberg-9.810
Token for
Token ID329
Feature activation+8.15e-01

Pos logit contributions
hots+1.290
gang+1.117
 Scor+1.101
hs+1.097
onga+1.094
Neg logit contributions
arenthood-1.235
atism-1.151
udeb-1.129
emet-1.114
eve-1.106
Token the
Token ID262
Feature activation+1.22e+00

Pos logit contributions
arenthood+0.524
atism+0.484
udeb+0.471
emet+0.471
eve+0.468
Neg logit contributions
hots-0.637
gang-0.561
hs-0.552
onga-0.552
 Scor-0.548
Token altar
Token ID18890
Feature activation+5.67e+00

Pos logit contributions
arenthood+0.857
atism+0.802
eve+0.779
udeb+0.777
emet+0.776
Neg logit contributions
hots-0.883
gang-0.766
onga-0.754
hs-0.753
 Scor-0.739
Token call
Token ID869
Feature activation+1.52e+00

Pos logit contributions
arenthood+3.709
atism+3.383
eve+3.338
emet+3.313
udeb+3.307
Neg logit contributions
hots-4.249
gang-3.703
onga-3.658
 Scor-3.628
hs-3.593
Token salt
Token ID8268
Feature activation+1.23e+00

Pos logit contributions
hots+1.117
gang+0.960
onga+0.939
hs+0.937
 Scor+0.931
Neg logit contributions
arenthood-1.196
atism-1.127
udeb-1.097
emet-1.091
eve-1.088
Token,
Token ID11
Feature activation-6.02e-01

Pos logit contributions
arenthood+0.841
atism+0.786
udeb+0.761
emet+0.758
eve+0.754
Neg logit contributions
hots-0.903
gang-0.790
onga-0.776
 Scor-0.772
hs-0.769
Token pepper
Token ID13385
Feature activation-2.44e+00

Pos logit contributions
hots+0.445
gang+0.384
onga+0.378
hs+0.377
 Scor+0.376
Neg logit contributions
arenthood-0.416
atism-0.390
udeb-0.380
eve-0.379
emet-0.377
Token and
Token ID290
Feature activation-2.01e+00

Pos logit contributions
hots+1.712
gang+1.476
 Scor+1.454
hs+1.447
onga+1.446
Neg logit contributions
arenthood-1.775
atism-1.653
udeb-1.625
emet-1.609
eve-1.598
Token chill
Token ID20493
Feature activation-1.36e+00

Pos logit contributions
hots+1.391
gang+1.194
onga+1.175
 Scor+1.171
hs+1.170
Neg logit contributions
arenthood-1.479
atism-1.385
udeb-1.355
emet-1.345
eve-1.345
Tokeni
Token ID72
Feature activation-1.23e+01

Pos logit contributions
hots+0.780
gang+0.647
onga+0.634
hs+0.627
 Scor+0.623
Neg logit contributions
arenthood-1.174
atism-1.113
udeb-1.091
emet-1.085
eve-1.078
Token by
Token ID416
Feature activation-1.87e+00

Pos logit contributions
hots+7.142
 Scor+6.118
gang+5.962
hs+5.955
onga+5.719
Neg logit contributions
arenthood-9.651
udeb-8.927
atism-8.788
emet-8.768
eve-8.588
Token tasting
Token ID26973
Feature activation+1.98e+00

Pos logit contributions
hots+1.350
gang+1.171
 Scor+1.152
onga+1.151
hs+1.147
Neg logit contributions
arenthood-1.319
atism-1.228
udeb-1.204
emet-1.193
eve-1.185
Token.
Token ID13
Feature activation+1.07e-02

Pos logit contributions
arenthood+1.256
atism+1.164
emet+1.142
eve+1.140
udeb+1.134
Neg logit contributions
hots-1.518
gang-1.340
onga-1.322
 Scor-1.300
hs-1.293
Token
Token ID198
Feature activation-9.36e-01

Pos logit contributions
arenthood+0.007
atism+0.007
udeb+0.007
eve+0.007
emet+0.007
Neg logit contributions
hots-0.008
gang-0.007
onga-0.007
hs-0.007
 Scor-0.007
Token
Token ID198
Feature activation-4.64e+00

Pos logit contributions
hots+0.679
gang+0.588
 Scor+0.580
onga+0.579
hs+0.576
Neg logit contributions
arenthood-0.660
atism-0.614
udeb-0.602
emet-0.596
eve-0.594
Token1
Token ID16
Feature activation-4.76e+00

Pos logit contributions
hots+1.780
gang+1.542
 Scor+1.522
onga+1.516
hs+1.508
Neg logit contributions
arenthood-1.780
atism-1.658
udeb-1.626
emet-1.611
eve-1.603
Token 2
Token ID362
Feature activation-9.53e+00

Pos logit contributions
hots+3.451
gang+2.966
hs+2.959
 Scor+2.929
onga+2.879
Neg logit contributions
arenthood-3.309
atism-3.136
udeb-3.058
emet-3.009
eve-2.954
Token 3
Token ID513
Feature activation-4.38e+00

Pos logit contributions
hots+6.783
hs+5.814
gang+5.803
onga+5.711
 Scor+5.660
Neg logit contributions
arenthood-6.491
udeb-6.143
atism-6.130
emet-5.857
ativity-5.780
Token 4
Token ID604
Feature activation-7.77e+00

Pos logit contributions
hots+3.377
gang+2.926
hs+2.904
 Scor+2.884
onga+2.858
Neg logit contributions
arenthood-2.879
atism-2.691
udeb-2.652
emet-2.596
eve-2.565
Token 5
Token ID642
Feature activation-8.30e+00

Pos logit contributions
hots+5.128
hs+4.238
gang+4.214
 Scor+4.186
la+4.134
Neg logit contributions
arenthood-5.812
atism-5.552
udeb-5.549
emet-5.370
ativity-5.327
Token 6
Token ID718
Feature activation-1.22e+01

Pos logit contributions
hots+5.541
hs+4.721
gang+4.660
 Scor+4.603
la+4.533
Neg logit contributions
arenthood-5.992
atism-5.801
udeb-5.783
emet-5.624
eve-5.469
Token 7
Token ID767
Feature activation-4.59e+00

Pos logit contributions
hots+8.208
hs+7.126
 Scor+6.830
onga+6.796
gang+6.731
Neg logit contributions
arenthood-8.292
atism-7.982
udeb-7.793
ativity-7.669
emet-7.589
Token 8
Token ID807
Feature activation-5.53e+00

Pos logit contributions
hots+3.650
hs+3.175
gang+3.161
 Scor+3.133
onga+3.114
Neg logit contributions
arenthood-2.889
atism-2.698
udeb-2.593
emet-2.577
ativity-2.542
Token 9
Token ID860
Feature activation-3.14e+00

Pos logit contributions
hots+4.343
hs+3.790
gang+3.751
onga+3.700
 Scor+3.673
Neg logit contributions
arenthood-3.533
atism-3.271
udeb-3.230
emet-3.156
ativity-3.083
Token 10
Token ID838
Feature activation-6.36e+00

Pos logit contributions
hots+2.061
gang+1.756
hs+1.734
 Scor+1.718
onga+1.710
Neg logit contributions
arenthood-2.425
atism-2.279
udeb-2.237
emet-2.224
eve-2.192
Token 11
Token ID1367
Feature activation-3.96e+00

Pos logit contributions
hots+4.216
hs+3.629
gang+3.618
onga+3.503
 Scor+3.481
Neg logit contributions
arenthood-4.732
atism-4.497
udeb-4.437
emet-4.396
eve-4.313
Token awesome
Token ID7427
Feature activation-1.11e+00

Pos logit contributions
arenthood+0.350
atism+0.324
udeb+0.317
emet+0.315
eve+0.314
Neg logit contributions
hots-0.384
gang-0.336
onga-0.331
 Scor-0.330
hs-0.329
Token grappling
Token ID36762
Feature activation-2.80e+00

Pos logit contributions
hots+0.816
gang+0.710
 Scor+0.699
onga+0.697
hs+0.696
Neg logit contributions
arenthood-0.774
atism-0.720
udeb-0.706
emet-0.698
eve-0.694
Token hook
Token ID8011
Feature activation-1.55e+00

Pos logit contributions
hots+2.031
gang+1.754
 Scor+1.729
onga+1.723
hs+1.722
Neg logit contributions
arenthood-1.981
atism-1.844
udeb-1.808
emet-1.789
eve-1.772
Token aw
Token ID3253
Feature activation+5.64e-01

Pos logit contributions
hots+1.132
gang+0.985
 Scor+0.970
onga+0.966
hs+0.965
Neg logit contributions
arenthood-1.080
atism-1.005
udeb-0.985
emet-0.975
eve-0.969
Tokenes
Token ID274
Feature activation-1.16e+01

Pos logit contributions
arenthood+0.351
atism+0.323
udeb+0.318
emet+0.314
eve+0.313
Neg logit contributions
hots-0.454
gang-0.401
 Scor-0.395
onga-0.392
hs-0.390
Tokenomen
Token ID3674
Feature activation-1.17e+01

Pos logit contributions
hots+5.989
la+4.699
onga+4.691
hs+4.669
gang+4.631
Neg logit contributions
arenthood-9.820
atism-9.219
udeb-9.186
eve-9.180
 Nept-9.085
Tokeness
Token ID408
Feature activation-2.00e+00

Pos logit contributions
hots+8.402
onga+7.278
gang+7.245
hs+7.107
la+7.101
Neg logit contributions
arenthood-7.742
atism-7.239
 Nept-7.027
ativity-6.915
utenberg-6.871
Token!
Token ID0
Feature activation-3.13e+00

Pos logit contributions
hots+1.457
gang+1.260
 Scor+1.243
onga+1.237
hs+1.237
Neg logit contributions
arenthood-1.408
atism-1.311
udeb-1.282
emet-1.271
eve-1.260
Token Having
Token ID11136
Feature activation+1.49e+00

Pos logit contributions
hots+2.306
gang+2.008
 Scor+1.985
hs+1.970
onga+1.964
Neg logit contributions
arenthood-2.172
atism-2.024
udeb-1.964
emet-1.955
eve-1.931
Token done
Token ID1760
Feature activation-3.74e-01

Pos logit contributions
arenthood+0.963
atism+0.891
udeb+0.876
eve+0.874
emet+0.868
Neg logit contributions
hots-1.149
gang-1.009
onga-0.997
hs-0.987
 Scor-0.983
Token any
Token ID597
Feature activation-1.02e+00

Pos logit contributions
hots+0.283
gang+0.247
onga+0.243
 Scor+0.243
hs+0.243
Neg logit contributions
arenthood-0.252
atism-0.234
udeb-0.229
emet-0.227
eve-0.226
Tokenstop
Token ID11338
Feature activation+5.15e-01

Pos logit contributions
hots+1.544
gang+1.332
 Scor+1.326
onga+1.306
hs+1.305
Neg logit contributions
arenthood-1.690
atism-1.595
udeb-1.557
emet-1.531
eve-1.521
Token awesome
Token ID7427
Feature activation-1.11e+00

Pos logit contributions
arenthood+0.350
atism+0.324
udeb+0.317
emet+0.315
eve+0.314
Neg logit contributions
hots-0.384
gang-0.336
onga-0.331
 Scor-0.330
hs-0.329
Token grappling
Token ID36762
Feature activation-2.80e+00

Pos logit contributions
hots+0.816
gang+0.710
 Scor+0.699
onga+0.697
hs+0.696
Neg logit contributions
arenthood-0.774
atism-0.720
udeb-0.706
emet-0.698
eve-0.694
Token hook
Token ID8011
Feature activation-1.55e+00

Pos logit contributions
hots+2.031
gang+1.754
 Scor+1.729
onga+1.723
hs+1.722
Neg logit contributions
arenthood-1.981
atism-1.844
udeb-1.808
emet-1.789
eve-1.772
Token aw
Token ID3253
Feature activation+5.64e-01

Pos logit contributions
hots+1.132
gang+0.985
 Scor+0.970
onga+0.966
hs+0.965
Neg logit contributions
arenthood-1.080
atism-1.005
udeb-0.985
emet-0.975
eve-0.969
Tokenes
Token ID274
Feature activation-1.16e+01

Pos logit contributions
arenthood+0.351
atism+0.323
udeb+0.318
emet+0.314
eve+0.313
Neg logit contributions
hots-0.454
gang-0.401
 Scor-0.395
onga-0.392
hs-0.390
Tokenomen
Token ID3674
Feature activation-1.17e+01

Pos logit contributions
hots+5.989
la+4.699
onga+4.691
hs+4.669
gang+4.631
Neg logit contributions
arenthood-9.820
atism-9.219
udeb-9.186
eve-9.180
 Nept-9.085
Tokeness
Token ID408
Feature activation-2.00e+00

Pos logit contributions
hots+8.402
onga+7.278
gang+7.245
hs+7.107
la+7.101
Neg logit contributions
arenthood-7.742
atism-7.239
 Nept-7.027
ativity-6.915
utenberg-6.871
Token!
Token ID0
Feature activation-3.13e+00

Pos logit contributions
hots+1.457
gang+1.260
 Scor+1.243
onga+1.237
hs+1.237
Neg logit contributions
arenthood-1.408
atism-1.311
udeb-1.282
emet-1.271
eve-1.260
Token Having
Token ID11136
Feature activation+1.49e+00

Pos logit contributions
hots+2.306
gang+2.008
 Scor+1.985
hs+1.970
onga+1.964
Neg logit contributions
arenthood-2.172
atism-2.024
udeb-1.964
emet-1.955
eve-1.931
Token done
Token ID1760
Feature activation-3.74e-01

Pos logit contributions
arenthood+0.963
atism+0.891
udeb+0.876
eve+0.874
emet+0.868
Neg logit contributions
hots-1.149
gang-1.009
onga-0.997
hs-0.987
 Scor-0.983
Token_
Token ID62
Feature activation-4.17e+00

Pos logit contributions
arenthood+1.374
atism+1.282
udeb+1.266
emet+1.253
eve+1.249
Neg logit contributions
hots-1.299
 Scor-1.120
gang-1.118
onga-1.102
hs-1.077
Tokenev
Token ID1990
Feature activation-1.09e+00

Pos logit contributions
hots+3.014
gang+2.627
hs+2.578
onga+2.551
 Scor+2.536
Neg logit contributions
arenthood-2.947
atism-2.742
udeb-2.680
emet-2.653
ativity-2.619
Tokenans
Token ID504
Feature activation-2.29e+00

Pos logit contributions
hots+0.755
gang+0.647
 Scor+0.643
onga+0.637
hs+0.634
Neg logit contributions
arenthood-0.808
atism-0.756
udeb-0.742
emet-0.734
eve-0.732
Token12
Token ID1065
Feature activation-2.70e+00

Pos logit contributions
hots+1.705
gang+1.485
 Scor+1.462
onga+1.458
hs+1.456
Neg logit contributions
arenthood-1.579
atism-1.468
udeb-1.437
emet-1.422
eve-1.412
Token19
Token ID1129
Feature activation-1.53e+00

Pos logit contributions
hots+2.008
gang+1.749
 Scor+1.723
hs+1.717
onga+1.715
Neg logit contributions
arenthood-1.859
atism-1.728
udeb-1.691
emet-1.674
eve-1.658
Token/
Token ID14
Feature activation-1.16e+01

Pos logit contributions
hots+1.131
gang+0.983
 Scor+0.968
onga+0.967
hs+0.964
Neg logit contributions
arenthood-1.057
atism-0.983
udeb-0.963
emet-0.953
eve-0.949
TokenInst
Token ID6310
Feature activation+6.79e-01

Pos logit contributions
hots+8.536
hs+7.502
gang+7.471
la+7.312
 Scor+7.127
Neg logit contributions
arenthood-7.440
atism-6.823
udeb-6.663
ativity-6.635
emet-6.578
Tokenagram
Token ID6713
Feature activation+1.92e+00

Pos logit contributions
arenthood+0.411
atism+0.381
udeb+0.369
emet+0.366
eve+0.364
Neg logit contributions
hots-0.559
gang-0.491
 Scor-0.491
onga-0.487
hs-0.485
Token
Token ID198
Feature activation-2.10e+00

Pos logit contributions
arenthood+1.318
atism+1.232
eve+1.196
udeb+1.193
emet+1.183
Neg logit contributions
hots-1.409
gang-1.218
onga-1.212
hs-1.201
 Scor-1.199
Token
Token ID198
Feature activation-7.65e-01

Pos logit contributions
hots+1.499
gang+1.298
 Scor+1.277
hs+1.274
onga+1.272
Neg logit contributions
arenthood-1.508
atism-1.408
udeb-1.379
emet-1.366
eve-1.354
TokenNow
Token ID3844
Feature activation+2.10e+00

Pos logit contributions
hots+0.574
gang+0.498
 Scor+0.496
onga+0.492
hs+0.488
Neg logit contributions
arenthood-0.521
atism-0.484
udeb-0.475
eve-0.470
emet-0.468
Token="
Token ID2625
Feature activation-2.93e+00

Pos logit contributions
arenthood+0.875
atism+0.806
udeb+0.785
emet+0.778
eve+0.771
Neg logit contributions
hots-1.205
gang-1.066
 Scor-1.054
onga-1.045
hs-1.042
TokenPhone
Token ID6132
Feature activation+7.02e-01

Pos logit contributions
hots+2.687
gang+2.401
hs+2.376
onga+2.359
 Scor+2.353
Neg logit contributions
arenthood-1.507
atism-1.370
udeb-1.321
emet-1.306
eve-1.286
TokenList
Token ID8053
Feature activation-1.81e+00

Pos logit contributions
arenthood+0.511
atism+0.477
udeb+0.470
emet+0.465
eve+0.462
Neg logit contributions
hots-0.490
gang-0.422
 Scor-0.417
onga-0.414
hs-0.411
TokenCtrl
Token ID40069
Feature activation-1.68e+00

Pos logit contributions
hots+1.581
gang+1.410
hs+1.395
onga+1.389
 Scor+1.387
Neg logit contributions
arenthood-1.015
atism-0.926
udeb-0.901
emet-0.891
eve-0.880
Token">
Token ID5320
Feature activation-6.57e+00

Pos logit contributions
hots+1.283
gang+1.121
hs+1.107
onga+1.106
 Scor+1.105
Neg logit contributions
arenthood-1.125
atism-1.043
udeb-1.019
emet-1.011
eve-1.003
Token <
Token ID1279
Feature activation-1.13e+01

Pos logit contributions
hots+3.867
gang+3.284
onga+3.247
hs+3.241
la+3.224
Neg logit contributions
arenthood-5.339
atism-5.119
udeb-5.080
emet-4.971
ativity-4.868
Tokenul
Token ID377
Feature activation-2.62e+00

Pos logit contributions
hots+5.558
hs+4.849
gang+4.700
la+4.660
onga+4.457
Neg logit contributions
arenthood-9.871
atism-9.174
 Nept-9.135
udeb-9.123
emet-8.980
Token>
Token ID29
Feature activation-6.07e+00

Pos logit contributions
hots+1.100
gang+0.845
hs+0.834
onga+0.826
 Scor+0.821
Neg logit contributions
arenthood-2.638
atism-2.508
udeb-2.484
emet-2.462
eve-2.446
Token <
Token ID1279
Feature activation-8.15e+00

Pos logit contributions
hots+3.601
onga+3.028
gang+3.028
hs+3.000
la+2.977
Neg logit contributions
arenthood-4.909
atism-4.694
udeb-4.642
emet-4.526
eve-4.472
Tokenli
Token ID4528
Feature activation-6.43e+00

Pos logit contributions
hots+3.641
hs+3.046
gang+2.991
la+2.920
onga+2.877
Neg logit contributions
arenthood-7.809
atism-7.327
udeb-7.313
emet-7.185
 Nept-7.114
Token ng
Token ID23370
Feature activation-2.63e-01

Pos logit contributions
hots+3.657
hs+3.226
onga+3.177
gang+3.108
la+3.084
Neg logit contributions
arenthood-5.303
udeb-4.981
atism-4.954
emet-4.896
eve-4.826
Token they
Token ID484
Feature activation+3.49e+00

Pos logit contributions
arenthood+0.735
atism+0.679
udeb+0.663
emet+0.659
eve+0.656
Neg logit contributions
hots-0.795
gang-0.694
onga-0.684
 Scor-0.681
hs-0.680
Token streamed
Token ID35377
Feature activation+5.29e+00

Pos logit contributions
arenthood+2.176
atism+2.057
emet+1.969
udeb+1.960
eve+1.944
Neg logit contributions
hots-2.732
gang-2.434
 Scor-2.396
onga-2.379
hs-2.333
Token down
Token ID866
Feature activation+8.48e-01

Pos logit contributions
arenthood+3.486
atism+3.208
 Nept+3.100
eve+3.100
emet+3.088
Neg logit contributions
hots-3.902
gang-3.441
onga-3.406
hs-3.306
 Scor-3.288
Token the
Token ID262
Feature activation+3.42e+00

Pos logit contributions
arenthood+0.588
atism+0.543
udeb+0.531
emet+0.530
eve+0.525
Neg logit contributions
hots-0.625
gang-0.544
onga-0.538
 Scor-0.535
hs-0.533
Token a
Token ID257
Feature activation-6.43e-01

Pos logit contributions
arenthood+2.325
atism+2.169
emet+2.131
eve+2.121
ativity+2.100
Neg logit contributions
hots-2.521
gang-2.185
onga-2.170
hs-2.156
 Scor-2.124
Tokenis
Token ID271
Feature activation-1.12e+01

Pos logit contributions
hots+0.489
gang+0.426
 Scor+0.423
onga+0.419
hs+0.416
Neg logit contributions
arenthood-0.431
atism-0.399
udeb-0.392
emet-0.388
eve-0.388
Tokenles
Token ID829
Feature activation+3.25e+00

Pos logit contributions
hots+5.934
la+5.301
hs+5.281
gang+5.074
onga+4.873
Neg logit contributions
arenthood-9.364
atism-9.265
udeb-8.787
 Nept-8.688
eve-8.663
Token,
Token ID11
Feature activation+3.72e+00

Pos logit contributions
arenthood+2.101
atism+1.919
emet+1.865
eve+1.854
udeb+1.854
Neg logit contributions
hots-2.495
gang-2.223
onga-2.203
 Scor-2.173
hs-2.164
Token this
Token ID428
Feature activation+1.20e+00

Pos logit contributions
arenthood+2.398
atism+2.233
emet+2.172
udeb+2.168
eve+2.142
Neg logit contributions
hots-2.861
gang-2.510
onga-2.475
hs-2.421
 Scor-2.416
Token time
Token ID640
Feature activation+9.03e-02

Pos logit contributions
arenthood+0.816
atism+0.758
udeb+0.739
emet+0.733
eve+0.730
Neg logit contributions
hots-0.908
gang-0.789
onga-0.777
 Scor-0.774
hs-0.774
Token to
Token ID284
Feature activation+1.59e+00

Pos logit contributions
arenthood+0.061
atism+0.056
udeb+0.055
emet+0.054
eve+0.054
Neg logit contributions
hots-0.069
gang-0.060
onga-0.059
 Scor-0.059
hs-0.059
Token a
Token ID257
Feature activation+4.09e+00

Pos logit contributions
arenthood+2.638
atism+2.401
emet+2.372
udeb+2.365
eve+2.351
Neg logit contributions
hots-3.564
gang-3.158
onga-3.097
hs-3.074
 Scor-3.045
Token grid
Token ID10706
Feature activation+1.84e+00

Pos logit contributions
arenthood+2.402
atism+2.195
udeb+2.171
emet+2.153
eve+2.125
Neg logit contributions
hots-3.380
gang-2.964
hs-2.893
onga-2.884
 Scor-2.847
Token:
Token ID25
Feature activation+3.21e+00

Pos logit contributions
arenthood+1.157
atism+1.066
udeb+1.050
emet+1.045
eve+1.034
Neg logit contributions
hots-1.472
gang-1.285
onga-1.266
 Scor-1.264
hs-1.263
Token
Token ID198
Feature activation-2.20e+00

Pos logit contributions
arenthood+2.058
atism+1.892
udeb+1.855
emet+1.850
eve+1.829
Neg logit contributions
hots-2.482
gang-2.174
onga-2.130
hs-2.120
 Scor-2.103
Token
Token ID198
Feature activation-1.43e+00

Pos logit contributions
hots+1.542
gang+1.335
hs+1.314
 Scor+1.311
onga+1.303
Neg logit contributions
arenthood-1.601
atism-1.499
udeb-1.467
emet-1.453
eve-1.436
Tokenvoid
Token ID19382
Feature activation-1.11e+01

Pos logit contributions
hots+1.169
gang+1.031
 Scor+1.023
onga+1.015
hs+1.012
Neg logit contributions
arenthood-0.876
atism-0.805
udeb-0.791
emet-0.778
eve-0.778
Token V
Token ID569
Feature activation-1.97e+00

Pos logit contributions
hots+7.565
 Scor+6.860
gang+6.699
onga+6.694
hs+6.590
Neg logit contributions
arenthood-7.702
atism-7.086
udeb-7.028
emet-6.962
agall-6.901
Tokenort
Token ID419
Feature activation-7.64e-01

Pos logit contributions
hots+1.793
gang+1.604
 Scor+1.584
onga+1.581
hs+1.579
Neg logit contributions
arenthood-1.031
atism-0.935
udeb-0.909
emet-0.896
eve-0.888
Tokenon
Token ID261
Feature activation-2.67e+00

Pos logit contributions
hots+0.536
gang+0.466
onga+0.461
 Scor+0.457
hs+0.455
Neg logit contributions
arenthood-0.554
atism-0.516
udeb-0.510
emet-0.502
eve-0.499
TokenSim
Token ID8890
Feature activation-7.90e-01

Pos logit contributions
hots+1.945
gang+1.700
 Scor+1.676
hs+1.668
onga+1.666
Neg logit contributions
arenthood-1.865
atism-1.743
udeb-1.707
emet-1.688
eve-1.676
Token::
Token ID3712
Feature activation-7.10e+00

Pos logit contributions
hots+0.466
gang+0.390
 Scor+0.382
onga+0.381
hs+0.380
Neg logit contributions
arenthood-0.664
atism-0.626
udeb-0.616
emet-0.611
eve-0.607
Token you
Token ID345
Feature activation+2.16e+00

Pos logit contributions
arenthood+0.154
atism+0.142
udeb+0.141
emet+0.138
eve+0.138
Neg logit contributions
hots-0.170
gang-0.149
hs-0.146
onga-0.146
 Scor-0.146
Token credit
Token ID3884
Feature activation+1.43e+00

Pos logit contributions
arenthood+1.381
atism+1.280
udeb+1.248
eve+1.234
ativity+1.231
Neg logit contributions
hots-1.673
gang-1.472
hs-1.451
onga-1.442
 Scor-1.436
Token for
Token ID329
Feature activation+2.53e+00

Pos logit contributions
arenthood+0.949
atism+0.874
udeb+0.865
emet+0.856
ativity+0.851
Neg logit contributions
hots-1.069
gang-0.942
 Scor-0.925
onga-0.925
hs-0.919
Token your
Token ID534
Feature activation+1.40e-01

Pos logit contributions
arenthood+1.608
atism+1.478
udeb+1.450
emet+1.437
ativity+1.436
Neg logit contributions
hots-1.965
gang-1.745
hs-1.721
onga-1.702
 Scor-1.697
Token aw
Token ID3253
Feature activation-9.97e-01

Pos logit contributions
arenthood+0.089
atism+0.082
udeb+0.080
emet+0.080
eve+0.079
Neg logit contributions
hots-0.110
gang-0.097
hs-0.096
 Scor-0.095
onga-0.095
Tokenes
Token ID274
Feature activation-1.11e+01

Pos logit contributions
hots+0.851
gang+0.755
 Scor+0.746
onga+0.742
hs+0.740
Neg logit contributions
arenthood-0.575
atism-0.527
udeb-0.515
emet-0.509
eve-0.505
Tokenomen
Token ID3674
Feature activation-1.10e+01

Pos logit contributions
hots+5.665
la+4.500
onga+4.465
gang+4.451
hs+4.378
Neg logit contributions
arenthood-9.417
atism-9.103
udeb-8.990
eve-8.793
"},-8.757
Tokeness
Token ID408
Feature activation-2.29e+00

Pos logit contributions
hots+8.018
onga+6.990
gang+6.911
hs+6.806
la+6.721
Neg logit contributions
arenthood-7.193
atism-6.719
 Nept-6.522
utenberg-6.466
emet-6.405
Token.
Token ID13
Feature activation+4.15e-01

Pos logit contributions
hots+1.667
gang+1.445
 Scor+1.423
onga+1.417
hs+1.417
Neg logit contributions
arenthood-1.614
atism-1.504
udeb-1.474
emet-1.458
eve-1.449
Token
Token ID198
Feature activation-1.13e+00

Pos logit contributions
arenthood+0.280
atism+0.259
udeb+0.254
eve+0.252
emet+0.250
Neg logit contributions
hots-0.312
gang-0.272
onga-0.270
 Scor-0.265
hs-0.265
Token
Token ID198
Feature activation-3.78e-02

Pos logit contributions
hots+0.810
gang+0.701
 Scor+0.691
onga+0.688
hs+0.688
Neg logit contributions
arenthood-0.804
atism-0.749
udeb-0.734
emet-0.727
eve-0.722
Token credit
Token ID3884
Feature activation+1.43e+00

Pos logit contributions
arenthood+1.381
atism+1.280
udeb+1.248
eve+1.234
ativity+1.231
Neg logit contributions
hots-1.673
gang-1.472
hs-1.451
onga-1.442
 Scor-1.436
Token for
Token ID329
Feature activation+2.53e+00

Pos logit contributions
arenthood+0.949
atism+0.874
udeb+0.865
emet+0.856
ativity+0.851
Neg logit contributions
hots-1.069
gang-0.942
 Scor-0.925
onga-0.925
hs-0.919
Token your
Token ID534
Feature activation+1.40e-01

Pos logit contributions
arenthood+1.608
atism+1.478
udeb+1.450
emet+1.437
ativity+1.436
Neg logit contributions
hots-1.965
gang-1.745
hs-1.721
onga-1.702
 Scor-1.697
Token aw
Token ID3253
Feature activation-9.97e-01

Pos logit contributions
arenthood+0.089
atism+0.082
udeb+0.080
emet+0.080
eve+0.079
Neg logit contributions
hots-0.110
gang-0.097
hs-0.096
 Scor-0.095
onga-0.095
Tokenes
Token ID274
Feature activation-1.11e+01

Pos logit contributions
hots+0.851
gang+0.755
 Scor+0.746
onga+0.742
hs+0.740
Neg logit contributions
arenthood-0.575
atism-0.527
udeb-0.515
emet-0.509
eve-0.505
Tokenomen
Token ID3674
Feature activation-1.10e+01

Pos logit contributions
hots+5.665
la+4.500
onga+4.465
gang+4.451
hs+4.378
Neg logit contributions
arenthood-9.417
atism-9.103
udeb-8.990
eve-8.793
"},-8.757
Tokeness
Token ID408
Feature activation-2.29e+00

Pos logit contributions
hots+8.018
onga+6.990
gang+6.911
hs+6.806
la+6.721
Neg logit contributions
arenthood-7.193
atism-6.719
 Nept-6.522
utenberg-6.466
emet-6.405
Token.
Token ID13
Feature activation+4.15e-01

Pos logit contributions
hots+1.667
gang+1.445
 Scor+1.423
onga+1.417
hs+1.417
Neg logit contributions
arenthood-1.614
atism-1.504
udeb-1.474
emet-1.458
eve-1.449
Token
Token ID198
Feature activation-1.13e+00

Pos logit contributions
arenthood+0.280
atism+0.259
udeb+0.254
eve+0.252
emet+0.250
Neg logit contributions
hots-0.312
gang-0.272
onga-0.270
 Scor-0.265
hs-0.265
Token
Token ID198
Feature activation-3.78e-02

Pos logit contributions
hots+0.810
gang+0.701
 Scor+0.691
onga+0.688
hs+0.688
Neg logit contributions
arenthood-0.804
atism-0.749
udeb-0.734
emet-0.727
eve-0.722
TokenIf
Token ID1532
Feature activation-3.00e+00

Pos logit contributions
hots+0.028
gang+0.024
 Scor+0.024
onga+0.024
hs+0.024
Neg logit contributions
arenthood-0.026
atism-0.024
udeb-0.024
eve-0.023
emet-0.023
Token wheelchair
Token ID27181
Feature activation-2.23e+00

Pos logit contributions
hots+0.470
gang+0.402
onga+0.396
hs+0.395
 Scor+0.395
Neg logit contributions
arenthood-0.472
atism-0.442
udeb-0.432
emet-0.429
eve-0.428
Token (
Token ID357
Feature activation-1.66e+00

Pos logit contributions
hots+1.658
gang+1.443
 Scor+1.422
onga+1.416
hs+1.415
Neg logit contributions
arenthood-1.542
atism-1.433
udeb-1.402
emet-1.388
eve-1.377
TokenFigure
Token ID11337
Feature activation-6.55e+00

Pos logit contributions
hots+1.223
gang+1.062
 Scor+1.051
onga+1.046
hs+1.041
Neg logit contributions
arenthood-1.150
atism-1.068
udeb-1.052
emet-1.039
eve-1.035
Token 2
Token ID362
Feature activation-7.23e+00

Pos logit contributions
hots+4.288
gang+3.697
hs+3.695
 Scor+3.627
onga+3.605
Neg logit contributions
arenthood-4.913
atism-4.643
udeb-4.543
emet-4.522
eve-4.468
TokenA
Token ID32
Feature activation-7.41e+00

Pos logit contributions
hots+4.485
gang+3.817
hs+3.780
 Scor+3.737
la+3.721
Neg logit contributions
arenthood-5.661
atism-5.365
udeb-5.282
emet-5.181
eve-5.116
Token,
Token ID11
Feature activation-1.09e+01

Pos logit contributions
hots+4.040
gang+3.312
hs+3.261
 Scor+3.243
onga+3.225
Neg logit contributions
arenthood-6.397
atism-6.074
udeb-5.992
emet-5.905
ativity-5.845
Token [
Token ID685
Feature activation-4.79e+00

Pos logit contributions
hots+7.154
gang+6.197
 Scor+6.112
hs+6.028
la+5.960
Neg logit contributions
arenthood-7.879
atism-7.367
ativity-7.076
emet-7.061
eve-7.013
TokenAction
Token ID12502
Feature activation+3.86e+00

Pos logit contributions
hots+3.404
gang+2.956
hs+2.895
 Scor+2.878
onga+2.869
Neg logit contributions
arenthood-3.444
atism-3.217
udeb-3.124
emet-3.097
eve-3.067
Token Junior
Token ID20000
Feature activation+5.06e+00

Pos logit contributions
arenthood+2.514
atism+2.366
eve+2.300
ativity+2.295
udeb+2.291
Neg logit contributions
hots-2.877
onga-2.479
gang-2.479
 Scor-2.452
hs-2.450
Token 3
Token ID513
Feature activation+2.20e+00

Pos logit contributions
arenthood+3.245
atism+2.959
udeb+2.937
eve+2.911
emet+2.886
Neg logit contributions
hots-3.850
gang-3.324
onga-3.302
hs-3.283
zb-3.223
Token,
Token ID11
Feature activation+3.45e-01

Pos logit contributions
arenthood+1.427
atism+1.297
udeb+1.290
emet+1.273
eve+1.271
Neg logit contributions
hots-1.695
onga-1.473
gang-1.472
 Scor-1.450
hs-1.438
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
hots+0.131
gang+0.115
onga+0.112
 Scor+0.112
hs+0.111
Neg logit contributions
arenthood-0.120
atism-0.111
udeb-0.109
emet-0.108
eve-0.107
Token A
Token ID317
Feature activation+7.36e-01

Pos logit contributions
hots+0.749
gang+0.651
onga+0.644
 Scor+0.636
hs+0.634
Neg logit contributions
arenthood-0.695
atism-0.638
udeb-0.628
emet-0.622
eve-0.619
Token voice
Token ID3809
Feature activation-1.21e+00

Pos logit contributions
arenthood+0.448
atism+0.408
udeb+0.402
emet+0.399
eve+0.393
Neg logit contributions
hots-0.608
gang-0.531
onga-0.527
 Scor-0.525
hs-0.516
Token in
Token ID287
Feature activation-1.78e+00

Pos logit contributions
hots+0.927
gang+0.811
 Scor+0.800
onga+0.798
hs+0.795
Neg logit contributions
arenthood-0.800
atism-0.741
udeb-0.725
emet-0.717
eve-0.713
Token the
Token ID262
Feature activation-2.87e+00

Pos logit contributions
hots+1.614
gang+1.443
 Scor+1.425
hs+1.423
onga+1.423
Neg logit contributions
arenthood-0.937
atism-0.851
udeb-0.828
emet-0.816
eve-0.809
Token back
Token ID736
Feature activation-1.09e+01

Pos logit contributions
hots+2.257
gang+1.981
 Scor+1.950
onga+1.946
hs+1.937
Neg logit contributions
arenthood-1.849
atism-1.706
udeb-1.666
emet-1.652
eve-1.640
Token of
Token ID286
Feature activation-1.44e+00

Pos logit contributions
hots+6.641
hs+5.784
gang+5.730
seat+5.666
la+5.516
Neg logit contributions
arenthood-8.252
atism-7.826
udeb-7.596
agall-7.571
utenberg-7.565
Token my
Token ID616
Feature activation-1.22e+00

Pos logit contributions
hots+1.305
gang+1.167
 Scor+1.153
hs+1.151
onga+1.150
Neg logit contributions
arenthood-0.749
atism-0.679
udeb-0.661
emet-0.652
eve-0.646
Token head
Token ID1182
Feature activation-3.78e-01

Pos logit contributions
hots+0.816
gang+0.696
 Scor+0.684
onga+0.679
hs+0.674
Neg logit contributions
arenthood-0.928
atism-0.872
udeb-0.852
emet-0.846
eve-0.837
Token,
Token ID11
Feature activation-1.33e+00

Pos logit contributions
hots+0.293
gang+0.257
 Scor+0.253
onga+0.253
hs+0.251
Neg logit contributions
arenthood-0.248
atism-0.230
udeb-0.225
emet-0.223
eve-0.221
Token probably
Token ID2192
Feature activation-1.78e+00

Pos logit contributions
hots+0.980
gang+0.853
 Scor+0.839
onga+0.838
hs+0.834
Neg logit contributions
arenthood-0.917
atism-0.853
udeb-0.836
emet-0.828
eve-0.821
Tokenher
Token ID372
Feature activation-2.83e+00

Pos logit contributions
hots+3.364
gang+2.881
hs+2.827
onga+2.801
 Scor+2.785
Neg logit contributions
arenthood-4.060
atism-3.803
udeb-3.736
emet-3.692
eve-3.675
Tokenself
Token ID944
Feature activation-2.18e+00

Pos logit contributions
hots+1.843
gang+1.573
 Scor+1.542
hs+1.539
onga+1.538
Neg logit contributions
arenthood-2.209
atism-2.073
udeb-2.041
emet-2.019
eve-2.008
Token as
Token ID355
Feature activation-8.69e-01

Pos logit contributions
hots+1.562
gang+1.353
 Scor+1.331
onga+1.327
hs+1.326
Neg logit contributions
arenthood-1.553
atism-1.448
udeb-1.420
emet-1.406
eve-1.396
Token someone
Token ID2130
Feature activation-3.35e-01

Pos logit contributions
hots+0.662
gang+0.577
 Scor+0.572
hs+0.567
onga+0.566
Neg logit contributions
arenthood-0.581
atism-0.537
udeb-0.525
emet-0.521
eve-0.519
Token he
Token ID339
Feature activation-1.05e+00

Pos logit contributions
hots+0.249
gang+0.218
 Scor+0.215
onga+0.214
hs+0.213
Neg logit contributions
arenthood-0.229
atism-0.211
udeb-0.207
emet-0.206
eve-0.206
Token/
Token ID14
Feature activation-1.08e+01

Pos logit contributions
hots+0.719
gang+0.617
 Scor+0.612
onga+0.605
hs+0.602
Neg logit contributions
arenthood-0.786
atism-0.736
udeb-0.720
emet-0.714
eve-0.712
Tokenshe
Token ID7091
Feature activation-4.09e+00

Pos logit contributions
hots+4.949
gang+4.110
hs+4.068
la+3.908
onga+3.664
Neg logit contributions
arenthood-10.166
atism-9.501
 Nept-9.376
utenberg-9.334
udeb-9.318
Token is
Token ID318
Feature activation-6.53e-01

Pos logit contributions
hots+3.145
gang+2.750
hs+2.707
onga+2.698
 Scor+2.688
Neg logit contributions
arenthood-2.708
atism-2.506
udeb-2.464
emet-2.435
eve-2.404
Token not
Token ID407
Feature activation+1.50e+00

Pos logit contributions
hots+0.487
 Scor+0.425
gang+0.423
onga+0.420
hs+0.416
Neg logit contributions
arenthood-0.440
atism-0.410
eve-0.401
udeb-0.400
emet-0.398
Token through
Token ID832
Feature activation+3.57e-01

Pos logit contributions
arenthood+0.963
atism+0.874
eve+0.864
emet+0.853
udeb+0.851
Neg logit contributions
hots-1.165
 Scor-1.028
gang-1.024
onga-0.998
hs-0.997
Token acts
Token ID6529
Feature activation-2.08e-01

Pos logit contributions
arenthood+0.239
atism+0.218
udeb+0.213
emet+0.212
eve+0.212
Neg logit contributions
hots-0.274
gang-0.237
 Scor-0.237
hs-0.235
onga-0.233
Token's
Token ID338
Feature activation+1.15e+00

Pos logit contributions
arenthood+0.767
atism+0.716
emet+0.684
eve+0.678
ativity+0.670
Neg logit contributions
hots-0.935
gang-0.810
onga-0.806
 Scor-0.795
hs-0.792
Token Chicago
Token ID4842
Feature activation+1.16e+00

Pos logit contributions
arenthood+0.733
atism+0.682
emet+0.659
udeb+0.651
eve+0.644
Neg logit contributions
hots-0.915
gang-0.798
onga-0.783
hs-0.780
 Scor-0.775
Token-
Token ID12
Feature activation-5.07e+00

Pos logit contributions
arenthood+0.792
atism+0.739
emet+0.714
eve+0.710
udeb+0.704
Neg logit contributions
hots-0.865
gang-0.735
onga-0.731
hs-0.724
 Scor-0.723
Tokenbased
Token ID3106
Feature activation+1.34e-01

Pos logit contributions
hots+2.335
gang+1.880
hs+1.791
 Scor+1.782
onga+1.764
Neg logit contributions
arenthood-4.917
atism-4.663
udeb-4.612
emet-4.560
ativity-4.520
Token he
Token ID339
Feature activation+1.71e+00

Pos logit contributions
arenthood+0.087
atism+0.082
emet+0.079
udeb+0.078
eve+0.077
Neg logit contributions
hots-0.104
gang-0.090
onga-0.089
hs-0.088
 Scor-0.088
Tokeni
Token ID72
Feature activation-1.08e+01

Pos logit contributions
arenthood+1.379
atism+1.314
udeb+1.285
emet+1.275
eve+1.272
Neg logit contributions
hots-1.062
gang-0.877
 Scor-0.873
onga-0.871
hs-0.851
Tokenress
Token ID601
Feature activation-3.59e+00

Pos logit contributions
hots+7.676
gang+6.876
hs+6.808
onga+6.648
 Scor+6.440
Neg logit contributions
arenthood-7.075
eve-6.520
udeb-6.468
atism-6.413
emet-6.321
Token Beat
Token ID12568
Feature activation+2.00e-01

Pos logit contributions
hots+2.723
gang+2.380
 Scor+2.346
hs+2.337
onga+2.335
Neg logit contributions
arenthood-2.407
atism-2.235
udeb-2.192
emet-2.164
eve-2.147
Tokenrice
Token ID20970
Feature activation-9.39e-01

Pos logit contributions
arenthood+0.141
atism+0.131
emet+0.129
udeb+0.128
eve+0.128
Neg logit contributions
hots-0.145
gang-0.124
 Scor-0.123
onga-0.122
hs-0.122
Token Joyce
Token ID25936
Feature activation-1.91e+00

Pos logit contributions
hots+0.688
gang+0.594
onga+0.586
 Scor+0.583
hs+0.582
Neg logit contributions
arenthood-0.657
atism-0.611
udeb-0.594
emet-0.593
eve-0.590
Token Ke
Token ID3873
Feature activation-2.96e+00

Pos logit contributions
hots+1.441
gang+1.252
 Scor+1.235
onga+1.234
hs+1.228
Neg logit contributions
arenthood-1.301
atism-1.207
udeb-1.173
emet-1.170
eve-1.162
Token the
Token ID262
Feature activation+8.38e-01

Pos logit contributions
hots+1.704
gang+1.477
 Scor+1.454
hs+1.448
onga+1.448
Neg logit contributions
arenthood-1.688
atism-1.573
udeb-1.540
emet-1.525
eve-1.514
Token world
Token ID995
Feature activation+1.27e+00

Pos logit contributions
arenthood+0.565
atism+0.525
udeb+0.515
eve+0.513
emet+0.512
Neg logit contributions
hots-0.631
gang-0.546
onga-0.541
 Scor-0.537
hs-0.536
Token.
Token ID13
Feature activation-9.73e-01

Pos logit contributions
arenthood+0.832
atism+0.767
udeb+0.757
emet+0.751
eve+0.748
Neg logit contributions
hots-0.962
gang-0.852
onga-0.838
 Scor-0.836
hs-0.828
Token (
Token ID357
Feature activation+2.06e+00

Pos logit contributions
hots+0.640
gang+0.547
onga+0.536
 Scor+0.535
hs+0.532
Neg logit contributions
arenthood-0.750
atism-0.699
udeb-0.688
emet-0.687
eve-0.685
TokenWa
Token ID33484
Feature activation-2.87e+00

Pos logit contributions
arenthood+1.493
atism+1.383
udeb+1.376
eve+1.374
emet+1.363
Neg logit contributions
hots-1.453
 Scor-1.250
gang-1.235
onga-1.220
hs-1.192
Tokenub
Token ID549
Feature activation-1.08e+01

Pos logit contributions
hots+2.708
gang+2.432
onga+2.404
hs+2.400
 Scor+2.392
Neg logit contributions
arenthood-1.401
atism-1.263
udeb-1.215
emet-1.205
eve-1.191
Tokenges
Token ID3212
Feature activation-3.47e+00

Pos logit contributions
hots+7.639
hs+6.804
gang+6.755
zb+6.346
la+6.336
Neg logit contributions
arenthood-7.171
atism-6.871
udeb-6.690
emet-6.610
 Nept-6.599
Tokenhig
Token ID25196
Feature activation-4.52e+00

Pos logit contributions
hots+1.659
gang+1.323
hs+1.290
onga+1.272
 Scor+1.264
Neg logit contributions
arenthood-3.313
atism-3.148
udeb-3.098
emet-3.081
eve-3.049
Token Rice
Token ID13823
Feature activation-2.79e+00

Pos logit contributions
hots+2.433
gang+2.024
 Scor+2.014
hs+1.976
onga+1.938
Neg logit contributions
arenthood-3.973
atism-3.805
udeb-3.726
emet-3.717
eve-3.639
Token/
Token ID14
Feature activation-6.60e+00

Pos logit contributions
hots+1.724
gang+1.459
 Scor+1.431
hs+1.425
onga+1.423
Neg logit contributions
arenthood-2.264
atism-2.132
udeb-2.092
emet-2.076
eve-2.059
TokenCBC
Token ID29208
Feature activation-9.54e-01

Pos logit contributions
hots+3.264
gang+2.726
hs+2.645
la+2.540
 Scor+2.517
Neg logit contributions
arenthood-5.985
atism-5.761
ativity-5.568
udeb-5.559
emet-5.550
Token he
Token ID339
Feature activation+1.37e+00

Pos logit contributions
hots+1.299
gang+1.132
onga+1.115
 Scor+1.109
hs+1.106
Neg logit contributions
arenthood-1.213
atism-1.135
udeb-1.104
emet-1.093
eve-1.088
Token used
Token ID973
Feature activation-5.00e-01

Pos logit contributions
arenthood+0.859
atism+0.809
udeb+0.782
eve+0.771
emet+0.765
Neg logit contributions
hots-1.078
gang-0.954
onga-0.946
 Scor-0.936
hs-0.926
Token every
Token ID790
Feature activation-1.84e+00

Pos logit contributions
hots+0.354
gang+0.306
onga+0.301
 Scor+0.300
hs+0.300
Neg logit contributions
arenthood-0.362
atism-0.338
udeb-0.332
emet-0.328
eve-0.326
Token dirty
Token ID11841
Feature activation-2.06e-01

Pos logit contributions
hots+1.324
gang+1.144
 Scor+1.125
onga+1.124
hs+1.121
Neg logit contributions
arenthood-1.307
atism-1.219
udeb-1.195
emet-1.183
eve-1.177
Token trick
Token ID6908
Feature activation-4.96e+00

Pos logit contributions
hots+0.197
gang+0.175
onga+0.173
hs+0.172
 Scor+0.172
Neg logit contributions
arenthood-0.098
atism-0.088
udeb-0.085
emet-0.085
eve-0.084
Token he
Token ID339
Feature activation-1.07e+01

Pos logit contributions
hots+3.342
gang+2.851
 Scor+2.819
hs+2.786
onga+2.780
Neg logit contributions
arenthood-3.757
atism-3.522
udeb-3.455
emet-3.427
eve-3.365
Token could
Token ID714
Feature activation-9.52e+00

Pos logit contributions
hots+6.655
hs+5.621
gang+5.608
onga+5.437
la+5.356
Neg logit contributions
arenthood-8.219
emet-7.720
utenberg-7.539
ativity-7.489
udeb-7.485
Token think
Token ID892
Feature activation-1.42e+00

Pos logit contributions
hots+6.178
onga+5.390
gang+5.378
hs+5.338
 Scor+5.315
Neg logit contributions
arenthood-6.804
atism-6.464
emet-6.296
ativity-6.199
utenberg-6.194
Token of
Token ID286
Feature activation-4.10e+00

Pos logit contributions
hots+1.069
gang+0.929
hs+0.910
onga+0.910
 Scor+0.909
Neg logit contributions
arenthood-0.972
atism-0.902
udeb-0.883
eve-0.871
emet-0.869
Token to
Token ID284
Feature activation-2.57e+00

Pos logit contributions
hots+2.824
gang+2.426
 Scor+2.398
onga+2.375
hs+2.374
Neg logit contributions
arenthood-3.023
atism-2.838
udeb-2.791
emet-2.754
eve-2.731
Token secure
Token ID5713
Feature activation+2.72e+00

Pos logit contributions
hots+2.034
gang+1.788
 Scor+1.765
onga+1.758
hs+1.757
Neg logit contributions
arenthood-1.636
atism-1.511
udeb-1.478
emet-1.461
eve-1.452
Token in
Token ID287
Feature activation-2.73e+00

Pos logit contributions
hots+2.209
gang+1.900
 Scor+1.872
hs+1.866
onga+1.855
Neg logit contributions
arenthood-2.414
atism-2.257
udeb-2.219
emet-2.190
eve-2.176
Token Boston
Token ID6182
Feature activation+7.20e-01

Pos logit contributions
hots+1.828
gang+1.580
 Scor+1.552
hs+1.544
onga+1.539
Neg logit contributions
arenthood-2.056
atism-1.916
udeb-1.886
emet-1.869
eve-1.844
Token.
Token ID13
Feature activation-5.15e-01

Pos logit contributions
arenthood+0.509
atism+0.473
udeb+0.462
emet+0.461
eve+0.461
Neg logit contributions
hots-0.516
gang-0.448
onga-0.443
 Scor-0.442
hs-0.440
Token (
Token ID357
Feature activation+1.08e+00

Pos logit contributions
hots+0.373
gang+0.322
onga+0.317
hs+0.313
 Scor+0.312
Neg logit contributions
arenthood-0.364
atism-0.337
udeb-0.332
emet-0.331
eve-0.331
TokenWa
Token ID33484
Feature activation-5.20e+00

Pos logit contributions
arenthood+0.776
atism+0.720
udeb+0.713
eve+0.711
emet+0.706
Neg logit contributions
hots-0.774
 Scor-0.664
gang-0.661
onga-0.654
hs-0.641
Tokenub
Token ID549
Feature activation-1.07e+01

Pos logit contributions
hots+4.733
gang+4.239
onga+4.207
hs+4.203
la+4.111
Neg logit contributions
arenthood-2.666
atism-2.422
emet-2.311
udeb-2.290
eve-2.267
Tokenges
Token ID3212
Feature activation-2.54e+00

Pos logit contributions
hots+7.593
hs+6.839
gang+6.768
la+6.350
zb+6.336
Neg logit contributions
arenthood-7.123
atism-6.841
udeb-6.636
emet-6.521
 Nept-6.510
Tokenhig
Token ID25196
Feature activation-4.39e+00

Pos logit contributions
hots+1.247
gang+1.003
 Scor+0.976
onga+0.973
hs+0.972
Neg logit contributions
arenthood-2.395
atism-2.272
udeb-2.237
emet-2.221
eve-2.210
Token Rice
Token ID13823
Feature activation-3.68e+00

Pos logit contributions
hots+2.356
gang+1.956
 Scor+1.948
hs+1.911
onga+1.875
Neg logit contributions
arenthood-3.876
atism-3.713
udeb-3.630
emet-3.624
eve-3.552
Token/
Token ID14
Feature activation-7.94e+00

Pos logit contributions
hots+2.213
gang+1.872
 Scor+1.831
hs+1.831
onga+1.813
Neg logit contributions
arenthood-3.035
atism-2.871
udeb-2.813
emet-2.795
eve-2.753
TokenCBC
Token ID29208
Feature activation-1.04e-01

Pos logit contributions
hots+3.794
gang+3.157
hs+3.061
la+2.958
onga+2.906
Neg logit contributions
arenthood-7.221
atism-6.986
ativity-6.753
udeb-6.743
emet-6.724
Tokenre
Token ID260
Feature activation+3.69e-02

Pos logit contributions
arenthood+0.208
atism+0.191
eve+0.189
udeb+0.187
emet+0.186
Neg logit contributions
hots-0.284
gang-0.248
 Scor-0.248
onga-0.247
hs-0.242
Token closed
Token ID4838
Feature activation+3.00e+00

Pos logit contributions
arenthood+0.025
atism+0.024
udeb+0.023
emet+0.023
eve+0.023
Neg logit contributions
hots-0.027
gang-0.024
onga-0.024
 Scor-0.023
hs-0.023
Token now
Token ID783
Feature activation+1.83e+00

Pos logit contributions
arenthood+1.936
atism+1.801
udeb+1.740
eve+1.736
ativity+1.721
Neg logit contributions
hots-2.304
gang-2.033
onga-2.020
 Scor-1.992
hs-1.978
Token!
Token ID0
Feature activation+2.36e+00

Pos logit contributions
arenthood+1.192
atism+1.106
udeb+1.078
eve+1.065
emet+1.057
Neg logit contributions
hots-1.402
gang-1.242
onga-1.216
 Scor-1.211
hs-1.205
Token come
Token ID1282
Feature activation+3.16e+00

Pos logit contributions
arenthood+1.661
atism+1.529
udeb+1.510
eve+1.502
emet+1.496
Neg logit contributions
hots-1.699
gang-1.462
onga-1.449
hs-1.419
 Scor-1.402
Token get
Token ID651
Feature activation+7.61e+00

Pos logit contributions
arenthood+2.027
atism+1.874
eve+1.803
udeb+1.801
emet+1.790
Neg logit contributions
hots-2.435
onga-2.148
gang-2.117
hs-2.091
 Scor-2.083
Token your
Token ID534
Feature activation+3.42e+00

Pos logit contributions
arenthood+4.230
atism+3.875
eve+3.777
udeb+3.762
ativity+3.761
Neg logit contributions
hots-6.170
onga-5.492
gang-5.486
hs-5.397
 Scor-5.308
Token kids
Token ID3988
Feature activation+5.07e+00

Pos logit contributions
arenthood+2.232
atism+2.093
udeb+2.028
emet+2.008
eve+2.002
Neg logit contributions
hots-2.590
gang-2.275
onga-2.254
hs-2.214
 Scor-2.197
Token!
Token ID0
Feature activation+3.47e+00

Pos logit contributions
arenthood+3.164
atism+2.917
udeb+2.857
ativity+2.839
eve+2.834
Neg logit contributions
hots-3.839
gang-3.427
onga-3.364
hs-3.326
 Scor-3.325
Token
Token ID447
Feature activation+1.13e+00

Pos logit contributions
arenthood+2.335
atism+2.154
udeb+2.118
eve+2.102
emet+2.092
Neg logit contributions
hots-2.574
gang-2.216
onga-2.215
hs-2.172
 Scor-2.139
Token
Token ID251
Feature activation+1.37e+00

Pos logit contributions
arenthood+0.965
atism+0.900
eve+0.882
udeb+0.881
emet+0.873
Neg logit contributions
hots-0.658
gang-0.541
onga-0.538
 Scor-0.529
hs-0.528
Token
Token ID247
Feature activation-6.50e-01

Pos logit contributions
hots+1.606
gang+1.368
 Scor+1.347
onga+1.344
hs+1.329
Neg logit contributions
arenthood-1.933
atism-1.806
udeb-1.770
eve-1.759
emet-1.756
Tokenve
Token ID303
Feature activation-4.53e-01

Pos logit contributions
hots+0.446
gang+0.385
 Scor+0.380
onga+0.379
hs+0.376
Neg logit contributions
arenthood-0.483
atism-0.450
udeb-0.442
emet-0.439
eve-0.438
Token been
Token ID587
Feature activation-2.46e+00

Pos logit contributions
hots+0.327
gang+0.284
 Scor+0.279
onga+0.279
hs+0.277
Neg logit contributions
arenthood-0.322
atism-0.299
udeb-0.293
emet-0.290
eve-0.289
Token there
Token ID612
Feature activation-2.12e-01

Pos logit contributions
hots+1.882
gang+1.644
 Scor+1.622
hs+1.615
onga+1.611
Neg logit contributions
arenthood-1.631
atism-1.514
udeb-1.479
emet-1.465
eve-1.452
Token for
Token ID329
Feature activation+3.89e+00

Pos logit contributions
hots+0.154
gang+0.135
 Scor+0.133
onga+0.132
hs+0.132
Neg logit contributions
arenthood-0.149
atism-0.138
udeb-0.135
eve-0.133
emet-0.133
Token almost
Token ID2048
Feature activation+1.00e+01

Pos logit contributions
arenthood+2.416
atism+2.205
eve+2.156
emet+2.147
udeb+2.137
Neg logit contributions
hots-3.064
gang-2.744
onga-2.707
 Scor-2.665
hs-2.651
Token 12
Token ID1105
Feature activation+2.52e+00

Pos logit contributions
arenthood+5.774
atism+5.106
emet+5.055
eve+5.046
 Nept+5.027
Neg logit contributions
hots-7.845
onga-6.986
gang-6.943
 Scor-6.731
zb-6.687
Token hours
Token ID2250
Feature activation+4.95e+00

Pos logit contributions
arenthood+0.995
atism+0.860
udeb+0.829
eve+0.813
emet+0.807
Neg logit contributions
hots-2.600
gang-2.376
onga-2.345
 Scor-2.339
hs-2.300
Token as
Token ID355
Feature activation+1.94e+00

Pos logit contributions
arenthood+3.296
atism+3.015
emet+2.953
udeb+2.950
eve+2.937
Neg logit contributions
hots-3.573
gang-3.284
 Scor-3.165
onga-3.158
hs-3.078
Token I
Token ID314
Feature activation+1.78e+00

Pos logit contributions
arenthood+1.264
atism+1.161
udeb+1.144
eve+1.135
emet+1.123
Neg logit contributions
hots-1.496
gang-1.324
onga-1.296
 Scor-1.285
hs-1.275
Token
Token ID447
Feature activation-1.14e+00

Pos logit contributions
arenthood+1.154
atism+1.070
udeb+1.048
emet+1.039
eve+1.030
Neg logit contributions
hots-1.377
gang-1.210
 Scor-1.192
onga-1.191
hs-1.172
Tokenс
Token ID21727
Feature activation+6.54e-01

Pos logit contributions
hots+0.192
gang+0.168
 Scor+0.166
onga+0.165
hs+0.165
Neg logit contributions
arenthood-0.172
atism-0.159
udeb-0.156
emet-0.155
eve-0.154
Token
Token ID12466
Feature activation-6.27e-01

Pos logit contributions
arenthood+0.364
atism+0.335
udeb+0.326
emet+0.321
eve+0.321
Neg logit contributions
hots-0.571
gang-0.506
onga-0.500
 Scor-0.500
hs-0.498
Token
Token ID123
Feature activation+4.05e+00

Pos logit contributions
hots+0.377
gang+0.316
 Scor+0.312
onga+0.311
hs+0.308
Neg logit contributions
arenthood-0.521
atism-0.491
udeb-0.482
emet-0.478
eve-0.477
Tokenр
Token ID21169
Feature activation+5.05e+00

Pos logit contributions
arenthood+1.850
atism+1.691
udeb+1.628
eve+1.613
emet+1.598
Neg logit contributions
hots-3.863
 Scor-3.439
onga-3.428
gang-3.427
hs-3.393
Tokenо
Token ID15166
Feature activation+1.47e+00

Pos logit contributions
arenthood+2.333
atism+2.152
eve+2.070
udeb+2.067
emet+2.055
Neg logit contributions
hots-4.745
 Scor-4.247
gang-4.229
onga-4.200
hs-4.186
Tokenс
Token ID21727
Feature activation+7.04e+00

Pos logit contributions
arenthood+0.988
atism+0.924
udeb+0.902
emet+0.896
eve+0.895
Neg logit contributions
hots-1.119
gang-0.971
onga-0.962
 Scor-0.961
hs-0.958
Tokenь
Token ID45367
Feature activation+5.66e+00

Pos logit contributions
arenthood+4.144
atism+3.880
eve+3.765
udeb+3.760
emet+3.726
Neg logit contributions
hots-5.619
gang-4.881
onga-4.875
 Scor-4.847
hs-4.832
Token
Token ID140
Feature activation+3.18e+00

Pos logit contributions
arenthood+3.183
atism+2.989
eve+2.899
udeb+2.859
emet+2.835
Neg logit contributions
hots-4.740
gang-4.143
onga-4.142
hs-4.116
 Scor-4.113
Token
Token ID109
Feature activation+5.73e+00

Pos logit contributions
arenthood+2.610
atism+2.482
eve+2.440
udeb+2.390
emet+2.383
Neg logit contributions
hots-1.922
gang-1.608
onga-1.592
 Scor-1.573
hs-1.554
Tokenо�
Token ID25443
Feature activation+1.47e+00

Pos logit contributions
arenthood+2.739
atism+2.554
eve+2.492
emet+2.449
udeb+2.391
Neg logit contributions
hots-5.326
gang-4.687
onga-4.632
 Scor-4.583
hs-4.576
Token
Token ID117
Feature activation+3.67e+00

Pos logit contributions
arenthood+1.172
atism+1.116
eve+1.086
udeb+1.082
emet+1.072
Neg logit contributions
hots-0.928
gang-0.788
onga-0.771
 Scor-0.765
hs-0.761
Token Offic
Token ID6328
Feature activation-9.48e-01

Pos logit contributions
hots+1.808
gang+1.571
 Scor+1.547
onga+1.541
hs+1.540
Neg logit contributions
arenthood-1.741
atism-1.620
udeb-1.588
emet-1.572
eve-1.561
Tokeniers
Token ID3183
Feature activation+3.21e+00

Pos logit contributions
hots+0.660
gang+0.568
 Scor+0.559
onga+0.557
hs+0.557
Neg logit contributions
arenthood-0.698
atism-0.652
udeb-0.639
emet-0.633
eve-0.629
Token et
Token ID2123
Feature activation+1.87e-01

Pos logit contributions
arenthood+2.198
atism+2.097
udeb+2.010
eve+2.001
emet+1.993
Neg logit contributions
hots-2.327
gang-1.993
onga-1.980
 Scor-1.970
hs-1.947
Token les
Token ID10287
Feature activation-2.97e+00

Pos logit contributions
arenthood+0.137
atism+0.129
udeb+0.126
emet+0.124
eve+0.124
Neg logit contributions
hots-0.131
gang-0.112
onga-0.111
 Scor-0.110
hs-0.110
Token F
Token ID376
Feature activation+4.07e+00

Pos logit contributions
hots+2.187
gang+1.906
 Scor+1.878
hs+1.868
onga+1.868
Neg logit contributions
arenthood-2.064
atism-1.918
udeb-1.881
emet-1.861
eve-1.846
Tokenond
Token ID623
Feature activation+7.18e+00

Pos logit contributions
arenthood+2.096
atism+1.889
udeb+1.888
emet+1.830
eve+1.800
Neg logit contributions
hots-3.663
 Scor-3.324
gang-3.266
hs-3.208
onga-3.186
Tokenateurs
Token ID45211
Feature activation-4.47e-01

Pos logit contributions
arenthood+4.206
atism+4.021
udeb+3.857
emet+3.833
ativity+3.758
Neg logit contributions
hots-5.627
gang-5.079
 Scor-5.075
onga-4.937
hs-4.892
Token cher
Token ID21382
Feature activation+3.66e+00

Pos logit contributions
hots+0.333
gang+0.289
 Scor+0.285
onga+0.285
hs+0.283
Neg logit contributions
arenthood-0.305
atism-0.285
udeb-0.278
emet-0.276
eve-0.274
Tokencher
Token ID2044
Feature activation+1.27e+00

Pos logit contributions
arenthood+2.574
atism+2.454
udeb+2.404
eve+2.386
emet+2.350
Neg logit contributions
hots-2.564
 Scor-2.214
gang-2.207
onga-2.158
hs-2.149
Tokenont
Token ID756
Feature activation+1.90e+00

Pos logit contributions
arenthood+0.896
atism+0.850
udeb+0.826
emet+0.816
eve+0.812
Neg logit contributions
hots-0.911
 Scor-0.784
gang-0.783
onga-0.769
hs-0.765
Token un
Token ID555
Feature activation-3.31e-01

Pos logit contributions
arenthood+1.325
atism+1.255
udeb+1.212
emet+1.209
eve+1.204
Neg logit contributions
hots-1.372
gang-1.181
 Scor-1.174
onga-1.156
hs-1.144
Token via
Token ID2884
Feature activation+1.00e+00

Pos logit contributions
arenthood+0.691
atism+0.644
udeb+0.629
emet+0.623
eve+0.619
Neg logit contributions
hots-0.786
gang-0.700
onga-0.686
 Scor-0.681
hs-0.678
Token the
Token ID262
Feature activation+2.98e+00

Pos logit contributions
arenthood+0.669
atism+0.625
udeb+0.613
emet+0.611
eve+0.608
Neg logit contributions
hots-0.752
gang-0.659
onga-0.647
hs-0.643
 Scor-0.642
Token
Token ID220
Feature activation+1.43e+00

Pos logit contributions
arenthood+1.951
atism+1.820
udeb+1.801
eve+1.797
emet+1.788
Neg logit contributions
hots-2.234
gang-1.967
onga-1.919
hs-1.897
 Scor-1.887
Tokenix
Token ID844
Feature activation+5.39e+00

Pos logit contributions
arenthood+0.999
udeb+0.932
atism+0.928
emet+0.922
eve+0.910
Neg logit contributions
hots-1.014
gang-0.897
 Scor-0.884
onga-0.871
hs-0.857
Tokeng
Token ID70
Feature activation+1.28e+00

Pos logit contributions
arenthood+3.725
udeb+3.511
atism+3.481
eve+3.465
emet+3.437
Neg logit contributions
hots-3.630
 Scor-3.245
onga-3.208
gang-3.154
 Prohibition-3.078
Tokenbe
Token ID1350
Feature activation+7.14e+00

Pos logit contributions
arenthood+0.886
atism+0.819
udeb+0.813
emet+0.808
eve+0.797
Neg logit contributions
hots-0.934
gang-0.811
 Scor-0.807
onga-0.797
hs-0.785
Token driver
Token ID4639
Feature activation-1.52e+00

Pos logit contributions
arenthood+4.762
emet+4.509
udeb+4.446
eve+4.433
atism+4.423
Neg logit contributions
hots-5.043
 Scor-4.377
onga-4.304
gang-4.268
 Prohibition-4.238
Token for
Token ID329
Feature activation-2.59e-01

Pos logit contributions
hots+1.117
gang+0.970
 Scor+0.955
onga+0.953
hs+0.951
Neg logit contributions
arenthood-1.065
atism-0.991
udeb-0.972
emet-0.962
eve-0.955
Token speeds
Token ID12055
Feature activation-1.58e+00

Pos logit contributions
hots+0.196
gang+0.172
onga+0.169
 Scor+0.168
hs+0.168
Neg logit contributions
arenthood-0.172
atism-0.160
udeb-0.157
emet-0.157
eve-0.156
Token up
Token ID510
Feature activation-1.41e+00

Pos logit contributions
hots+1.160
gang+1.023
onga+1.008
 Scor+1.006
hs+0.997
Neg logit contributions
arenthood-1.085
atism-1.008
udeb-0.996
emet-0.985
eve-0.978
Token to
Token ID284
Feature activation-2.93e+00

Pos logit contributions
hots+1.029
gang+0.897
 Scor+0.881
onga+0.881
hs+0.875
Neg logit contributions
arenthood-0.988
atism-0.919
udeb-0.902
emet-0.895
eve-0.890
Token logs
Token ID17259
Feature activation-1.87e+00

Pos logit contributions
hots+0.612
gang+0.536
 Scor+0.530
hs+0.530
onga+0.528
Neg logit contributions
arenthood-0.501
atism-0.462
udeb-0.452
emet-0.447
eve-0.443
Token.
Token ID764
Feature activation-2.91e+00

Pos logit contributions
hots+1.392
gang+1.211
 Scor+1.194
onga+1.190
hs+1.189
Neg logit contributions
arenthood-1.289
atism-1.198
udeb-1.173
emet-1.161
eve-1.153
Token To
Token ID1675
Feature activation+3.81e-01

Pos logit contributions
hots+2.044
gang+1.764
 Scor+1.736
onga+1.730
hs+1.727
Neg logit contributions
arenthood-2.124
atism-1.984
udeb-1.945
emet-1.926
eve-1.915
Token see
Token ID766
Feature activation-1.25e-01

Pos logit contributions
arenthood+0.242
atism+0.226
udeb+0.220
emet+0.219
eve+0.217
Neg logit contributions
hots-0.301
gang-0.264
 Scor-0.260
hs-0.257
onga-0.257
Token the
Token ID262
Feature activation+3.83e+00

Pos logit contributions
hots+0.094
gang+0.083
onga+0.081
 Scor+0.081
hs+0.081
Neg logit contributions
arenthood-0.084
atism-0.078
udeb-0.076
emet-0.076
eve-0.075
Token logs
Token ID17259
Feature activation+1.61e+00

Pos logit contributions
arenthood+2.150
atism+1.976
eve+1.960
udeb+1.939
emet+1.928
Neg logit contributions
hots-3.234
gang-2.905
onga-2.834
 Scor-2.813
hs-2.773
Token for
Token ID329
Feature activation+3.18e+00

Pos logit contributions
arenthood+1.061
atism+0.986
udeb+0.966
emet+0.961
eve+0.957
Neg logit contributions
hots-1.227
gang-1.084
 Scor-1.062
onga-1.060
hs-1.048
Token the
Token ID262
Feature activation+5.08e+00

Pos logit contributions
arenthood+1.987
eve+1.842
atism+1.831
emet+1.793
udeb+1.785
Neg logit contributions
hots-2.473
gang-2.210
onga-2.131
hs-2.131
 Scor-2.126
Token function
Token ID2163
Feature activation+3.96e-01

Pos logit contributions
arenthood+3.236
eve+3.054
atism+2.971
emet+2.936
udeb+2.910
Neg logit contributions
hots-3.828
gang-3.409
onga-3.272
 Scor-3.268
hs-3.210
Token test
Token ID1332
Feature activation+5.12e+00

Pos logit contributions
arenthood+0.265
atism+0.244
udeb+0.240
emet+0.239
eve+0.237
Neg logit contributions
hots-0.301
gang-0.263
onga-0.259
 Scor-0.259
hs-0.256
Token for
Token ID329
Feature activation+7.01e-01

Pos logit contributions
arenthood+2.916
emet+2.665
atism+2.659
eve+2.648
udeb+2.605
Neg logit contributions
hots-4.278
 Scor-3.762
gang-3.724
onga-3.714
hs-3.605
Token along
Token ID1863
Feature activation+4.13e+00

Pos logit contributions
arenthood+2.508
atism+2.269
eve+2.204
emet+2.179
ativity+2.169
Neg logit contributions
hots-3.057
gang-2.674
onga-2.668
 Scor-2.622
hs-2.587
Token,
Token ID11
Feature activation+5.88e+00

Pos logit contributions
arenthood+2.587
atism+2.337
eve+2.292
emet+2.266
 Nept+2.263
Neg logit contributions
hots-3.252
onga-2.837
gang-2.835
hs-2.782
 Scor-2.760
Token my
Token ID616
Feature activation+1.43e+00

Pos logit contributions
arenthood+3.547
atism+3.269
eve+3.202
 Nept+3.192
emet+3.126
Neg logit contributions
hots-4.607
onga-4.024
gang-3.996
hs-3.941
zb-3.871
Token dear
Token ID13674
Feature activation+4.65e-01

Pos logit contributions
arenthood+0.802
atism+0.732
eve+0.707
udeb+0.707
emet+0.702
Neg logit contributions
hots-1.234
gang-1.097
onga-1.079
 Scor-1.075
hs-1.071
Token,
Token ID11
Feature activation+2.90e+00

Pos logit contributions
arenthood+0.303
atism+0.280
udeb+0.273
emet+0.272
eve+0.271
Neg logit contributions
hots-0.361
gang-0.316
onga-0.311
 Scor-0.310
hs-0.309
Token come
Token ID1282
Feature activation+4.94e+00

Pos logit contributions
arenthood+1.809
atism+1.652
eve+1.613
udeb+1.602
emet+1.600
Neg logit contributions
hots-2.306
gang-2.020
onga-2.005
hs-1.987
 Scor-1.960
Token along
Token ID1863
Feature activation+3.58e+00

Pos logit contributions
arenthood+2.387
atism+2.132
eve+2.012
emet+1.993
ativity+1.973
Neg logit contributions
hots-4.569
gang-4.140
onga-4.080
 Scor-4.063
hs-4.053
Token,
Token ID11
Feature activation+4.16e+00

Pos logit contributions
arenthood+2.297
atism+2.101
eve+2.034
udeb+2.013
emet+2.010
Neg logit contributions
hots-2.769
gang-2.436
onga-2.414
hs-2.386
 Scor-2.376
Token it
Token ID340
Feature activation+2.13e+00

Pos logit contributions
arenthood+2.508
atism+2.288
eve+2.225
emet+2.215
udeb+2.210
Neg logit contributions
hots-3.345
gang-2.932
onga-2.929
hs-2.888
 Scor-2.839
Token will
Token ID481
Feature activation+3.13e+00

Pos logit contributions
arenthood+1.386
atism+1.284
eve+1.235
udeb+1.226
emet+1.225
Neg logit contributions
hots-1.656
gang-1.457
 Scor-1.437
onga-1.421
hs-1.404
Token pass
Token ID1208
Feature activation+6.05e+00

Pos logit contributions
arenthood+2.228
atism+2.089
eve+2.016
emet+1.997
udeb+1.971
Neg logit contributions
hots-2.233
gang-1.927
 Scor-1.911
onga-1.873
hs-1.865
Token year
Token ID614
Feature activation+1.67e+00

Pos logit contributions
arenthood+2.737
emet+2.415
atism+2.409
udeb+2.366
eve+2.343
Neg logit contributions
hots-5.046
gang-4.434
 Scor-4.416
onga-4.388
hs-4.344
Token.
Token ID13
Feature activation+1.43e-01

Pos logit contributions
arenthood+1.095
atism+1.018
udeb+0.991
emet+0.991
eve+0.978
Neg logit contributions
hots-1.276
gang-1.131
 Scor-1.105
hs-1.092
onga-1.090
Token
Token ID198
Feature activation+5.51e-01

Pos logit contributions
arenthood+0.099
atism+0.091
udeb+0.090
emet+0.089
eve+0.088
Neg logit contributions
hots-0.106
gang-0.093
onga-0.091
hs-0.090
 Scor-0.090
Token
Token ID198
Feature activation+1.77e+00

Pos logit contributions
arenthood+0.370
atism+0.341
udeb+0.335
eve+0.334
emet+0.331
Neg logit contributions
hots-0.417
gang-0.362
onga-0.359
 Scor-0.359
hs-0.352
TokenCivil
Token ID32610
Feature activation+2.03e+00

Pos logit contributions
arenthood+1.192
atism+1.099
udeb+1.087
eve+1.076
emet+1.073
Neg logit contributions
hots-1.326
 Scor-1.160
gang-1.157
onga-1.140
hs-1.129
Token Vessel
Token ID44734
Feature activation+2.39e+00

Pos logit contributions
arenthood+1.407
atism+1.301
udeb+1.264
emet+1.262
eve+1.252
Neg logit contributions
hots-1.513
gang-1.286
hs-1.282
 Scor-1.270
onga-1.252
Tokens
Token ID82
Feature activation-3.90e-02

Pos logit contributions
arenthood+1.602
atism+1.464
emet+1.441
eve+1.422
udeb+1.421
Neg logit contributions
hots-1.807
gang-1.572
onga-1.551
hs-1.538
 Scor-1.523
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
hots+0.029
gang+0.025
hs+0.025
onga+0.025
 Scor+0.025
Neg logit contributions
arenthood-0.027
atism-0.025
udeb-0.024
emet-0.024
eve-0.024
Token
Token ID198
Feature activation+6.97e-01

Pos logit contributions
hots+0.985
gang+0.853
 Scor+0.840
onga+0.838
hs+0.836
Neg logit contributions
arenthood-0.974
atism-0.908
udeb-0.890
emet-0.881
eve-0.875
TokenN
Token ID45
Feature activation+4.92e-02

Pos logit contributions
arenthood+0.466
atism+0.431
udeb+0.423
eve+0.420
emet+0.419
Neg logit contributions
hots-0.529
gang-0.461
 Scor-0.459
onga-0.455
hs-0.451
Tokenuclear
Token ID4016
Feature activation+4.76e+00

Pos logit contributions
arenthood+0.034
atism+0.032
udeb+0.031
emet+0.031
eve+0.031
Neg logit contributions
hots-0.036
gang-0.032
 Scor-0.031
hs-0.031
onga-0.031
Token technology
Token ID3037
Feature activation-2.31e+00

Pos logit contributions
hots+0.224
gang+0.194
onga+0.190
hs+0.190
 Scor+0.190
Neg logit contributions
arenthood-0.219
atism-0.205
udeb-0.199
emet-0.198
eve-0.197
Token,
Token ID11
Feature activation-4.83e-01

Pos logit contributions
hots+1.750
gang+1.528
 Scor+1.506
hs+1.500
onga+1.498
Neg logit contributions
arenthood-1.554
atism-1.439
udeb-1.412
emet-1.398
eve-1.387
Token as
Token ID355
Feature activation+4.05e+00

Pos logit contributions
hots+0.353
gang+0.307
onga+0.303
 Scor+0.301
hs+0.300
Neg logit contributions
arenthood-0.337
atism-0.319
udeb-0.308
emet-0.304
eve-0.302
Token political
Token ID1964
Feature activation+3.72e+00

Pos logit contributions
arenthood+2.574
atism+2.462
udeb+2.363
eve+2.316
emet+2.304
Neg logit contributions
hots-3.109
gang-2.768
onga-2.694
hs-2.676
zb-2.635
Token data
Token ID1366
Feature activation-2.09e+00

Pos logit contributions
arenthood+2.505
atism+2.395
eve+2.281
emet+2.266
udeb+2.263
Neg logit contributions
hots-2.740
gang-2.382
onga-2.368
 Scor-2.344
hs-2.335
Token wizards
Token ID34836
Feature activation+2.89e+00

Pos logit contributions
hots+1.595
gang+1.392
 Scor+1.373
hs+1.368
onga+1.365
Neg logit contributions
arenthood-1.389
atism-1.290
udeb-1.265
emet-1.247
eve-1.238
Token like
Token ID588
Feature activation+2.27e-01

Pos logit contributions
arenthood+1.887
atism+1.748
udeb+1.722
emet+1.700
eve+1.691
Neg logit contributions
hots-2.204
gang-1.960
 Scor-1.921
onga-1.917
hs-1.897
Token to
Token ID284
Feature activation-2.67e-02

Pos logit contributions
arenthood+0.148
atism+0.139
udeb+0.134
emet+0.133
eve+0.133
Neg logit contributions
hots-0.176
gang-0.155
onga-0.153
hs-0.152
 Scor-0.151
Token say
Token ID910
Feature activation+4.79e+00

Pos logit contributions
hots+0.021
gang+0.018
 Scor+0.018
hs+0.018
onga+0.018
Neg logit contributions
arenthood-0.017
atism-0.016
udeb-0.016
emet-0.016
eve-0.016
Token,
Token ID11
Feature activation+3.42e-01

Pos logit contributions
arenthood+3.062
atism+2.813
udeb+2.737
emet+2.711
eve+2.700
Neg logit contributions
hots-3.718
gang-3.296
 Scor-3.236
onga-3.228
hs-3.220
Token has
Token ID468
Feature activation-3.41e-01

Pos logit contributions
arenthood+0.218
atism+0.203
udeb+0.197
emet+0.194
eve+0.194
Neg logit contributions
hots-0.269
gang-0.238
onga-0.235
 Scor-0.234
hs-0.233
Token who
Token ID508
Feature activation+2.92e+00

Pos logit contributions
arenthood+1.404
atism+1.322
udeb+1.270
eve+1.259
emet+1.256
Neg logit contributions
hots-1.696
gang-1.499
onga-1.470
 Scor-1.450
hs-1.449
Token have
Token ID423
Feature activation+2.77e-01

Pos logit contributions
arenthood+1.888
atism+1.782
udeb+1.705
emet+1.692
eve+1.687
Neg logit contributions
hots-2.267
gang-2.012
 Scor-1.965
onga-1.947
hs-1.921
Token never
Token ID1239
Feature activation+6.67e-01

Pos logit contributions
arenthood+0.189
atism+0.176
udeb+0.172
emet+0.170
eve+0.170
Neg logit contributions
hots-0.207
gang-0.181
onga-0.178
 Scor-0.177
hs-0.176
Token let
Token ID1309
Feature activation-9.59e-01

Pos logit contributions
arenthood+0.438
atism+0.416
udeb+0.397
eve+0.395
emet+0.394
Neg logit contributions
hots-0.513
gang-0.449
onga-0.441
 Scor-0.440
hs-0.433
Token worries
Token ID18572
Feature activation+4.48e-02

Pos logit contributions
hots+0.720
gang+0.628
 Scor+0.618
onga+0.617
hs+0.616
Neg logit contributions
arenthood-0.653
atism-0.607
udeb-0.593
emet-0.586
eve-0.584
Token of
Token ID286
Feature activation+3.01e+00

Pos logit contributions
arenthood+0.031
atism+0.029
udeb+0.028
emet+0.028
eve+0.028
Neg logit contributions
hots-0.033
gang-0.029
onga-0.028
 Scor-0.028
hs-0.028
Token appearing
Token ID12655
Feature activation+2.68e+00

Pos logit contributions
arenthood+2.134
atism+2.014
udeb+1.931
eve+1.924
emet+1.891
Neg logit contributions
hots-2.147
gang-1.848
onga-1.836
 Scor-1.806
hs-1.805
Token tedious
Token ID32460
Feature activation-2.90e+00

Pos logit contributions
arenthood+1.748
atism+1.656
udeb+1.582
eve+1.555
emet+1.541
Neg logit contributions
hots-2.044
gang-1.777
onga-1.775
 Scor-1.751
hs-1.734
Token stand
Token ID1302
Feature activation+1.75e+00

Pos logit contributions
hots+2.136
gang+1.855
 Scor+1.831
hs+1.825
onga+1.820
Neg logit contributions
arenthood-2.000
atism-1.866
udeb-1.832
emet-1.809
eve-1.799
Token in
Token ID287
Feature activation+2.03e+00

Pos logit contributions
arenthood+1.154
atism+1.069
eve+1.044
emet+1.042
ativity+1.020
Neg logit contributions
hots-1.341
gang-1.170
 Scor-1.153
onga-1.152
hs-1.135
Token the
Token ID262
Feature activation+9.76e-01

Pos logit contributions
arenthood+1.269
atism+1.167
eve+1.129
emet+1.124
udeb+1.123
Neg logit contributions
hots-1.651
gang-1.446
onga-1.417
hs-1.412
 Scor-1.410
Token.
Token ID13
Feature activation-1.89e+00

Pos logit contributions
hots+0.564
gang+0.489
 Scor+0.482
hs+0.480
onga+0.478
Neg logit contributions
arenthood-0.551
atism-0.513
udeb-0.503
emet-0.497
eve-0.494
Token Again
Token ID6521
Feature activation-1.37e+00

Pos logit contributions
hots+1.377
gang+1.194
 Scor+1.175
onga+1.173
hs+1.171
Neg logit contributions
arenthood-1.332
atism-1.241
udeb-1.215
emet-1.203
eve-1.196
Token,
Token ID11
Feature activation+4.54e-01

Pos logit contributions
hots+0.991
gang+0.855
 Scor+0.847
hs+0.840
onga+0.838
Neg logit contributions
arenthood-0.967
atism-0.901
udeb-0.888
emet-0.876
eve-0.870
Token the
Token ID262
Feature activation-3.02e-01

Pos logit contributions
arenthood+0.312
atism+0.293
udeb+0.283
emet+0.281
eve+0.280
Neg logit contributions
hots-0.336
gang-0.294
onga-0.289
hs-0.288
 Scor-0.287
Token United
Token ID1578
Feature activation-3.63e+00

Pos logit contributions
hots+0.224
gang+0.196
hs+0.192
onga+0.192
 Scor+0.192
Neg logit contributions
arenthood-0.206
atism-0.194
udeb-0.187
emet-0.186
eve-0.186
Token States
Token ID1829
Feature activation-1.60e+00

Pos logit contributions
hots+1.689
gang+1.368
 Scor+1.312
hs+1.306
la+1.301
Neg logit contributions
arenthood-3.446
udeb-3.271
atism-3.267
emet-3.223
eve-3.180
Token did
Token ID750
Feature activation+1.19e+00

Pos logit contributions
hots+1.219
gang+1.065
 Scor+1.049
onga+1.048
hs+1.044
Neg logit contributions
arenthood-1.078
atism-1.002
udeb-0.977
emet-0.968
eve-0.962
Token not
Token ID407
Feature activation+3.50e-01

Pos logit contributions
arenthood+0.858
atism+0.802
emet+0.777
udeb+0.776
eve+0.771
Neg logit contributions
hots-0.842
gang-0.737
 Scor-0.725
onga-0.718
hs-0.715
Token raise
Token ID5298
Feature activation-3.15e+00

Pos logit contributions
arenthood+0.223
atism+0.209
emet+0.200
udeb+0.200
eve+0.197
Neg logit contributions
hots-0.277
gang-0.244
 Scor-0.240
onga-0.238
hs-0.237
Token interest
Token ID1393
Feature activation+2.88e-01

Pos logit contributions
hots+2.287
gang+1.976
 Scor+1.952
hs+1.945
onga+1.942
Neg logit contributions
arenthood-2.221
atism-2.041
udeb-2.026
emet-2.006
eve-1.992
Token rates
Token ID3965
Feature activation-1.38e+00

Pos logit contributions
arenthood+0.226
atism+0.213
udeb+0.207
emet+0.206
eve+0.204
Neg logit contributions
hots-0.186
gang-0.159
onga-0.156
 Scor-0.155
hs-0.154
Token guns
Token ID6541
Feature activation+1.64e+00

Pos logit contributions
arenthood+0.274
atism+0.254
udeb+0.247
eve+0.245
emet+0.243
Neg logit contributions
hots-0.299
gang-0.261
onga-0.258
 Scor-0.257
hs-0.255
Token are
Token ID389
Feature activation+2.16e+00

Pos logit contributions
arenthood+1.093
atism+1.002
udeb+0.973
eve+0.972
emet+0.952
Neg logit contributions
hots-1.248
gang-1.103
 Scor-1.097
onga-1.083
hs-1.074
Token carried
Token ID5281
Feature activation-1.35e+00

Pos logit contributions
arenthood+1.448
atism+1.346
udeb+1.301
eve+1.290
emet+1.285
Neg logit contributions
hots-1.618
gang-1.399
onga-1.390
 Scor-1.382
hs-1.376
Token in
Token ID287
Feature activation+1.42e+00

Pos logit contributions
hots+0.995
gang+0.867
 Scor+0.855
onga+0.850
hs+0.845
Neg logit contributions
arenthood-0.940
atism-0.871
udeb-0.850
emet-0.843
eve-0.840
Token America
Token ID2253
Feature activation-2.62e-01

Pos logit contributions
arenthood+0.886
atism+0.815
udeb+0.779
eve+0.776
emet+0.774
Neg logit contributions
hots-1.144
gang-1.007
onga-1.000
 Scor-0.994
hs-0.986
Token,
Token ID11
Feature activation-1.32e+00

Pos logit contributions
hots+0.199
gang+0.174
 Scor+0.172
onga+0.171
hs+0.170
Neg logit contributions
arenthood-0.176
atism-0.163
udeb-0.159
emet-0.157
eve-0.157
Token and
Token ID290
Feature activation+2.31e+00

Pos logit contributions
hots+0.979
gang+0.853
 Scor+0.839
onga+0.838
hs+0.835
Neg logit contributions
arenthood-0.903
atism-0.839
udeb-0.821
emet-0.813
eve-0.808
Token both
Token ID1111
Feature activation-1.69e+00

Pos logit contributions
arenthood+1.513
atism+1.425
emet+1.365
udeb+1.362
eve+1.352
Neg logit contributions
hots-1.743
gang-1.534
onga-1.527
 Scor-1.484
hs-1.480
Token actually
Token ID1682
Feature activation+2.95e+00

Pos logit contributions
hots+1.245
gang+1.085
onga+1.067
 Scor+1.066
hs+1.060
Neg logit contributions
arenthood-1.168
atism-1.089
udeb-1.063
emet-1.054
eve-1.047
Token expand
Token ID4292
Feature activation-2.97e+00

Pos logit contributions
arenthood+1.909
atism+1.816
udeb+1.746
emet+1.735
eve+1.710
Neg logit contributions
hots-2.239
gang-1.982
 Scor-1.937
onga-1.925
hs-1.881
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
hots+2.209
gang+1.933
hs+1.909
 Scor+1.907
onga+1.899
Neg logit contributions
arenthood-2.016
atism-1.882
udeb-1.856
emet-1.833
eve-1.815
TokenWe
Token ID1135
Feature activation-2.54e+00

Pos logit contributions
hots+1.565
gang+1.366
 Scor+1.346
hs+1.342
onga+1.339
Neg logit contributions
arenthood-1.430
atism-1.333
udeb-1.300
emet-1.290
eve-1.277
Token're
Token ID821
Feature activation-9.18e-01

Pos logit contributions
hots+1.890
gang+1.644
 Scor+1.623
hs+1.620
onga+1.619
Neg logit contributions
arenthood-1.738
atism-1.611
udeb-1.581
emet-1.564
eve-1.552
Token looking
Token ID2045
Feature activation-1.96e+00

Pos logit contributions
hots+0.688
gang+0.601
onga+0.593
 Scor+0.589
hs+0.587
Neg logit contributions
arenthood-0.626
atism-0.582
udeb-0.567
emet-0.562
eve-0.561
Token into
Token ID656
Feature activation-4.32e+00

Pos logit contributions
hots+1.562
gang+1.368
 Scor+1.352
hs+1.346
onga+1.343
Neg logit contributions
arenthood-1.242
atism-1.144
udeb-1.123
emet-1.110
eve-1.100
Token two
Token ID734
Feature activation-2.71e-01

Pos logit contributions
hots+3.130
 Scor+2.701
gang+2.698
hs+2.659
onga+2.657
Neg logit contributions
arenthood-3.044
atism-2.836
udeb-2.779
emet-2.749
eve-2.712
Token other
Token ID584
Feature activation-7.25e-01

Pos logit contributions
hots+0.206
gang+0.182
onga+0.180
 Scor+0.177
hs+0.177
Neg logit contributions
arenthood-0.180
atism-0.167
udeb-0.163
emet-0.161
eve-0.161
Token scenarios
Token ID13858
Feature activation-2.13e+00

Pos logit contributions
hots+0.536
gang+0.469
onga+0.462
hs+0.458
 Scor+0.457
Neg logit contributions
arenthood-0.498
atism-0.463
udeb-0.452
emet-0.449
eve-0.448
Token that
Token ID326
Feature activation-4.40e-01

Pos logit contributions
hots+1.609
gang+1.403
 Scor+1.383
onga+1.378
hs+1.377
Neg logit contributions
arenthood-1.443
atism-1.339
udeb-1.311
emet-1.297
eve-1.288
Token may
Token ID743
Feature activation-2.33e+00

Pos logit contributions
hots+0.330
gang+0.289
 Scor+0.283
onga+0.283
hs+0.282
Neg logit contributions
arenthood-0.299
atism-0.278
udeb-0.272
emet-0.269
eve-0.268
Token allow
Token ID1249
Feature activation-2.65e+00

Pos logit contributions
hots+1.666
gang+1.440
 Scor+1.418
onga+1.416
hs+1.414
Neg logit contributions
arenthood-1.671
atism-1.560
udeb-1.532
emet-1.514
eve-1.504
Token us
Token ID514
Feature activation+2.24e+00

Pos logit contributions
hots+2.128
gang+1.873
 Scor+1.850
onga+1.841
hs+1.840
Neg logit contributions
arenthood-1.665
atism-1.539
udeb-1.503
emet-1.486
eve-1.473
Token statistics
Token ID7869
Feature activation-1.62e-01

Pos logit contributions
hots+2.152
gang+1.870
 Scor+1.842
onga+1.835
hs+1.834
Neg logit contributions
arenthood-2.045
atism-1.903
udeb-1.864
emet-1.845
eve-1.832
Token and
Token ID290
Feature activation-1.10e-01

Pos logit contributions
hots+0.125
gang+0.110
onga+0.109
 Scor+0.109
hs+0.107
Neg logit contributions
arenthood-0.106
atism-0.099
emet-0.096
udeb-0.095
eve-0.095
Token think
Token ID892
Feature activation+2.78e+00

Pos logit contributions
hots+0.082
gang+0.071
onga+0.070
 Scor+0.070
hs+0.069
Neg logit contributions
arenthood-0.075
atism-0.070
udeb-0.068
emet-0.068
eve-0.068
Token:
Token ID25
Feature activation+1.34e+00

Pos logit contributions
arenthood+1.737
atism+1.611
ativity+1.541
udeb+1.536
emet+1.534
Neg logit contributions
hots-2.222
onga-1.921
gang-1.918
 Scor-1.910
hs-1.901
Token "
Token ID366
Feature activation-1.68e+00

Pos logit contributions
arenthood+0.834
atism+0.775
udeb+0.746
emet+0.741
eve+0.738
Neg logit contributions
hots-1.073
gang-0.932
onga-0.932
hs-0.924
 Scor-0.912
TokenWell
Token ID5779
Feature activation-5.81e-01

Pos logit contributions
hots+1.282
gang+1.117
 Scor+1.108
onga+1.103
hs+1.098
Neg logit contributions
arenthood-1.113
atism-1.033
udeb-1.012
emet-1.000
eve-0.996
Token,
Token ID11
Feature activation-3.87e-01

Pos logit contributions
hots+0.444
gang+0.388
 Scor+0.382
onga+0.382
hs+0.380
Neg logit contributions
arenthood-0.387
atism-0.359
udeb-0.350
emet-0.347
eve-0.346
Token that
Token ID326
Feature activation-1.23e+00

Pos logit contributions
hots+0.294
gang+0.255
onga+0.252
hs+0.251
 Scor+0.250
Neg logit contributions
arenthood-0.259
atism-0.242
udeb-0.235
emet-0.233
eve-0.231
Token seems
Token ID2331
Feature activation-3.20e+00

Pos logit contributions
hots+0.945
gang+0.822
 Scor+0.811
onga+0.810
hs+0.806
Neg logit contributions
arenthood-0.819
atism-0.762
udeb-0.741
emet-0.735
eve-0.731
Token like
Token ID588
Feature activation-3.32e+00

Pos logit contributions
hots+2.377
gang+2.068
 Scor+2.038
onga+2.031
hs+2.031
Neg logit contributions
arenthood-2.200
atism-2.045
udeb-2.004
emet-1.983
eve-1.969
Token a
Token ID257
Feature activation-5.28e+00

Pos logit contributions
hots+2.415
gang+2.096
 Scor+2.065
hs+2.055
onga+2.054
Neg logit contributions
arenthood-2.342
atism-2.180
udeb-2.141
emet-2.115
eve-2.102
Token.
Token ID13
Feature activation-1.66e+00

Pos logit contributions
hots+2.604
gang+2.242
hs+2.215
 Scor+2.211
onga+2.205
Neg logit contributions
arenthood-2.673
atism-2.493
udeb-2.447
emet-2.417
eve-2.396
TokenFurthermore
Token ID24951
Feature activation-4.62e+00

Pos logit contributions
hots+1.205
gang+1.043
onga+1.027
 Scor+1.024
hs+1.021
Neg logit contributions
arenthood-1.173
atism-1.090
udeb-1.069
emet-1.058
eve-1.053
Token,
Token ID11
Feature activation+4.22e-01

Pos logit contributions
hots+3.216
gang+2.758
hs+2.740
onga+2.723
 Scor+2.721
Neg logit contributions
arenthood-3.311
atism-3.092
udeb-3.081
emet-3.012
eve-2.989
Token what
Token ID644
Feature activation-1.52e+00

Pos logit contributions
arenthood+0.286
atism+0.268
udeb+0.260
emet+0.258
eve+0.256
Neg logit contributions
hots-0.317
gang-0.276
onga-0.272
 Scor-0.271
hs-0.270
Token these
Token ID777
Feature activation-1.99e+00

Pos logit contributions
hots+1.151
gang+1.005
 Scor+0.988
onga+0.987
hs+0.985
Neg logit contributions
arenthood-1.027
atism-0.955
udeb-0.932
emet-0.924
eve-0.918
Token theorists
Token ID33142
Feature activation-1.85e+00

Pos logit contributions
hots+1.452
gang+1.264
 Scor+1.242
onga+1.241
hs+1.234
Neg logit contributions
arenthood-1.392
atism-1.298
udeb-1.267
emet-1.257
eve-1.250
Token ignore
Token ID8856
Feature activation-1.76e+00

Pos logit contributions
hots+1.376
gang+1.196
 Scor+1.179
hs+1.177
onga+1.175
Neg logit contributions
arenthood-1.274
atism-1.183
udeb-1.160
emet-1.148
eve-1.139
Token entirely
Token ID5000
Feature activation-1.98e+00

Pos logit contributions
hots+1.334
gang+1.167
 Scor+1.151
onga+1.147
hs+1.142
Neg logit contributions
arenthood-1.189
atism-1.106
udeb-1.077
emet-1.069
eve-1.061
Token is
Token ID318
Feature activation+1.07e+00

Pos logit contributions
hots+1.512
gang+1.323
 Scor+1.305
onga+1.300
hs+1.296
Neg logit contributions
arenthood-1.328
atism-1.233
udeb-1.203
emet-1.192
eve-1.185
Token that
Token ID326
Feature activation+2.95e-01

Pos logit contributions
arenthood+0.731
atism+0.680
udeb+0.658
emet+0.658
eve+0.653
Neg logit contributions
hots-0.792
gang-0.694
 Scor-0.682
onga-0.680
hs-0.675
Token the
Token ID262
Feature activation-1.04e+00

Pos logit contributions
arenthood+0.198
atism+0.185
udeb+0.178
emet+0.178
eve+0.177
Neg logit contributions
hots-0.223
gang-0.195
onga-0.192
 Scor-0.191
hs-0.190
Tokenstop
Token ID11338
Feature activation+5.15e-01

Pos logit contributions
hots+1.544
gang+1.332
 Scor+1.326
onga+1.306
hs+1.305
Neg logit contributions
arenthood-1.690
atism-1.595
udeb-1.557
emet-1.531
eve-1.521
Token awesome
Token ID7427
Feature activation-1.11e+00

Pos logit contributions
arenthood+0.350
atism+0.324
udeb+0.317
emet+0.315
eve+0.314
Neg logit contributions
hots-0.384
gang-0.336
onga-0.331
 Scor-0.330
hs-0.329
Token grappling
Token ID36762
Feature activation-2.80e+00

Pos logit contributions
hots+0.816
gang+0.710
 Scor+0.699
onga+0.697
hs+0.696
Neg logit contributions
arenthood-0.774
atism-0.720
udeb-0.706
emet-0.698
eve-0.694
Token hook
Token ID8011
Feature activation-1.55e+00

Pos logit contributions
hots+2.031
gang+1.754
 Scor+1.729
onga+1.723
hs+1.722
Neg logit contributions
arenthood-1.981
atism-1.844
udeb-1.808
emet-1.789
eve-1.772
Token aw
Token ID3253
Feature activation+5.64e-01

Pos logit contributions
hots+1.132
gang+0.985
 Scor+0.970
onga+0.966
hs+0.965
Neg logit contributions
arenthood-1.080
atism-1.005
udeb-0.985
emet-0.975
eve-0.969
Tokenes
Token ID274
Feature activation-1.16e+01

Pos logit contributions
arenthood+0.351
atism+0.323
udeb+0.318
emet+0.314
eve+0.313
Neg logit contributions
hots-0.454
gang-0.401
 Scor-0.395
onga-0.392
hs-0.390
Tokenomen
Token ID3674
Feature activation-1.17e+01

Pos logit contributions
hots+5.989
la+4.699
onga+4.691
hs+4.669
gang+4.631
Neg logit contributions
arenthood-9.820
atism-9.219
udeb-9.186
eve-9.180
 Nept-9.085
Tokeness
Token ID408
Feature activation-2.00e+00

Pos logit contributions
hots+8.402
onga+7.278
gang+7.245
hs+7.107
la+7.101
Neg logit contributions
arenthood-7.742
atism-7.239
 Nept-7.027
ativity-6.915
utenberg-6.871
Token!
Token ID0
Feature activation-3.13e+00

Pos logit contributions
hots+1.457
gang+1.260
 Scor+1.243
onga+1.237
hs+1.237
Neg logit contributions
arenthood-1.408
atism-1.311
udeb-1.282
emet-1.271
eve-1.260
Token Having
Token ID11136
Feature activation+1.49e+00

Pos logit contributions
hots+2.306
gang+2.008
 Scor+1.985
hs+1.970
onga+1.964
Neg logit contributions
arenthood-2.172
atism-2.024
udeb-1.964
emet-1.955
eve-1.931
Token done
Token ID1760
Feature activation-3.74e-01

Pos logit contributions
arenthood+0.963
atism+0.891
udeb+0.876
eve+0.874
emet+0.868
Neg logit contributions
hots-1.149
gang-1.009
onga-0.997
hs-0.987
 Scor-0.983
TokenWa
Token ID33484
Feature activation-5.20e+00

Pos logit contributions
arenthood+0.776
atism+0.720
udeb+0.713
eve+0.711
emet+0.706
Neg logit contributions
hots-0.774
 Scor-0.664
gang-0.661
onga-0.654
hs-0.641
Tokenub
Token ID549
Feature activation-1.07e+01

Pos logit contributions
hots+4.733
gang+4.239
onga+4.207
hs+4.203
la+4.111
Neg logit contributions
arenthood-2.666
atism-2.422
emet-2.311
udeb-2.290
eve-2.267
Tokenges
Token ID3212
Feature activation-2.54e+00

Pos logit contributions
hots+7.593
hs+6.839
gang+6.768
la+6.350
zb+6.336
Neg logit contributions
arenthood-7.123
atism-6.841
udeb-6.636
emet-6.521
 Nept-6.510
Tokenhig
Token ID25196
Feature activation-4.39e+00

Pos logit contributions
hots+1.247
gang+1.003
 Scor+0.976
onga+0.973
hs+0.972
Neg logit contributions
arenthood-2.395
atism-2.272
udeb-2.237
emet-2.221
eve-2.210
Token Rice
Token ID13823
Feature activation-3.68e+00

Pos logit contributions
hots+2.356
gang+1.956
 Scor+1.948
hs+1.911
onga+1.875
Neg logit contributions
arenthood-3.876
atism-3.713
udeb-3.630
emet-3.624
eve-3.552
Token/
Token ID14
Feature activation-7.94e+00

Pos logit contributions
hots+2.213
gang+1.872
 Scor+1.831
hs+1.831
onga+1.813
Neg logit contributions
arenthood-3.035
atism-2.871
udeb-2.813
emet-2.795
eve-2.753
TokenCBC
Token ID29208
Feature activation-1.04e-01

Pos logit contributions
hots+3.794
gang+3.157
hs+3.061
la+2.958
onga+2.906
Neg logit contributions
arenthood-7.221
atism-6.986
ativity-6.753
udeb-6.743
emet-6.724
Token)
Token ID8
Feature activation-2.18e+00

Pos logit contributions
hots+0.062
gang+0.052
onga+0.051
 Scor+0.051
hs+0.051
Neg logit contributions
arenthood-0.086
atism-0.081
udeb-0.080
emet-0.079
eve-0.079
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
hots+1.649
gang+1.437
 Scor+1.412
onga+1.411
hs+1.409
Neg logit contributions
arenthood-1.478
atism-1.371
udeb-1.341
emet-1.329
eve-1.322
Token
Token ID198
Feature activation-1.76e+00

Pos logit contributions
hots+0.764
gang+0.662
 Scor+0.653
onga+0.651
hs+0.648
Neg logit contributions
arenthood-0.741
atism-0.689
udeb-0.676
emet-0.669
eve-0.666
TokenInsp
Token ID41502
Feature activation-1.75e+00

Pos logit contributions
hots+1.292
gang+1.119
 Scor+1.108
onga+1.100
hs+1.097
Neg logit contributions
arenthood-1.234
atism-1.147
udeb-1.126
emet-1.114
eve-1.113
Token.
Token ID13
Feature activation-5.85e-01

Pos logit contributions
hots+1.516
gang+1.310
hs+1.285
 Scor+1.279
onga+1.274
Neg logit contributions
arenthood-1.498
atism-1.400
udeb-1.376
emet-1.358
eve-1.342
Tokenw
Token ID86
Feature activation+3.51e-02

Pos logit contributions
hots+0.495
gang+0.438
 Scor+0.432
onga+0.431
hs+0.431
Neg logit contributions
arenthood-0.342
atism-0.314
udeb-0.306
emet-0.302
eve-0.300
Tokenbur
Token ID6236
Feature activation-3.20e+00

Pos logit contributions
arenthood+0.024
atism+0.022
udeb+0.021
emet+0.021
eve+0.021
Neg logit contributions
hots-0.027
gang-0.023
 Scor-0.023
onga-0.023
hs-0.023
Token.
Token ID13
Feature activation-2.81e+00

Pos logit contributions
hots+2.311
gang+2.013
hs+2.003
onga+1.981
 Scor+1.951
Neg logit contributions
arenthood-2.243
atism-2.089
udeb-2.050
emet-2.027
eve-2.011
Tokenorg
Token ID2398
Feature activation-6.37e+00

Pos logit contributions
hots+2.283
gang+2.009
hs+1.985
 Scor+1.964
onga+1.963
Neg logit contributions
arenthood-1.744
atism-1.604
udeb-1.577
emet-1.552
eve-1.532
Token/
Token ID14
Feature activation-9.04e+00

Pos logit contributions
hots+3.881
gang+3.241
hs+3.218
 Scor+3.217
onga+3.115
Neg logit contributions
arenthood-5.115
atism-4.873
udeb-4.816
emet-4.702
ativity-4.670
Token2015
Token ID4626
Feature activation-4.22e+00

Pos logit contributions
hots+6.528
gang+5.628
hs+5.618
la+5.477
 Scor+5.435
Neg logit contributions
arenthood-6.125
atism-5.723
udeb-5.703
ativity-5.543
emet-5.488
Token/
Token ID14
Feature activation-3.39e+00

Pos logit contributions
hots+2.443
gang+2.062
hs+2.018
 Scor+1.997
onga+1.957
Neg logit contributions
arenthood-3.543
atism-3.381
udeb-3.329
emet-3.274
ativity-3.250
Token08
Token ID2919
Feature activation-3.50e+00

Pos logit contributions
hots+2.643
gang+2.325
hs+2.284
 Scor+2.277
onga+2.269
Neg logit contributions
arenthood-2.209
atism-2.045
udeb-2.001
emet-1.979
eve-1.952
Token/
Token ID14
Feature activation-8.21e+00

Pos logit contributions
hots+2.056
gang+1.740
hs+1.706
 Scor+1.678
la+1.660
Neg logit contributions
arenthood-2.940
atism-2.791
udeb-2.730
emet-2.718
ativity-2.680
Token11
Token ID1157
Feature activation-2.62e+00

Pos logit contributions
hots+5.588
gang+4.957
hs+4.854
la+4.767
onga+4.640
Neg logit contributions
arenthood-5.847
atism-5.545
udeb-5.426
 Nept-5.376
emet-5.336
Token Av
Token ID5184
Feature activation-1.88e+00

Pos logit contributions
hots+1.637
gang+1.422
 Scor+1.400
onga+1.396
hs+1.394
Neg logit contributions
arenthood-1.550
atism-1.442
udeb-1.413
emet-1.399
eve-1.391
Tokenarg
Token ID853
Feature activation+3.91e-01

Pos logit contributions
hots+1.401
gang+1.221
 Scor+1.200
onga+1.200
hs+1.198
Neg logit contributions
arenthood-1.291
atism-1.199
udeb-1.174
emet-1.162
eve-1.154
Tokenues
Token ID947
Feature activation-9.68e-01

Pos logit contributions
arenthood+0.267
atism+0.248
udeb+0.244
emet+0.243
eve+0.239
Neg logit contributions
hots-0.292
gang-0.254
 Scor-0.252
onga-0.248
hs-0.248
Token-
Token ID12
Feature activation-1.29e+00

Pos logit contributions
hots+0.724
gang+0.631
 Scor+0.624
hs+0.618
onga+0.616
Neg logit contributions
arenthood-0.659
atism-0.613
udeb-0.602
emet-0.597
eve-0.593
TokenWe
Token ID1135
Feature activation-9.59e-01

Pos logit contributions
hots+0.941
gang+0.816
 Scor+0.805
onga+0.802
hs+0.799
Neg logit contributions
arenthood-0.905
atism-0.842
udeb-0.828
emet-0.819
eve-0.814
Tokenber
Token ID527
Feature activation-7.80e+00

Pos logit contributions
hots+0.649
gang+0.556
 Scor+0.550
onga+0.545
hs+0.542
Neg logit contributions
arenthood-0.723
atism-0.676
udeb-0.666
emet-0.659
eve-0.656
Token (
Token ID357
Feature activation-2.33e-01

Pos logit contributions
hots+5.728
gang+5.046
onga+4.965
hs+4.954
la+4.920
Neg logit contributions
arenthood-5.279
atism-4.855
udeb-4.829
emet-4.725
eve-4.666
TokenUn
Token ID3118
Feature activation-1.42e+00

Pos logit contributions
hots+0.167
gang+0.144
 Scor+0.143
onga+0.141
hs+0.140
Neg logit contributions
arenthood-0.166
atism-0.155
udeb-0.152
emet-0.151
eve-0.151
Tokenivers
Token ID1191
Feature activation-1.39e+00

Pos logit contributions
hots+1.266
gang+1.127
 Scor+1.118
onga+1.111
hs+1.105
Neg logit contributions
arenthood-0.773
atism-0.705
udeb-0.686
emet-0.678
eve-0.674
Tokenité
Token ID43816
Feature activation+2.14e+00

Pos logit contributions
hots+0.920
gang+0.786
 Scor+0.773
onga+0.770
hs+0.767
Neg logit contributions
arenthood-1.071
atism-1.004
udeb-0.984
emet-0.976
eve-0.969
Token de
Token ID390
Feature activation-4.97e+00

Pos logit contributions
arenthood+1.515
atism+1.409
 Nept+1.371
udeb+1.370
eve+1.362
Neg logit contributions
hots-1.522
gang-1.329
onga-1.307
 Scor-1.259
oused-1.254
Token grown
Token ID7334
Feature activation-1.23e-01

Pos logit contributions
hots+1.296
gang+1.125
 Scor+1.108
hs+1.104
onga+1.103
Neg logit contributions
arenthood-1.248
atism-1.162
udeb-1.138
emet-1.126
eve-1.119
Token from
Token ID422
Feature activation-4.44e+00

Pos logit contributions
hots+0.093
gang+0.081
onga+0.080
 Scor+0.080
hs+0.079
Neg logit contributions
arenthood-0.082
atism-0.076
udeb-0.074
eve-0.074
emet-0.074
Token a
Token ID257
Feature activation-3.33e+00

Pos logit contributions
hots+3.296
gang+2.875
 Scor+2.873
hs+2.848
onga+2.810
Neg logit contributions
arenthood-3.038
atism-2.789
udeb-2.746
emet-2.703
eve-2.678
Token single
Token ID2060
Feature activation-1.20e+00

Pos logit contributions
hots+2.545
gang+2.237
 Scor+2.213
hs+2.206
onga+2.192
Neg logit contributions
arenthood-2.210
atism-2.039
udeb-1.989
emet-1.964
eve-1.958
Token congregation
Token ID28862
Feature activation-8.23e-01

Pos logit contributions
hots+0.902
gang+0.786
 Scor+0.775
onga+0.773
hs+0.772
Neg logit contributions
arenthood-0.814
atism-0.756
udeb-0.740
emet-0.732
eve-0.727
Token to
Token ID284
Feature activation-7.91e+00

Pos logit contributions
hots+0.601
gang+0.520
onga+0.513
 Scor+0.513
hs+0.509
Neg logit contributions
arenthood-0.577
atism-0.537
udeb-0.526
emet-0.522
eve-0.519
Token embrace
Token ID12553
Feature activation-2.58e+00

Pos logit contributions
hots+5.261
gang+4.504
 Scor+4.468
hs+4.451
onga+4.425
Neg logit contributions
arenthood-5.791
udeb-5.391
atism-5.377
emet-5.280
eve-5.267
Token millions
Token ID5242
Feature activation-1.04e-02

Pos logit contributions
hots+1.908
gang+1.659
 Scor+1.639
hs+1.628
onga+1.628
Neg logit contributions
arenthood-1.776
atism-1.648
udeb-1.620
emet-1.602
eve-1.587
Token.
Token ID13
Feature activation-2.43e-01

Pos logit contributions
hots+0.008
gang+0.007
onga+0.007
 Scor+0.007
hs+0.007
Neg logit contributions
arenthood-0.007
atism-0.007
udeb-0.007
emet-0.006
eve-0.006
Token Today
Token ID6288
Feature activation-1.94e-01

Pos logit contributions
hots+0.179
gang+0.155
onga+0.153
hs+0.152
 Scor+0.152
Neg logit contributions
arenthood-0.168
atism-0.156
udeb-0.153
emet-0.151
eve-0.151
Token Br
Token ID1709
Feature activation+2.37e-01

Pos logit contributions
hots+0.147
gang+0.128
 Scor+0.126
onga+0.125
hs+0.125
Neg logit contributions
arenthood-0.131
atism-0.121
udeb-0.118
emet-0.117
eve-0.117