TOP ACTIVATIONS
MAX = 3.236

is one of the st aun chest supporters of Trump 's
morning 's prices were a bubble is ultimately a prediction about
In the months before the IPO , Black fish
be regarded as a pand emic but wanted clear evidence before
News 24 . Topics : beef - c attle
so rapidly ? Though the boom in global commodity prices played
Hay es , at the Sud z ha pumping station on
a full - blown pand emic . SW INE FL U
and the Paradox of Credit Bub bles , Equity and Demand
45 366 . Topics : community - and -
activists protesting the theft of earthquake aid & pill age of
T Secrets St James in Monte go Bay from £ 1
we are in a pand emic situation ," he said .
tad pole had just a tail I sold ' em for
into them ". Topics : marine - biology ,
support the mission of New Advent and get the full contents
problem is that the pand emic phase system is designed for
that she was pressing for Jun cker to take the reins
We 're hoping that he sur rend ers ," the police
5 years on the housing bubble / b ust :

MIN ACTIVATIONS
MIN = -2.799

star ( Sh rav ana Nak sh tra ) these p
a number of things to argue with in Reed
, r ' \ [ +( \ S + )\ s
] :: From Ar gb ($ BG [ 0 ], $
look up from the bridge ) I
know this was a totally biased decision , was the fact
Results and achievements [ edit ] The ion
in the first quarter to lobby on domestic spying legislation and
Indeed , about an hour before the festivities started at
string format Switch ($ Al ign ) { Center { $
More than an hour before kick - off Bruce
miles . Eas ily the hardest day of the trip ,
a chief of B ani Nad ir and Saf iyah
Soviets , Lad isl av Sm ol j ak
cancer and one of the hardest things I have dealt with
! Bob bi Krist ina celebrates Whitney Houston 's
1 - 0 [ Event " 78 th Tata Steel Chess
( 0 , 0 , ($ SR . Width ), ($
the bye week , because Jord y Nelson awaits .
neurons activated . Krist ofer B ouch ard ,

INTERVAL 1.727 - 3.236
CONTAINS 0.202%

a premiere ninja in the Foot , and as a reward
option adopted by Pu ig dem ont and his
insofar as mobile teachers are short changed by teacher pensions .
In Public - Writ ters Strike 2008 01 04 O &
electing a president would be indul ging in the very reflex

INTERVAL 0.219 - 1.727
CONTAINS 33.559%

from an interpretation of the word d isson ant
trade asset . And the Padres should have left him alone
rates , or at a refresh rate more likely achieved during
Why don t you trust women to make this
, transparency , sound st aging , and surprising bass response

INTERVAL -1.290 - 0.219
CONTAINS 64.862%

of the galaxy , and the Milky Way is at least
your wife is the kind of sweet heart who loves you
established notions of what constitutes the middle class , rather than
with homelessness . No single system tracks street people
were going to pit a city ordinance against human rights ,

INTERVAL -2.799 - -1.290
CONTAINS 1.377%

which includes additional instructions for ensuring compatibility with V OD services
stri ps runner - up Israel ( at 4 . 11
rounds of ammunition that disappeared last week have been located .
that this has made it harder for screen ers to identify
. An example is below ( select category --> drill through
Token is
Token ID318
Feature activation-1.93e-01

Pos logit contributions
ANE+0.906
awan+0.870
+0.855
 srf+0.848
UA+0.846
Neg logit contributions
ertodd-0.812
ysis-0.640
verts-0.606
ered-0.604
 quo-0.595
Token one
Token ID530
Feature activation+7.73e-01

Pos logit contributions
ANE+0.612
awan+0.587
+0.581
 srf+0.576
UA+0.571
Neg logit contributions
ertodd-0.526
ysis-0.416
verts-0.396
ered-0.396
 quo-0.392
Token of
Token ID286
Feature activation+1.03e+00

Pos logit contributions
ertodd+2.178
ysis+1.717
ered+1.628
verts+1.625
 quo+1.600
Neg logit contributions
ANE-2.397
awan-2.305
-2.263
UA-2.238
-2.234
Token the
Token ID262
Feature activation+4.49e-01

Pos logit contributions
ertodd+2.648
ysis+2.070
ered+1.980
verts+1.958
 Jehovah+1.952
Neg logit contributions
ANE-3.410
awan-3.274
-3.240
 srf-3.210
-3.201
Token st
Token ID336
Feature activation+1.42e-01

Pos logit contributions
ertodd+1.401
ysis+1.138
verts+1.101
ered+1.098
 quo+1.082
Neg logit contributions
ANE-1.252
awan-1.196
-1.181
 srf-1.166
UA-1.163
Tokenaun
Token ID1942
Feature activation+3.24e+00

Pos logit contributions
ertodd+0.287
ysis+0.203
verts+0.186
ered+0.185
 quo+0.180
Neg logit contributions
ANE-0.552
awan-0.535
-0.527
UA-0.523
-0.523
Tokenchest
Token ID46713
Feature activation-9.99e-01

Pos logit contributions
ertodd+8.057
verts+6.771
ered+6.764
ysis+6.579
 quo+6.488
Neg logit contributions
ANE-10.008
-9.340
senal-9.227
UA-9.208
awan-9.151
Token supporters
Token ID5941
Feature activation+9.52e-02

Pos logit contributions
ANE+3.069
awan+2.951
+2.896
UA+2.877
+2.865
Neg logit contributions
ertodd-2.848
ysis-2.231
ered-2.099
verts-2.096
 quo-2.057
Token of
Token ID286
Feature activation-2.19e-01

Pos logit contributions
ertodd+0.279
ysis+0.222
verts+0.211
ered+0.209
 quo+0.205
Neg logit contributions
ANE-0.286
awan-0.274
-0.269
UA-0.267
-0.267
Token Trump
Token ID1301
Feature activation-1.50e-01

Pos logit contributions
ANE+0.752
awan+0.726
+0.713
UA+0.708
+0.706
Neg logit contributions
ertodd-0.547
ysis-0.416
verts-0.389
ered-0.386
 quo-0.378
Token's
Token ID338
Feature activation+1.94e-01

Pos logit contributions
ANE+0.425
awan+0.406
+0.397
UA+0.394
 srf+0.393
Neg logit contributions
ertodd-0.466
ysis-0.377
verts-0.360
ered-0.359
 quo-0.355
Token morning
Token ID3329
Feature activation+5.02e-02

Pos logit contributions
ANE+2.722
awan+2.611
+2.554
+2.522
UA+2.522
Neg logit contributions
ertodd-3.016
ysis-2.462
verts-2.326
ered-2.299
 quo-2.280
Token's
Token ID338
Feature activation+9.99e-01

Pos logit contributions
ertodd+0.140
ysis+0.110
verts+0.105
ered+0.105
 quo+0.103
Neg logit contributions
ANE-0.157
awan-0.151
-0.148
 srf-0.147
UA-0.147
Token prices
Token ID4536
Feature activation+1.96e+00

Pos logit contributions
ertodd+2.835
ysis+2.218
ered+2.130
verts+2.130
 quo+2.116
Neg logit contributions
ANE-3.034
awan-2.952
 srf-2.912
-2.887
-2.873
Token were
Token ID547
Feature activation+3.84e-01

Pos logit contributions
ertodd+4.638
ysis+3.616
 quo+3.521
ered+3.483
verts+3.390
Neg logit contributions
ANE-6.573
 srf-6.437
awan-6.406
senal-6.369
-6.292
Token a
Token ID257
Feature activation+1.01e+00

Pos logit contributions
ertodd+1.105
ysis+0.891
ered+0.860
 quo+0.858
verts+0.852
Neg logit contributions
ANE-1.145
awan-1.105
-1.092
 srf-1.088
-1.078
Token bubble
Token ID14310
Feature activation+3.13e+00

Pos logit contributions
ertodd+2.935
ysis+2.369
ered+2.307
verts+2.288
 quo+2.288
Neg logit contributions
ANE-2.947
awan-2.860
-2.820
 srf-2.812
UA-2.799
Token is
Token ID318
Feature activation-6.53e-01

Pos logit contributions
ertodd+7.876
ered+6.152
 quo+5.988
verts+5.902
ysis+5.800
Neg logit contributions
ANE-9.843
senal-9.533
 srf-9.519
awan-9.450
-9.276
Token ultimately
Token ID6165
Feature activation-5.46e-01

Pos logit contributions
ANE+1.842
awan+1.764
+1.726
UA+1.709
+1.706
Neg logit contributions
ertodd-2.029
ysis-1.642
verts-1.563
ered-1.557
 quo-1.535
Token a
Token ID257
Feature activation+3.17e-01

Pos logit contributions
ANE+1.433
awan+1.368
+1.335
UA+1.321
 srf+1.321
Neg logit contributions
ertodd-1.802
ysis-1.482
verts-1.417
ered-1.415
 quo-1.395
Token prediction
Token ID17724
Feature activation+3.53e-01

Pos logit contributions
ertodd+1.036
ysis+0.854
ered+0.829
verts+0.828
 quo+0.818
Neg logit contributions
ANE-0.831
awan-0.793
 srf-0.774
-0.773
UA-0.770
Token about
Token ID546
Feature activation+1.49e-01

Pos logit contributions
ertodd+1.030
ysis+0.833
ered+0.811
 quo+0.798
verts+0.798
Neg logit contributions
ANE-1.049
awan-1.004
 srf-0.990
-0.982
-0.975
TokenIn
Token ID818
Feature activation+7.87e-01

Pos logit contributions
ANE+0.463
 srf+0.450
awan+0.445
senal+0.432
+0.429
Neg logit contributions
ertodd-0.738
ysis-0.622
verts-0.605
ered-0.603
 quo-0.588
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
ertodd+2.076
ysis+1.612
verts+1.555
ered+1.526
 quo+1.491
Neg logit contributions
ANE-2.552
awan-2.465
-2.433
 srf-2.417
-2.409
Token months
Token ID1933
Feature activation-4.68e-01

Pos logit contributions
ertodd+0.353
ysis+0.286
verts+0.274
ered+0.272
 quo+0.268
Neg logit contributions
ANE-0.334
awan-0.320
-0.315
-0.312
UA-0.311
Token before
Token ID878
Feature activation-7.92e-01

Pos logit contributions
ANE+1.276
awan+1.221
+1.194
UA+1.182
+1.180
Neg logit contributions
ertodd-1.495
ysis-1.219
verts-1.162
ered-1.159
 quo-1.143
Token the
Token ID262
Feature activation+5.79e-01

Pos logit contributions
ANE+2.491
awan+2.396
+2.347
UA+2.334
EMENT+2.321
Neg logit contributions
ertodd-2.209
ysis-1.725
verts-1.627
ered-1.620
 quo-1.595
Token IPO
Token ID41805
Feature activation+2.94e+00

Pos logit contributions
ertodd+1.686
ysis+1.370
verts+1.310
ered+1.297
 Jehovah+1.292
Neg logit contributions
ANE-1.700
awan-1.637
-1.608
-1.608
 srf-1.604
Token,
Token ID11
Feature activation-1.83e-01

Pos logit contributions
ertodd+7.542
ered+6.012
ysis+5.952
verts+5.835
 Rupert+5.821
Neg logit contributions
ANE-8.619
 srf-8.571
awan-8.347
-8.278
 adolesc-8.183
Token
Token ID564
Feature activation-1.18e+00

Pos logit contributions
ANE+0.522
awan+0.501
+0.490
+0.485
UA+0.485
Neg logit contributions
ertodd-0.563
ysis-0.455
verts-0.433
ered-0.431
 quo-0.425
Token
Token ID250
Feature activation+2.87e-02

Pos logit contributions
ANE+2.195
awan+2.072
+2.007
+1.995
RAW+1.976
Neg logit contributions
ertodd-4.733
ysis-4.030
verts-3.902
ered-3.857
 quo-3.833
TokenBlack
Token ID9915
Feature activation-3.72e-01

Pos logit contributions
ertodd+0.097
ysis+0.080
ered+0.077
verts+0.076
 quo+0.075
Neg logit contributions
ANE-0.074
awan-0.070
-0.068
 srf-0.068
UA-0.067
Tokenfish
Token ID11084
Feature activation+3.16e-01

Pos logit contributions
ANE+0.844
awan+0.800
+0.778
 srf+0.769
UA+0.766
Neg logit contributions
ertodd-1.363
ysis-1.143
verts-1.098
ered-1.097
 quo-1.081
Token be
Token ID307
Feature activation+5.21e-02

Pos logit contributions
ertodd+0.931
ysis+0.718
ered+0.685
verts+0.677
 quo+0.665
Neg logit contributions
ANE-1.216
awan-1.172
-1.157
UA-1.150
 srf-1.144
Token regarded
Token ID11987
Feature activation+1.06e+00

Pos logit contributions
ertodd+0.143
ysis+0.115
ered+0.111
verts+0.109
 quo+0.108
Neg logit contributions
ANE-0.163
awan-0.157
-0.154
 srf-0.154
UA-0.152
Token as
Token ID355
Feature activation+5.72e-01

Pos logit contributions
ertodd+2.949
ysis+2.383
ered+2.291
verts+2.240
 quo+2.238
Neg logit contributions
ANE-3.242
awan-3.105
 srf-3.064
-3.062
UA-3.039
Token a
Token ID257
Feature activation+6.37e-01

Pos logit contributions
ertodd+1.563
ysis+1.248
ered+1.194
verts+1.181
 quo+1.172
Neg logit contributions
ANE-1.796
awan-1.731
-1.708
 srf-1.694
UA-1.690
Token pand
Token ID19798
Feature activation+2.10e+00

Pos logit contributions
ertodd+1.838
ysis+1.494
ered+1.435
verts+1.420
 quo+1.401
Neg logit contributions
ANE-1.897
awan-1.826
-1.804
UA-1.791
 srf-1.782
Tokenemic
Token ID5314
Feature activation+2.78e+00

Pos logit contributions
ertodd+3.636
ered+2.599
ysis+2.562
verts+2.190
 quo+1.971
Neg logit contributions
 srf-8.550
ANE-8.512
senal-8.401
-8.237
-8.213
Token but
Token ID475
Feature activation-1.38e-01

Pos logit contributions
ertodd+7.188
ysis+6.198
ered+6.155
 quo+5.924
verts+5.877
Neg logit contributions
ANE-7.850
 srf-7.769
awan-7.699
-7.680
senal-7.627
Token wanted
Token ID2227
Feature activation+5.36e-01

Pos logit contributions
ANE+0.441
awan+0.425
+0.417
UA+0.413
+0.413
Neg logit contributions
ertodd-0.379
ysis-0.297
verts-0.280
ered-0.279
 quo-0.274
Token clear
Token ID1598
Feature activation-2.44e-01

Pos logit contributions
ertodd+1.598
ysis+1.305
ered+1.240
verts+1.237
 quo+1.218
Neg logit contributions
ANE-1.547
awan-1.485
-1.463
 srf-1.453
UA-1.446
Token evidence
Token ID2370
Feature activation+4.03e-01

Pos logit contributions
ANE+0.748
awan+0.719
+0.705
UA+0.699
+0.698
Neg logit contributions
ertodd-0.700
ysis-0.552
verts-0.522
ered-0.519
 quo-0.511
Token before
Token ID878
Feature activation-5.76e-01

Pos logit contributions
ertodd+1.155
ysis+0.943
ered+0.898
verts+0.891
 quo+0.883
Neg logit contributions
ANE-1.205
awan-1.162
-1.138
 srf-1.135
UA-1.126
Token News
Token ID3000
Feature activation+3.31e-01

Pos logit contributions
ertodd+1.948
ysis+1.629
verts+1.571
ered+1.559
 Jehovah+1.521
Neg logit contributions
ANE-1.849
awan-1.807
-1.765
 srf-1.760
-1.748
Token 24
Token ID1987
Feature activation+7.08e-01

Pos logit contributions
ertodd+0.959
ysis+0.780
verts+0.753
ered+0.747
 quo+0.732
Neg logit contributions
ANE-0.960
awan-0.925
-0.911
-0.910
 srf-0.906
Token.
Token ID13
Feature activation+7.82e-01

Pos logit contributions
ertodd+2.108
ysis+1.757
verts+1.707
ered+1.691
 Jehovah+1.644
Neg logit contributions
ANE-1.962
awan-1.890
-1.865
-1.848
 srf-1.844
Token
Token ID198
Feature activation+4.27e-01

Pos logit contributions
ertodd+2.014
ysis+1.583
verts+1.522
ered+1.498
 quo+1.466
Neg logit contributions
ANE-2.529
awan-2.455
-2.415
 srf-2.415
-2.391
Token
Token ID198
Feature activation-1.60e-01

Pos logit contributions
ertodd+1.040
ysis+0.791
ered+0.756
verts+0.754
 quo+0.727
Neg logit contributions
ANE-1.475
 srf-1.444
senal-1.428
awan-1.421
-1.405
TokenTopics
Token ID25902
Feature activation+2.77e+00

Pos logit contributions
ANE+0.493
awan+0.477
 srf+0.469
+0.467
+0.463
Neg logit contributions
ertodd-0.450
ysis-0.357
verts-0.342
ered-0.340
 quo-0.332
Token:
Token ID25
Feature activation+5.45e-01

Pos logit contributions
ertodd+6.490
ered+5.036
verts+4.764
ysis+4.720
 Rupert+4.659
Neg logit contributions
 srf-9.565
senal-9.532
 adolesc-9.120
ANE-9.097
awan-8.802
Token beef
Token ID12023
Feature activation-3.13e-02

Pos logit contributions
ertodd+1.409
ysis+1.107
ered+1.048
verts+1.047
 quo+1.040
Neg logit contributions
ANE-1.795
awan-1.720
-1.699
UA-1.691
 srf-1.678
Token-
Token ID12
Feature activation-4.27e-01

Pos logit contributions
ANE+0.089
awan+0.086
+0.084
UA+0.083
EMENT+0.083
Neg logit contributions
ertodd-0.096
ysis-0.078
verts-0.074
ered-0.073
 quo-0.073
Tokenc
Token ID66
Feature activation-7.69e-01

Pos logit contributions
ANE+1.160
awan+1.106
+1.086
UA+1.072
 srf+1.070
Neg logit contributions
ertodd-1.370
ysis-1.117
verts-1.068
ered-1.064
 quo-1.047
Tokenattle
Token ID1999
Feature activation+6.23e-01

Pos logit contributions
ANE+2.324
awan+2.270
UA+2.176
RAW+2.175
+2.171
Neg logit contributions
ertodd-2.218
ysis-1.734
 quo-1.650
verts-1.641
ered-1.623
Token so
Token ID523
Feature activation-9.37e-03

Pos logit contributions
ertodd+2.884
ysis+2.355
ered+2.265
 quo+2.262
verts+2.245
Neg logit contributions
ANE-2.484
awan-2.378
 srf-2.327
senal-2.321
-2.318
Token rapidly
Token ID8902
Feature activation-1.72e-03

Pos logit contributions
ANE+0.028
awan+0.026
 srf+0.026
+0.026
+0.026
Neg logit contributions
ertodd-0.028
ysis-0.022
ered-0.021
verts-0.021
 quo-0.021
Token?
Token ID30
Feature activation+4.49e-01

Pos logit contributions
ANE+0.004
awan+0.004
+0.004
UA+0.004
+0.004
Neg logit contributions
ertodd-0.006
ysis-0.005
verts-0.004
ered-0.004
 quo-0.004
Token Though
Token ID7486
Feature activation-3.44e-01

Pos logit contributions
ertodd+1.210
ysis+0.952
verts+0.909
ered+0.908
 quo+0.888
Neg logit contributions
ANE-1.428
awan-1.381
 srf-1.372
-1.349
-1.340
Token the
Token ID262
Feature activation+1.61e-01

Pos logit contributions
ANE+1.077
awan+1.037
+1.017
UA+1.007
+1.006
Neg logit contributions
ertodd-0.961
ysis-0.755
verts-0.710
ered-0.705
 quo-0.692
Token boom
Token ID14166
Feature activation+2.76e+00

Pos logit contributions
ertodd+0.470
ysis+0.377
verts+0.357
ered+0.356
 quo+0.352
Neg logit contributions
ANE-0.482
awan-0.462
-0.453
UA-0.449
-0.449
Token in
Token ID287
Feature activation+6.85e-01

Pos logit contributions
ertodd+7.098
ered+5.858
ysis+5.539
 quo+5.493
verts+5.366
Neg logit contributions
ANE-8.320
 srf-8.118
awan-7.976
senal-7.922
UA-7.906
Token global
Token ID3298
Feature activation+4.99e-01

Pos logit contributions
ertodd+1.933
ysis+1.546
verts+1.477
ered+1.467
 quo+1.451
Neg logit contributions
ANE-2.091
awan-2.008
 srf-1.977
-1.977
UA-1.962
Token commodity
Token ID19464
Feature activation+8.91e-01

Pos logit contributions
ertodd+1.450
ysis+1.168
ered+1.107
verts+1.107
 quo+1.088
Neg logit contributions
ANE-1.494
awan-1.437
-1.407
 srf-1.405
UA-1.395
Token prices
Token ID4536
Feature activation+2.10e+00

Pos logit contributions
ertodd+2.377
ysis+1.886
verts+1.818
ered+1.810
 quo+1.784
Neg logit contributions
ANE-2.842
awan-2.740
 srf-2.688
-2.659
-2.646
Token played
Token ID2826
Feature activation+1.13e+00

Pos logit contributions
ertodd+5.424
ysis+4.313
ered+4.301
 quo+4.245
verts+4.140
Neg logit contributions
ANE-6.637
senal-6.506
 srf-6.447
awan-6.304
UA-6.164
TokenHay
Token ID31306
Feature activation+1.59e+00

Pos logit contributions
ANE+1.231
awan+1.159
+1.131
+1.112
 srf+1.108
Neg logit contributions
ertodd-2.363
ysis-2.002
verts-1.940
ered-1.929
 quo-1.905
Tokenes
Token ID274
Feature activation+7.32e-01

Pos logit contributions
ertodd+4.247
verts+3.301
ered+3.277
ysis+3.243
 quo+3.163
Neg logit contributions
ANE-5.066
 srf-4.910
-4.819
senal-4.805
awan-4.749
Token,
Token ID11
Feature activation+4.76e-01

Pos logit contributions
ertodd+1.896
ysis+1.476
verts+1.431
ered+1.414
 quo+1.383
Neg logit contributions
ANE-2.391
-2.283
awan-2.278
 srf-2.271
EMENT-2.236
Token at
Token ID379
Feature activation+4.47e-01

Pos logit contributions
ertodd+1.353
ysis+1.081
verts+1.027
ered+1.021
 quo+1.008
Neg logit contributions
ANE-1.453
awan-1.391
-1.374
-1.355
UA-1.355
Token the
Token ID262
Feature activation+7.26e-01

Pos logit contributions
ertodd+1.113
ysis+0.861
verts+0.808
ered+0.805
 quo+0.790
Neg logit contributions
ANE-1.525
awan-1.471
-1.453
-1.438
RAW-1.437
Token Sud
Token ID14818
Feature activation+2.74e+00

Pos logit contributions
ertodd+2.201
ysis+1.785
verts+1.710
ered+1.707
 Jehovah+1.668
Neg logit contributions
ANE-2.082
awan-1.977
-1.951
-1.949
 srf-1.939
Tokenz
Token ID89
Feature activation+3.21e-01

Pos logit contributions
ertodd+7.714
ered+6.324
ysis+6.274
verts+6.112
 quo+5.801
Neg logit contributions
ANE-7.636
 srf-7.587
senal-7.425
-7.365
-7.209
Tokenha
Token ID3099
Feature activation+6.04e-01

Pos logit contributions
ertodd+1.010
ysis+0.833
verts+0.795
ered+0.793
 quo+0.773
Neg logit contributions
ANE-0.871
awan-0.828
-0.824
 srf-0.821
-0.816
Token pumping
Token ID26916
Feature activation+3.77e-01

Pos logit contributions
ertodd+1.713
ysis+1.372
ered+1.306
verts+1.302
 quo+1.261
Neg logit contributions
ANE-1.852
awan-1.763
-1.751
-1.737
EMENT-1.733
Token station
Token ID4429
Feature activation-2.12e-01

Pos logit contributions
ertodd+1.202
ysis+0.996
verts+0.946
ered+0.945
 quo+0.933
Neg logit contributions
ANE-1.022
awan-0.977
 srf-0.957
-0.955
-0.949
Token on
Token ID319
Feature activation+5.95e-02

Pos logit contributions
ANE+0.572
awan+0.547
+0.535
UA+0.530
+0.528
Neg logit contributions
ertodd-0.685
ysis-0.558
verts-0.532
ered-0.530
 quo-0.523
Token a
Token ID257
Feature activation+7.08e-01

Pos logit contributions
ertodd+4.779
ysis+4.032
ered+3.868
verts+3.760
 quo+3.759
Neg logit contributions
ANE-6.047
 srf-5.964
-5.834
awan-5.834
senal-5.771
Token full
Token ID1336
Feature activation+7.07e-01

Pos logit contributions
ertodd+2.050
ysis+1.695
ered+1.633
verts+1.593
 quo+1.572
Neg logit contributions
ANE-2.072
awan-2.001
-1.992
UA-1.954
 srf-1.942
Token-
Token ID12
Feature activation+9.33e-01

Pos logit contributions
ertodd+1.666
ysis+1.286
ered+1.193
verts+1.191
 quo+1.166
Neg logit contributions
ANE-2.499
awan-2.420
-2.377
-2.365
UA-2.357
Tokenblown
Token ID31290
Feature activation+5.11e-01

Pos logit contributions
ertodd+2.740
ysis+2.253
verts+2.162
ered+2.140
 quo+2.083
Neg logit contributions
ANE-2.734
awan-2.599
-2.562
-2.556
 srf-2.551
Token pand
Token ID19798
Feature activation+1.82e+00

Pos logit contributions
ertodd+1.405
ysis+1.150
ered+1.097
verts+1.071
 Jehovah+1.058
Neg logit contributions
ANE-1.574
awan-1.524
-1.514
 srf-1.492
UA-1.490
Tokenemic
Token ID5314
Feature activation+2.72e+00

Pos logit contributions
ertodd+3.283
ysis+2.384
ered+2.312
verts+2.070
 Rupert+1.844
Neg logit contributions
ANE-7.352
 srf-7.277
-7.177
senal-7.155
-7.105
Token.
Token ID13
Feature activation-2.60e-01

Pos logit contributions
ertodd+7.625
ysis+6.423
ered+6.193
 quo+6.058
verts+6.029
Neg logit contributions
ANE-7.353
 srf-7.237
awan-7.170
-7.138
senal-7.118
Token SW
Token ID12672
Feature activation-7.98e-01

Pos logit contributions
ANE+0.846
awan+0.815
+0.800
UA+0.794
+0.792
Neg logit contributions
ertodd-0.695
ysis-0.539
verts-0.507
ered-0.504
 quo-0.496
TokenINE
Token ID8881
Feature activation+6.83e-02

Pos logit contributions
ANE+1.629
awan+1.523
+1.475
UA+1.462
RAW+1.450
Neg logit contributions
ertodd-3.116
ysis-2.635
verts-2.536
ered-2.523
 quo-2.502
Token FL
Token ID9977
Feature activation-5.40e-01

Pos logit contributions
ertodd+0.197
ysis+0.158
verts+0.150
ered+0.150
 quo+0.146
Neg logit contributions
ANE-0.205
awan-0.198
-0.194
-0.192
 srf-0.192
TokenU
Token ID52
Feature activation+7.85e-01

Pos logit contributions
ANE+0.861
awan+0.803
+0.771
+0.755
 srf+0.755
Neg logit contributions
ertodd-2.334
ysis-2.017
verts-1.949
ered-1.945
 quo-1.922
Token and
Token ID290
Feature activation-6.28e-01

Pos logit contributions
ANE+2.264
awan+2.185
+2.142
UA+2.128
+2.122
Neg logit contributions
ertodd-1.761
ysis-1.358
verts-1.262
ered-1.257
 quo-1.233
Token the
Token ID262
Feature activation+1.89e-01

Pos logit contributions
ANE+2.020
awan+1.953
+1.908
UA+1.902
EMENT+1.894
Neg logit contributions
ertodd-1.704
ysis-1.326
verts-1.230
ered-1.222
 quo-1.215
Token Paradox
Token ID37983
Feature activation+1.09e+00

Pos logit contributions
ertodd+0.502
ysis+0.391
verts+0.368
ered+0.367
 quo+0.360
Neg logit contributions
ANE-0.619
awan-0.595
-0.585
UA-0.580
-0.579
Token of
Token ID286
Feature activation-8.89e-02

Pos logit contributions
ertodd+3.123
ysis+2.508
ered+2.383
verts+2.379
 quo+2.326
Neg logit contributions
ANE-3.295
awan-3.163
-3.128
 srf-3.099
-3.080
Token Credit
Token ID10504
Feature activation+7.95e-01

Pos logit contributions
ANE+0.289
awan+0.279
+0.273
UA+0.271
+0.271
Neg logit contributions
ertodd-0.238
ysis-0.185
verts-0.174
ered-0.173
 quo-0.170
Token Bub
Token ID19645
Feature activation+2.70e+00

Pos logit contributions
ertodd+2.188
ysis+1.751
verts+1.676
ered+1.669
 quo+1.628
Neg logit contributions
ANE-2.478
awan-2.365
-2.339
 srf-2.335
-2.308
Tokenbles
Token ID7689
Feature activation+1.60e+00

Pos logit contributions
ertodd+5.806
verts+4.368
ysis+4.310
ered+4.128
gencies+3.914
Neg logit contributions
ANE-9.437
 srf-9.405
senal-9.392
-9.356
-9.169
Token,
Token ID11
Feature activation-2.60e-02

Pos logit contributions
ertodd+4.635
ysis+3.728
ered+3.606
verts+3.589
 quo+3.509
Neg logit contributions
ANE-4.618
awan-4.439
 srf-4.400
-4.386
-4.332
Token Equity
Token ID35659
Feature activation-4.93e-01

Pos logit contributions
ANE+0.080
awan+0.077
+0.076
UA+0.075
+0.075
Neg logit contributions
ertodd-0.073
ysis-0.058
verts-0.055
ered-0.055
 quo-0.054
Token and
Token ID290
Feature activation-5.88e-01

Pos logit contributions
ANE+1.532
awan+1.481
+1.447
UA+1.435
EMENT+1.433
Neg logit contributions
ertodd-1.392
ysis-1.094
verts-1.022
ered-1.018
 quo-1.006
Token Demand
Token ID34479
Feature activation+1.08e+00

Pos logit contributions
ANE+1.937
awan+1.875
+1.828
UA+1.822
EMENT+1.819
Neg logit contributions
ertodd-1.551
ysis-1.190
verts-1.096
ered-1.091
 quo-1.083
Token45
Token ID2231
Feature activation+6.97e-01

Pos logit contributions
ertodd+2.017
ysis+1.678
verts+1.624
ered+1.602
 Jehovah+1.577
Neg logit contributions
 srf-1.948
awan-1.920
ANE-1.918
senal-1.875
-1.829
Token 366
Token ID44856
Feature activation+6.59e-01

Pos logit contributions
ertodd+2.002
ysis+1.655
verts+1.582
ered+1.567
 Jehovah+1.547
Neg logit contributions
ANE-2.018
awan-1.988
 srf-1.927
-1.905
-1.891
Token.
Token ID13
Feature activation+2.77e-02

Pos logit contributions
ertodd+2.132
ysis+1.774
verts+1.719
ered+1.714
 quo+1.684
Neg logit contributions
ANE-1.690
awan-1.644
-1.606
 srf-1.583
RAW-1.577
Token
Token ID198
Feature activation+4.19e-01

Pos logit contributions
ertodd+0.076
ysis+0.059
verts+0.056
ered+0.055
 quo+0.054
Neg logit contributions
ANE-0.089
awan-0.085
-0.084
UA-0.083
-0.083
Token
Token ID198
Feature activation-1.30e-01

Pos logit contributions
ertodd+1.028
ysis+0.784
ered+0.747
verts+0.745
 quo+0.721
Neg logit contributions
ANE-1.445
 srf-1.406
awan-1.392
senal-1.390
-1.375
TokenTopics
Token ID25902
Feature activation+2.69e+00

Pos logit contributions
ANE+0.379
awan+0.365
 srf+0.361
+0.358
+0.354
Neg logit contributions
ertodd-0.385
ysis-0.311
verts-0.298
ered-0.297
 quo-0.290
Token:
Token ID25
Feature activation+6.12e-01

Pos logit contributions
ertodd+6.301
ered+4.874
verts+4.694
ysis+4.630
 Rupert+4.571
Neg logit contributions
 srf-9.265
senal-9.230
 adolesc-8.807
ANE-8.806
awan-8.538
Token community
Token ID2055
Feature activation+7.37e-01

Pos logit contributions
ertodd+1.727
ysis+1.396
ered+1.340
verts+1.336
 quo+1.318
Neg logit contributions
ANE-1.854
awan-1.769
-1.758
UA-1.745
RAW-1.739
Token-
Token ID12
Feature activation-1.15e-01

Pos logit contributions
ertodd+1.713
ysis+1.285
verts+1.199
ered+1.190
 quo+1.165
Neg logit contributions
ANE-2.654
awan-2.558
-2.516
 srf-2.510
UA-2.497
Tokenand
Token ID392
Feature activation+3.85e-01

Pos logit contributions
ANE+0.266
awan+0.260
+0.250
UA+0.247
+0.246
Neg logit contributions
ertodd-0.413
ysis-0.342
ered-0.325
verts-0.324
 quo-0.323
Token-
Token ID12
Feature activation-2.15e-01

Pos logit contributions
ertodd+0.882
ysis+0.655
ered+0.616
verts+0.615
 quo+0.597
Neg logit contributions
ANE-1.401
awan-1.349
 srf-1.331
-1.331
-1.318
Token activists
Token ID7941
Feature activation-4.27e-01

Pos logit contributions
ertodd+0.552
ysis+0.445
ered+0.425
verts+0.425
 quo+0.417
Neg logit contributions
ANE-0.567
awan-0.543
-0.534
 srf-0.532
-0.529
Token protesting
Token ID23655
Feature activation-9.20e-02

Pos logit contributions
ANE+1.408
awan+1.357
+1.333
UA+1.322
+1.320
Neg logit contributions
ertodd-1.119
ysis-0.867
verts-0.815
ered-0.812
 quo-0.798
Token the
Token ID262
Feature activation+1.46e-01

Pos logit contributions
ANE+0.278
awan+0.266
+0.261
 srf+0.261
+0.259
Neg logit contributions
ertodd-0.262
ysis-0.213
verts-0.202
ered-0.201
 quo-0.199
Token theft
Token ID12402
Feature activation+2.31e-01

Pos logit contributions
ertodd+0.436
ysis+0.358
verts+0.336
ered+0.336
 quo+0.333
Neg logit contributions
ANE-0.426
awan-0.406
 srf-0.399
-0.398
-0.398
Token of
Token ID286
Feature activation-3.83e-01

Pos logit contributions
ertodd+0.670
ysis+0.532
verts+0.504
ered+0.500
 quo+0.492
Neg logit contributions
ANE-0.701
awan-0.674
-0.661
UA-0.654
-0.653
Token earthquake
Token ID16295
Feature activation+2.69e+00

Pos logit contributions
ANE+1.163
awan+1.114
+1.096
+1.090
 srf+1.087
Neg logit contributions
ertodd-1.098
ysis-0.881
verts-0.833
ered-0.833
 quo-0.820
Token aid
Token ID6133
Feature activation+3.07e-02

Pos logit contributions
ertodd+5.831
ysis+4.767
ered+4.613
 quo+4.408
verts+4.292
Neg logit contributions
ANE-9.085
awan-8.809
 srf-8.788
-8.690
RAW-8.660
Token &
Token ID1222
Feature activation-1.59e-01

Pos logit contributions
ertodd+0.088
ysis+0.071
ered+0.068
verts+0.068
 quo+0.066
Neg logit contributions
ANE-0.093
awan-0.089
-0.087
 srf-0.086
-0.086
Token pill
Token ID9582
Feature activation+4.13e-01

Pos logit contributions
ANE+0.482
awan+0.462
+0.453
UA+0.449
+0.449
Neg logit contributions
ertodd-0.458
ysis-0.366
verts-0.346
ered-0.346
 quo-0.340
Tokenage
Token ID496
Feature activation+6.01e-01

Pos logit contributions
ertodd+1.255
ysis+1.035
ered+0.991
verts+0.978
 quo+0.955
Neg logit contributions
ANE-1.159
awan-1.111
-1.094
 srf-1.092
UA-1.090
Token of
Token ID286
Feature activation-4.75e-01

Pos logit contributions
ertodd+1.735
ysis+1.415
ered+1.365
 quo+1.338
verts+1.337
Neg logit contributions
ANE-1.789
awan-1.699
 srf-1.679
-1.656
RAW-1.650
TokenT
Token ID51
Feature activation+7.57e-01

Pos logit contributions
ertodd+2.201
ysis+1.853
verts+1.788
ered+1.784
 quo+1.752
Neg logit contributions
ANE-1.270
awan-1.203
-1.168
 srf-1.154
-1.153
Token Secrets
Token ID23561
Feature activation-4.10e-01

Pos logit contributions
ertodd+2.117
ysis+1.695
verts+1.617
ered+1.615
 quo+1.576
Neg logit contributions
ANE-2.309
awan-2.220
-2.178
-2.170
 srf-2.164
Token St
Token ID520
Feature activation+3.20e-01

Pos logit contributions
ANE+1.200
awan+1.152
+1.128
UA+1.117
+1.116
Neg logit contributions
ertodd-1.227
ysis-0.985
verts-0.935
ered-0.932
 quo-0.917
Token James
Token ID3700
Feature activation+1.16e+00

Pos logit contributions
ertodd+0.890
ysis+0.710
ered+0.674
verts+0.669
 quo+0.655
Neg logit contributions
ANE-0.995
awan-0.952
-0.940
-0.939
 srf-0.930
Token in
Token ID287
Feature activation+2.24e-01

Pos logit contributions
ertodd+3.309
ysis+2.714
verts+2.593
ered+2.585
 Rupert+2.517
Neg logit contributions
ANE-3.417
awan-3.244
-3.228
-3.222
 srf-3.221
Token Monte
Token ID22489
Feature activation+2.69e+00

Pos logit contributions
ertodd+0.622
ysis+0.490
verts+0.465
ered+0.462
 quo+0.454
Neg logit contributions
ANE-0.705
awan-0.678
-0.665
-0.659
UA-0.659
Tokengo
Token ID2188
Feature activation+1.38e+00

Pos logit contributions
ertodd+8.068
verts+6.791
ysis+6.732
ered+6.615
 Rupert+6.375
Neg logit contributions
ANE-7.150
-6.893
-6.772
 srf-6.724
RAW-6.689
Token Bay
Token ID4696
Feature activation+6.21e-01

Pos logit contributions
ertodd+3.533
ered+2.721
verts+2.706
ysis+2.700
 Jehovah+2.546
Neg logit contributions
ANE-4.433
awan-4.313
-4.312
RAW-4.278
EMENT-4.260
Token from
Token ID422
Feature activation+3.29e-01

Pos logit contributions
ertodd+1.838
ysis+1.497
ered+1.448
verts+1.444
 quo+1.396
Neg logit contributions
ANE-1.791
awan-1.710
-1.678
RAW-1.678
EMENT-1.677
Token £
Token ID4248
Feature activation-2.77e-02

Pos logit contributions
ertodd+1.036
ysis+0.839
verts+0.797
ered+0.793
 quo+0.783
Neg logit contributions
ANE-0.917
awan-0.879
-0.859
UA-0.851
-0.848
Token1
Token ID16
Feature activation-4.17e-02

Pos logit contributions
ANE+0.063
awan+0.060
 srf+0.058
+0.058
UA+0.057
Neg logit contributions
ertodd-0.101
ysis-0.085
verts-0.082
ered-0.082
 quo-0.080
Token we
Token ID356
Feature activation+3.55e-01

Pos logit contributions
ANE+1.508
awan+1.449
+1.419
UA+1.406
+1.406
Neg logit contributions
ertodd-1.432
ysis-1.131
verts-1.069
ered-1.063
 quo-1.047
Token are
Token ID389
Feature activation+3.68e-01

Pos logit contributions
ertodd+0.898
ysis+0.694
ered+0.670
verts+0.654
 quo+0.649
Neg logit contributions
ANE-1.187
awan-1.142
 srf-1.137
-1.135
UA-1.126
Token in
Token ID287
Feature activation+1.31e+00

Pos logit contributions
ertodd+1.073
ysis+0.875
ered+0.841
verts+0.830
 quo+0.822
Neg logit contributions
ANE-1.084
awan-1.043
-1.026
 srf-1.022
UA-1.015
Token a
Token ID257
Feature activation+8.32e-01

Pos logit contributions
ertodd+3.219
ysis+2.515
verts+2.419
ered+2.386
 quo+2.335
Neg logit contributions
ANE-4.371
awan-4.254
-4.215
 srf-4.149
UA-4.132
Token pand
Token ID19798
Feature activation+1.80e+00

Pos logit contributions
ertodd+2.536
ysis+2.096
verts+2.014
ered+2.009
 quo+1.987
Neg logit contributions
ANE-2.310
awan-2.223
-2.206
UA-2.170
 srf-2.162
Tokenemic
Token ID5314
Feature activation+2.67e+00

Pos logit contributions
ertodd+3.296
ysis+2.278
ered+2.244
verts+1.999
 quo+1.799
Neg logit contributions
ANE-7.259
 srf-7.228
senal-7.140
-7.061
-6.996
Token situation
Token ID3074
Feature activation+1.12e+00

Pos logit contributions
ertodd+7.179
ysis+6.085
ered+5.933
verts+5.778
 quo+5.769
Neg logit contributions
ANE-7.528
 srf-7.362
senal-7.351
-7.350
awan-7.292
Token,"
Token ID553
Feature activation+8.92e-01

Pos logit contributions
ertodd+3.192
ysis+2.596
ered+2.498
 quo+2.485
verts+2.472
Neg logit contributions
ANE-3.298
awan-3.183
 srf-3.171
-3.156
senal-3.151
Token he
Token ID339
Feature activation+1.06e+00

Pos logit contributions
ertodd+2.145
ysis+1.635
ered+1.530
verts+1.525
 quo+1.504
Neg logit contributions
ANE-3.096
awan-2.981
-2.945
 srf-2.935
UA-2.927
Token said
Token ID531
Feature activation+3.12e-01

Pos logit contributions
ertodd+2.926
ysis+2.310
ered+2.216
verts+2.204
 quo+2.183
Neg logit contributions
ANE-3.281
awan-3.127
 srf-3.117
-3.091
-3.063
Token.
Token ID13
Feature activation+9.25e-01

Pos logit contributions
ertodd+1.068
ysis+0.884
verts+0.849
ered+0.849
 quo+0.835
Neg logit contributions
ANE-0.779
awan-0.738
-0.722
 srf-0.717
UA-0.715
Token tad
Token ID36264
Feature activation+9.67e-01

Pos logit contributions
ertodd+0.946
ysis+0.774
verts+0.740
ered+0.738
 quo+0.730
Neg logit contributions
ANE-0.860
awan-0.823
-0.808
 srf-0.803
-0.803
Tokenpole
Token ID36869
Feature activation+1.09e+00

Pos logit contributions
ertodd+3.384
ysis+2.807
verts+2.697
ered+2.683
 quo+2.663
Neg logit contributions
ANE-2.350
awan-2.213
-2.184
UA-2.156
 srf-2.151
Token had
Token ID550
Feature activation+1.10e+00

Pos logit contributions
ertodd+2.957
ysis+2.315
ered+2.243
verts+2.216
 quo+2.199
Neg logit contributions
ANE-3.484
 srf-3.356
-3.316
awan-3.311
senal-3.308
Token just
Token ID655
Feature activation+1.10e+00

Pos logit contributions
ertodd+2.923
ysis+2.325
ered+2.272
verts+2.199
 Jehovah+2.160
Neg logit contributions
ANE-3.513
awan-3.392
 srf-3.365
-3.326
senal-3.324
Token a
Token ID257
Feature activation+1.27e+00

Pos logit contributions
ertodd+2.968
ysis+2.337
ered+2.299
verts+2.228
 quo+2.198
Neg logit contributions
ANE-3.468
 srf-3.334
awan-3.326
senal-3.325
-3.278
Token tail
Token ID7894
Feature activation+2.64e+00

Pos logit contributions
ertodd+3.882
ysis+3.216
ered+3.167
verts+3.121
 quo+3.101
Neg logit contributions
ANE-3.428
awan-3.303
-3.251
 srf-3.242
UA-3.237
Token I
Token ID314
Feature activation+2.13e-03

Pos logit contributions
ertodd+6.603
ysis+5.398
ered+5.397
 quo+5.225
verts+5.060
Neg logit contributions
ANE-7.920
 srf-7.863
senal-7.769
-7.730
-7.649
Token sold
Token ID2702
Feature activation+1.74e-01

Pos logit contributions
ertodd+0.005
ysis+0.004
ered+0.004
verts+0.004
 quo+0.003
Neg logit contributions
ANE-0.008
awan-0.007
-0.007
 srf-0.007
UA-0.007
Token '
Token ID705
Feature activation-6.19e-01

Pos logit contributions
ertodd+0.463
ysis+0.365
ered+0.350
verts+0.344
 quo+0.337
Neg logit contributions
ANE-0.564
awan-0.542
-0.533
 srf-0.532
-0.531
Tokenem
Token ID368
Feature activation-2.43e-01

Pos logit contributions
ANE+1.681
awan+1.618
+1.575
UA+1.562
+1.553
Neg logit contributions
ertodd-1.984
ysis-1.611
verts-1.534
ered-1.522
 quo-1.510
Token for
Token ID329
Feature activation-7.77e-02

Pos logit contributions
ANE+0.689
awan+0.659
+0.646
UA+0.641
+0.640
Neg logit contributions
ertodd-0.752
ysis-0.613
ered-0.583
verts-0.582
 quo-0.573
Token into
Token ID656
Feature activation-1.01e-01

Pos logit contributions
ertodd+0.350
ysis+0.292
ered+0.282
verts+0.279
 quo+0.276
Neg logit contributions
ANE-0.272
awan-0.261
-0.255
 srf-0.255
UA-0.252
Token them
Token ID606
Feature activation-2.60e-02

Pos logit contributions
ANE+0.318
awan+0.307
+0.301
UA+0.298
+0.298
Neg logit contributions
ertodd-0.282
ysis-0.222
verts-0.210
ered-0.209
 quo-0.205
Token".
Token ID1911
Feature activation+8.69e-01

Pos logit contributions
ANE+0.072
awan+0.069
+0.067
 srf+0.066
UA+0.066
Neg logit contributions
ertodd-0.083
ysis-0.067
ered-0.064
verts-0.064
 quo-0.063
Token
Token ID198
Feature activation+6.99e-01

Pos logit contributions
ertodd+2.114
ysis+1.604
ered+1.506
verts+1.497
 quo+1.457
Neg logit contributions
ANE-3.009
 srf-2.921
awan-2.900
senal-2.882
-2.872
Token
Token ID198
Feature activation+2.49e-01

Pos logit contributions
ertodd+1.662
ysis+1.260
ered+1.211
verts+1.203
 quo+1.157
Neg logit contributions
ANE-2.443
 srf-2.426
senal-2.405
awan-2.352
-2.331
TokenTopics
Token ID25902
Feature activation+2.63e+00

Pos logit contributions
ertodd+0.805
ysis+0.664
ered+0.642
verts+0.641
 quo+0.624
Neg logit contributions
ANE-0.652
 srf-0.633
awan-0.628
senal-0.615
-0.615
Token:
Token ID25
Feature activation+6.96e-01

Pos logit contributions
ertodd+6.171
ered+4.789
verts+4.625
ysis+4.580
 Rupert+4.515
Neg logit contributions
 srf-9.048
senal-8.972
 adolesc-8.589
ANE-8.561
awan-8.345
Token marine
Token ID16050
Feature activation+1.65e+00

Pos logit contributions
ertodd+1.912
ysis+1.542
ered+1.483
verts+1.483
 quo+1.463
Neg logit contributions
ANE-2.147
-2.046
awan-2.043
UA-2.012
RAW-2.007
Token-
Token ID12
Feature activation-2.84e-01

Pos logit contributions
ertodd+3.795
ysis+2.852
verts+2.708
ered+2.703
 quo+2.604
Neg logit contributions
ANE-5.868
awan-5.613
-5.572
 srf-5.567
EMENT-5.548
Tokenbiology
Token ID43592
Feature activation+1.34e+00

Pos logit contributions
ANE+0.769
awan+0.737
+0.719
UA+0.713
+0.711
Neg logit contributions
ertodd-0.917
ysis-0.746
verts-0.711
ered-0.708
 quo-0.700
Token,
Token ID11
Feature activation+7.47e-01

Pos logit contributions
ertodd+3.890
ysis+3.140
verts+3.022
ered+3.009
 quo+2.922
Neg logit contributions
ANE-3.975
 srf-3.839
senal-3.790
awan-3.750
-3.730
Token support
Token ID1104
Feature activation-2.37e-01

Pos logit contributions
ANE+1.427
awan+1.372
+1.344
UA+1.331
+1.330
Neg logit contributions
ertodd-1.186
ysis-0.924
verts-0.865
ered-0.860
 quo-0.848
Token the
Token ID262
Feature activation+2.24e-02

Pos logit contributions
ANE+0.781
awan+0.744
UA+0.729
+0.728
+0.724
Neg logit contributions
ertodd-0.639
ysis-0.491
verts-0.459
ered-0.455
 quo-0.447
Token mission
Token ID4365
Feature activation+9.15e-01

Pos logit contributions
ertodd+0.071
ysis+0.057
verts+0.054
ered+0.054
 quo+0.053
Neg logit contributions
ANE-0.063
awan-0.060
-0.059
UA-0.058
-0.058
Token of
Token ID286
Feature activation-7.32e-01

Pos logit contributions
ertodd+2.387
ysis+1.873
ered+1.777
verts+1.771
 quo+1.769
Neg logit contributions
ANE-2.981
awan-2.835
 srf-2.830
-2.823
senal-2.804
Token New
Token ID968
Feature activation+5.78e-01

Pos logit contributions
ANE+2.193
awan+2.048
UA+2.047
+2.038
RAW+2.032
Neg logit contributions
ertodd-2.214
ysis-1.712
ered-1.592
verts-1.585
 quo-1.568
Token Advent
Token ID33732
Feature activation+2.62e+00

Pos logit contributions
ertodd+1.218
ysis+0.902
ered+0.836
verts+0.824
 Jehovah+0.809
Neg logit contributions
ANE-2.174
awan-2.115
-2.074
EMENT-2.069
RAW-2.065
Token and
Token ID290
Feature activation-5.40e-01

Pos logit contributions
ertodd+6.008
ered+4.649
ysis+4.580
 quo+4.263
verts+4.236
Neg logit contributions
 srf-9.085
ANE-9.026
awan-8.813
senal-8.797
-8.711
Token get
Token ID651
Feature activation-5.22e-01

Pos logit contributions
ANE+1.359
awan+1.322
+1.278
RAW+1.269
EMENT+1.262
Neg logit contributions
ertodd-1.860
ysis-1.491
verts-1.437
ered-1.387
 quo-1.385
Token the
Token ID262
Feature activation-4.72e-01

Pos logit contributions
ANE+1.600
awan+1.563
+1.535
EMENT+1.532
UA+1.518
Neg logit contributions
ertodd-1.488
ysis-1.175
verts-1.088
ered-1.080
 quo-1.035
Token full
Token ID1336
Feature activation+6.11e-01

Pos logit contributions
ANE+1.019
awan+0.990
UA+0.946
+0.943
+0.938
Neg logit contributions
ertodd-1.769
ysis-1.482
verts-1.419
ered-1.399
 Jehovah-1.372
Token contents
Token ID10154
Feature activation+3.71e-01

Pos logit contributions
ertodd+2.152
ysis+1.816
verts+1.760
 quo+1.736
ered+1.735
Neg logit contributions
ANE-1.474
awan-1.366
-1.350
-1.337
RAW-1.322
Token problem
Token ID1917
Feature activation+1.61e+00

Pos logit contributions
ANE+0.333
awan+0.320
+0.313
UA+0.310
+0.310
Neg logit contributions
ertodd-0.297
ysis-0.233
verts-0.219
ered-0.218
 quo-0.215
Token is
Token ID318
Feature activation-3.50e-01

Pos logit contributions
ertodd+3.963
ysis+3.064
verts+2.951
ered+2.937
 quo+2.913
Neg logit contributions
ANE-5.373
 srf-5.219
awan-5.205
-5.196
senal-5.092
Token that
Token ID326
Feature activation-2.57e-01

Pos logit contributions
ANE+1.013
awan+0.973
+0.953
UA+0.943
+0.941
Neg logit contributions
ertodd-1.060
ysis-0.853
verts-0.810
ered-0.807
 quo-0.795
Token the
Token ID262
Feature activation-3.03e-02

Pos logit contributions
ANE+0.803
awan+0.773
+0.757
UA+0.750
+0.750
Neg logit contributions
ertodd-0.723
ysis-0.567
verts-0.535
ered-0.531
 quo-0.523
Token pand
Token ID19798
Feature activation+1.37e+00

Pos logit contributions
ANE+0.095
awan+0.091
+0.089
UA+0.089
+0.089
Neg logit contributions
ertodd-0.085
ysis-0.067
verts-0.063
ered-0.063
 quo-0.062
Tokenemic
Token ID5314
Feature activation+2.61e+00

Pos logit contributions
ertodd+2.656
ysis+1.886
ered+1.822
verts+1.796
 quo+1.553
Neg logit contributions
ANE-5.398
 srf-5.298
-5.218
-5.197
senal-5.172
Token phase
Token ID7108
Feature activation+1.25e+00

Pos logit contributions
ertodd+6.100
ysis+4.812
verts+4.760
ered+4.695
 quo+4.559
Neg logit contributions
ANE-8.561
 srf-8.556
-8.400
senal-8.285
awan-8.263
Token system
Token ID1080
Feature activation+2.97e-01

Pos logit contributions
ertodd+3.145
ysis+2.485
ered+2.368
verts+2.358
 quo+2.349
Neg logit contributions
ANE-4.101
awan-3.992
 srf-3.969
-3.947
-3.924
Token is
Token ID318
Feature activation-6.74e-02

Pos logit contributions
ertodd+0.800
ysis+0.629
verts+0.595
ered+0.593
 quo+0.583
Neg logit contributions
ANE-0.957
awan-0.921
-0.910
 srf-0.903
-0.899
Token designed
Token ID3562
Feature activation-4.60e-02

Pos logit contributions
ANE+0.194
awan+0.187
+0.184
 srf+0.183
UA+0.181
Neg logit contributions
ertodd-0.203
ysis-0.166
ered-0.158
verts-0.157
 quo-0.155
Token for
Token ID329
Feature activation+8.55e-01

Pos logit contributions
ANE+0.126
awan+0.121
+0.118
UA+0.117
+0.117
Neg logit contributions
ertodd-0.147
ysis-0.119
verts-0.114
ered-0.113
 quo-0.112
Token that
Token ID326
Feature activation-1.86e-02

Pos logit contributions
ertodd+0.845
ysis+0.663
ered+0.628
verts+0.626
 quo+0.612
Neg logit contributions
ANE-1.040
awan-1.001
-0.983
 srf-0.981
UA-0.976
Token she
Token ID673
Feature activation+5.19e-02

Pos logit contributions
ANE+0.062
awan+0.060
+0.059
UA+0.058
+0.058
Neg logit contributions
ertodd-0.048
ysis-0.037
verts-0.035
ered-0.034
 quo-0.034
Token was
Token ID373
Feature activation+6.19e-01

Pos logit contributions
ertodd+0.140
ysis+0.109
verts+0.103
ered+0.103
 quo+0.101
Neg logit contributions
ANE-0.167
awan-0.161
-0.158
 srf-0.157
UA-0.157
Token pressing
Token ID12273
Feature activation-1.05e-01

Pos logit contributions
ertodd+1.672
ysis+1.348
ered+1.291
verts+1.283
 quo+1.278
Neg logit contributions
ANE-1.938
awan-1.875
 srf-1.866
-1.844
senal-1.823
Token for
Token ID329
Feature activation+5.26e-01

Pos logit contributions
ANE+0.311
awan+0.299
+0.293
UA+0.290
+0.290
Neg logit contributions
ertodd-0.310
ysis-0.248
verts-0.235
ered-0.234
 quo-0.231
Token Jun
Token ID7653
Feature activation+2.58e+00

Pos logit contributions
ertodd+1.332
ysis+1.029
verts+0.967
ered+0.963
 quo+0.950
Neg logit contributions
ANE-1.777
awan-1.716
-1.690
 srf-1.674
UA-1.670
Tokencker
Token ID15280
Feature activation+1.71e+00

Pos logit contributions
ertodd+2.303
ered+1.029
ysis+0.966
verts+0.916
 quo+0.842
Neg logit contributions
senal-12.517
 srf-12.417
ANE-12.278
-12.005
 adolesc-11.969
Token to
Token ID284
Feature activation+8.52e-01

Pos logit contributions
ertodd+5.110
ysis+4.170
ered+3.970
verts+3.918
 quo+3.898
Neg logit contributions
ANE-4.920
awan-4.705
 srf-4.610
-4.592
UA-4.589
Token take
Token ID1011
Feature activation+1.39e+00

Pos logit contributions
ertodd+2.306
ysis+1.855
ered+1.831
 quo+1.766
verts+1.756
Neg logit contributions
ANE-2.676
 srf-2.584
senal-2.579
awan-2.553
-2.546
Token the
Token ID262
Feature activation+2.83e-01

Pos logit contributions
ertodd+3.494
ysis+2.884
ered+2.741
verts+2.734
 quo+2.673
Neg logit contributions
ANE-4.456
 srf-4.284
-4.277
awan-4.274
UA-4.215
Token reins
Token ID35627
Feature activation+3.00e-01

Pos logit contributions
ertodd+0.825
ysis+0.667
verts+0.640
ered+0.639
 quo+0.631
Neg logit contributions
ANE-0.838
awan-0.802
-0.793
 srf-0.788
-0.785
TokenWe
Token ID1135
Feature activation+3.15e-01

Pos logit contributions
ANE+0.439
 srf+0.427
awan+0.423
senal+0.410
+0.409
Neg logit contributions
ertodd-0.742
ysis-0.632
verts-0.611
ered-0.609
 quo-0.598
Token're
Token ID821
Feature activation+7.97e-01

Pos logit contributions
ertodd+0.830
ysis+0.648
ered+0.624
verts+0.608
 quo+0.606
Neg logit contributions
ANE-1.027
awan-0.981
-0.978
 srf-0.976
UA-0.972
Token hoping
Token ID7725
Feature activation+1.99e-01

Pos logit contributions
ertodd+2.335
ysis+1.900
ered+1.826
verts+1.823
 Jehovah+1.820
Neg logit contributions
ANE-2.302
-2.206
awan-2.204
 srf-2.187
UA-2.177
Token that
Token ID326
Feature activation-2.98e-01

Pos logit contributions
ertodd+0.528
ysis+0.418
ered+0.396
verts+0.394
 quo+0.391
Neg logit contributions
ANE-0.639
awan-0.616
-0.611
 srf-0.607
-0.604
Token he
Token ID339
Feature activation+4.09e-01

Pos logit contributions
ANE+0.944
awan+0.909
+0.894
UA+0.885
 srf+0.885
Neg logit contributions
ertodd-0.820
ysis-0.648
verts-0.613
ered-0.611
 quo-0.602
Token sur
Token ID969
Feature activation+2.57e+00

Pos logit contributions
ertodd+1.089
ysis+0.850
verts+0.804
ered+0.804
 quo+0.789
Neg logit contributions
ANE-1.337
awan-1.285
-1.264
 srf-1.260
UA-1.256
Tokenrend
Token ID10920
Feature activation+1.67e+00

Pos logit contributions
ertodd+6.401
ysis+5.139
verts+5.062
ered+5.032
prises+4.858
Neg logit contributions
ANE-8.369
 srf-7.996
senal-7.985
-7.957
UA-7.881
Tokeners
Token ID364
Feature activation+6.47e-01

Pos logit contributions
ertodd+3.340
ered+2.436
ysis+2.315
verts+2.287
 quo+2.023
Neg logit contributions
ANE-6.614
senal-6.519
 srf-6.514
-6.376
-6.335
Token,"
Token ID553
Feature activation+6.71e-01

Pos logit contributions
ertodd+1.842
ysis+1.494
ered+1.431
verts+1.416
 quo+1.408
Neg logit contributions
ANE-1.967
awan-1.877
-1.848
 srf-1.843
-1.836
Token the
Token ID262
Feature activation+4.15e-01

Pos logit contributions
ertodd+1.555
ysis+1.166
ered+1.082
verts+1.081
 quo+1.068
Neg logit contributions
ANE-2.398
awan-2.310
-2.289
-2.267
UA-2.262
Token police
Token ID1644
Feature activation-2.75e-01

Pos logit contributions
ertodd+1.081
ysis+0.849
ered+0.794
verts+0.791
 quo+0.785
Neg logit contributions
ANE-1.360
awan-1.309
-1.294
-1.283
UA-1.282
Token 5
Token ID642
Feature activation-4.00e-01

Pos logit contributions
ANE+5.387
awan+5.140
+5.055
RAW+4.985
UA+4.966
Neg logit contributions
ertodd-7.167
ysis-5.840
verts-5.453
ered-5.426
 quo-5.369
Token years
Token ID812
Feature activation-7.85e-01

Pos logit contributions
ANE+1.277
awan+1.230
+1.205
UA+1.195
+1.194
Neg logit contributions
ertodd-1.091
ysis-0.854
verts-0.807
ered-0.804
 quo-0.789
Token on
Token ID319
Feature activation-6.92e-01

Pos logit contributions
ANE+2.200
awan+2.109
+2.063
UA+2.041
+2.039
Neg logit contributions
ertodd-2.453
ysis-1.986
verts-1.890
ered-1.880
 quo-1.853
Token the
Token ID262
Feature activation-2.51e-01

Pos logit contributions
ANE+2.130
awan+2.050
+2.010
UA+1.992
+1.988
Neg logit contributions
ertodd-1.972
ysis-1.560
verts-1.473
ered-1.466
 quo-1.442
Token housing
Token ID5627
Feature activation-7.65e-01

Pos logit contributions
ANE+0.726
awan+0.695
+0.681
UA+0.675
+0.674
Neg logit contributions
ertodd-0.762
ysis-0.615
verts-0.584
ered-0.582
 quo-0.574
Token bubble
Token ID14310
Feature activation+2.57e+00

Pos logit contributions
ANE+2.364
awan+2.275
+2.231
UA+2.212
+2.207
Neg logit contributions
ertodd-2.168
ysis-1.713
verts-1.618
ered-1.609
 quo-1.581
Token/
Token ID14
Feature activation-9.58e-01

Pos logit contributions
ertodd+7.144
ered+5.722
ysis+5.702
 quo+5.649
verts+5.474
Neg logit contributions
ANE-7.457
awan-7.099
 srf-7.075
-6.939
-6.871
Tokenb
Token ID65
Feature activation+7.85e-02

Pos logit contributions
ANE+2.443
awan+2.342
+2.282
UA+2.266
+2.256
Neg logit contributions
ertodd-3.230
ysis-2.656
verts-2.527
ered-2.516
 quo-2.492
Tokenust
Token ID436
Feature activation+7.72e-01

Pos logit contributions
ertodd+0.251
ysis+0.205
ered+0.197
verts+0.196
 quo+0.191
Neg logit contributions
ANE-0.214
awan-0.203
-0.202
 srf-0.202
-0.200
Token:
Token ID25
Feature activation-7.18e-01

Pos logit contributions
ertodd+2.337
ysis+1.898
ered+1.853
 quo+1.797
verts+1.795
Neg logit contributions
ANE-2.199
awan-2.118
-2.073
 srf-2.050
-2.042
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
ANE+2.256
awan+2.178
+2.136
+2.120
UA+2.118
Neg logit contributions
ertodd-1.966
ysis-1.548
verts-1.459
ered-1.442
 quo-1.403
Token star
Token ID3491
Feature activation+3.12e-01

Pos logit contributions
ANE+2.467
awan+2.375
+2.317
UA+2.299
+2.287
Neg logit contributions
ertodd-2.737
ysis-2.207
verts-2.095
ered-2.082
 quo-2.061
Token (
Token ID357
Feature activation-1.28e+00

Pos logit contributions
ertodd+0.886
ysis+0.702
verts+0.671
ered+0.668
 quo+0.654
Neg logit contributions
ANE-0.958
awan-0.918
-0.902
-0.897
UA-0.894
TokenSh
Token ID2484
Feature activation-1.76e-01

Pos logit contributions
ANE+3.087
awan+2.943
+2.878
UA+2.844
+2.830
Neg logit contributions
ertodd-4.473
ysis-3.706
verts-3.529
ered-3.523
 quo-3.495
Tokenrav
Token ID4108
Feature activation-4.94e-01

Pos logit contributions
ANE+0.431
awan+0.409
+0.401
 srf+0.397
+0.397
Neg logit contributions
ertodd-0.613
ysis-0.510
ered-0.488
verts-0.487
 quo-0.478
Tokenana
Token ID2271
Feature activation-4.57e-03

Pos logit contributions
ANE+1.320
awan+1.268
+1.229
UA+1.219
+1.212
Neg logit contributions
ertodd-1.615
ysis-1.311
verts-1.254
ered-1.247
 quo-1.234
Token Nak
Token ID22255
Feature activation-2.80e+00

Pos logit contributions
ANE+0.012
awan+0.012
+0.011
UA+0.011
+0.011
Neg logit contributions
ertodd-0.015
ysis-0.012
verts-0.012
ered-0.012
 quo-0.011
Tokensh
Token ID1477
Feature activation-8.51e-01

Pos logit contributions
awan+6.988
ANE+6.937
UA+6.493
+6.274
pull+6.250
Neg logit contributions
ertodd-8.990
ysis-7.167
 quo-6.986
verts-6.931
ered-6.805
Tokentra
Token ID9535
Feature activation+2.06e-01

Pos logit contributions
ANE+2.097
awan+2.017
+1.933
UA+1.933
RAW+1.911
Neg logit contributions
ertodd-2.940
ysis-2.425
verts-2.323
ered-2.303
 quo-2.294
Token)
Token ID8
Feature activation+7.31e-01

Pos logit contributions
ertodd+0.710
ysis+0.591
verts+0.569
ered+0.568
 quo+0.559
Neg logit contributions
ANE-0.504
awan-0.477
-0.466
 srf-0.463
-0.462
Token these
Token ID777
Feature activation+4.00e-01

Pos logit contributions
ertodd+1.992
ysis+1.584
verts+1.507
ered+1.503
 quo+1.493
Neg logit contributions
ANE-2.285
awan-2.183
 srf-2.149
EMENT-2.141
-2.137
Token p
Token ID279
Feature activation-1.80e-01

Pos logit contributions
ertodd+1.120
ysis+0.890
verts+0.844
ered+0.842
 quo+0.829
Neg logit contributions
ANE-1.242
awan-1.198
-1.173
UA-1.161
 srf-1.160
Token a
Token ID257
Feature activation+1.33e-01

Pos logit contributions
ANE+0.038
awan+0.037
+0.036
 srf+0.036
UA+0.036
Neg logit contributions
ertodd-0.034
ysis-0.027
ered-0.026
verts-0.026
 quo-0.025
Token number
Token ID1271
Feature activation+1.43e-01

Pos logit contributions
ertodd+0.402
ysis+0.326
verts+0.309
ered+0.309
 quo+0.305
Neg logit contributions
ANE-0.385
awan-0.368
-0.360
UA-0.360
 srf-0.357
Token of
Token ID286
Feature activation-6.48e-01

Pos logit contributions
ertodd+0.419
ysis+0.333
verts+0.317
ered+0.315
 quo+0.307
Neg logit contributions
ANE-0.425
awan-0.408
-0.401
-0.397
UA-0.397
Token things
Token ID1243
Feature activation-3.04e-02

Pos logit contributions
ANE+1.923
awan+1.847
+1.809
UA+1.792
+1.789
Neg logit contributions
ertodd-1.919
ysis-1.533
verts-1.453
ered-1.447
 quo-1.424
Token to
Token ID284
Feature activation-5.26e-01

Pos logit contributions
ANE+0.094
awan+0.091
+0.089
 srf+0.088
UA+0.088
Neg logit contributions
ertodd-0.085
ysis-0.068
ered-0.064
verts-0.064
 quo-0.063
Token argue
Token ID7267
Feature activation-2.75e+00

Pos logit contributions
ANE+1.636
awan+1.575
+1.543
+1.528
UA+1.527
Neg logit contributions
ertodd-1.482
ysis-1.170
verts-1.104
ered-1.094
 quo-1.078
Token with
Token ID351
Feature activation-6.72e-01

Pos logit contributions
ANE+6.309
awan+5.946
RAW+5.803
+5.775
EMENT+5.772
Neg logit contributions
ertodd-9.502
ysis-7.779
verts-7.476
ered-7.291
gencies-7.277
Token in
Token ID287
Feature activation-2.87e-01

Pos logit contributions
ANE+1.784
awan+1.705
+1.666
UA+1.648
+1.645
Neg logit contributions
ertodd-2.197
ysis-1.799
verts-1.717
ered-1.710
 quo-1.687
Token Reed
Token ID16105
Feature activation-3.60e-01

Pos logit contributions
ANE+0.918
awan+0.884
+0.868
UA+0.861
+0.859
Neg logit contributions
ertodd-0.785
ysis-0.614
verts-0.581
ered-0.577
 quo-0.568
Token
Token ID447
Feature activation+4.78e-02

Pos logit contributions
ANE+1.076
awan+1.033
+1.013
UA+1.005
+1.003
Neg logit contributions
ertodd-1.054
ysis-0.840
verts-0.796
ered-0.793
 quo-0.780
Token
Token ID247
Feature activation+3.40e-01

Pos logit contributions
ertodd+0.173
ysis+0.145
ered+0.139
verts+0.139
 quo+0.137
Neg logit contributions
ANE-0.110
awan-0.105
-0.101
UA-0.100
-0.100
Token,
Token ID837
Feature activation+4.94e-01

Pos logit contributions
ANE+3.553
awan+3.365
+3.309
UA+3.294
RAW+3.283
Neg logit contributions
ertodd-4.454
ysis-3.605
verts-3.441
ered-3.437
 quo-3.416
Token r
Token ID374
Feature activation-2.31e-01

Pos logit contributions
ertodd+1.583
ysis+1.307
verts+1.267
ered+1.253
 quo+1.250
Neg logit contributions
ANE-1.318
awan-1.271
-1.239
-1.217
UA-1.211
Token '
Token ID705
Feature activation+9.38e-02

Pos logit contributions
ANE+0.587
awan+0.561
+0.548
+0.541
UA+0.538
Neg logit contributions
ertodd-0.781
ysis-0.646
verts-0.620
ered-0.616
 quo-0.607
Token\
Token ID59
Feature activation-4.77e-01

Pos logit contributions
ertodd+0.317
ysis+0.264
verts+0.253
ered+0.252
 quo+0.248
Neg logit contributions
ANE-0.237
awan-0.227
-0.220
 srf-0.219
-0.218
Token[
Token ID58
Feature activation-1.12e+00

Pos logit contributions
ANE+1.220
awan+1.164
+1.135
UA+1.120
 srf+1.119
Neg logit contributions
ertodd-1.608
ysis-1.329
verts-1.272
ered-1.267
 quo-1.248
Token+(
Token ID33747
Feature activation-2.74e+00

Pos logit contributions
ANE+2.855
awan+2.715
+2.652
UA+2.651
+2.625
Neg logit contributions
ertodd-3.744
ysis-3.069
verts-2.917
ered-2.907
 quo-2.880
Token\
Token ID59
Feature activation-1.09e+00

Pos logit contributions
ANE+6.665
awan+6.282
UA+6.273
RAW+6.194
EMENT+6.179
Neg logit contributions
ertodd-9.121
ysis-7.472
 quo-7.028
ered-7.028
verts-6.981
TokenS
Token ID50
Feature activation-6.04e-01

Pos logit contributions
ANE+2.797
awan+2.664
+2.607
UA+2.584
+2.576
Neg logit contributions
ertodd-3.672
ysis-3.009
verts-2.870
ered-2.865
 quo-2.841
Token+
Token ID10
Feature activation-6.77e-01

Pos logit contributions
ANE+1.393
awan+1.325
+1.291
UA+1.271
+1.270
Neg logit contributions
ertodd-2.180
ysis-1.826
verts-1.753
ered-1.747
 quo-1.725
Token)\
Token ID19415
Feature activation+1.77e-01

Pos logit contributions
ANE+1.370
awan+1.287
+1.247
UA+1.234
+1.229
Neg logit contributions
ertodd-2.641
ysis-2.240
verts-2.153
ered-2.146
 quo-2.128
Tokens
Token ID82
Feature activation-2.79e-01

Pos logit contributions
ertodd+0.613
ysis+0.513
verts+0.496
ered+0.489
 quo+0.479
Neg logit contributions
ANE-0.432
awan-0.416
 srf-0.406
-0.399
EMENT-0.396
Token]
Token ID60
Feature activation+1.02e-01

Pos logit contributions
ANE+3.181
awan+3.040
+2.974
UA+2.944
RAW+2.930
Neg logit contributions
ertodd-3.809
ysis-3.099
verts-2.950
ered-2.941
 quo-2.902
Token::
Token ID3712
Feature activation-1.20e+00

Pos logit contributions
ertodd+0.380
ysis+0.321
ered+0.310
verts+0.308
 quo+0.304
Neg logit contributions
ANE-0.218
awan-0.208
-0.202
-0.201
 srf-0.200
TokenFrom
Token ID4863
Feature activation+4.48e-02

Pos logit contributions
ANE+2.535
awan+2.394
+2.321
UA+2.299
+2.281
Neg logit contributions
ertodd-4.594
ysis-3.873
verts-3.715
ered-3.704
 quo-3.674
TokenAr
Token ID3163
Feature activation+5.50e-02

Pos logit contributions
ertodd+0.170
ysis+0.143
verts+0.139
ered+0.139
 quo+0.136
Neg logit contributions
ANE-0.093
awan-0.090
 srf-0.088
-0.086
-0.086
Tokengb
Token ID22296
Feature activation-1.29e+00

Pos logit contributions
ertodd+0.137
ysis+0.104
verts+0.098
ered+0.098
 quo+0.095
Neg logit contributions
ANE-0.189
awan-0.182
-0.180
 srf-0.178
-0.178
Token($
Token ID16763
Feature activation-2.70e+00

Pos logit contributions
ANE+3.126
awan+2.966
+2.897
UA+2.873
RAW+2.866
Neg logit contributions
ertodd-4.484
ysis-3.709
verts-3.562
ered-3.542
 quo-3.505
TokenBG
Token ID40469
Feature activation-1.17e+00

Pos logit contributions
ANE+5.978
UA+5.782
RAW+5.653
awan+5.649
+5.480
Neg logit contributions
ertodd-9.607
ysis-7.881
 quo-7.727
 Jehovah-7.475
ered-7.423
Token[
Token ID58
Feature activation-1.29e+00

Pos logit contributions
ANE+2.735
awan+2.586
+2.525
UA+2.514
RAW+2.493
Neg logit contributions
ertodd-4.217
ysis-3.514
verts-3.372
ered-3.361
 quo-3.337
Token0
Token ID15
Feature activation-5.39e-01

Pos logit contributions
ANE+2.837
awan+2.679
UA+2.608
+2.606
RAW+2.575
Neg logit contributions
ertodd-4.796
ysis-4.011
verts-3.839
ered-3.826
 quo-3.817
Token],
Token ID4357
Feature activation+6.64e-02

Pos logit contributions
ANE+1.453
awan+1.387
+1.357
UA+1.346
RAW+1.337
Neg logit contributions
ertodd-1.744
ysis-1.419
verts-1.352
ered-1.343
 quo-1.332
Token$
Token ID3
Feature activation-1.41e+00

Pos logit contributions
ertodd+0.219
ysis+0.181
verts+0.174
ered+0.173
 quo+0.170
Neg logit contributions
ANE-0.172
awan-0.165
-0.160
 srf-0.159
-0.159
Token look
Token ID804
Feature activation-4.83e-01

Pos logit contributions
ANE+1.660
awan+1.594
+1.569
UA+1.550
 srf+1.549
Neg logit contributions
ertodd-1.665
ysis-1.335
ered-1.274
verts-1.271
 quo-1.248
Token up
Token ID510
Feature activation+5.43e-01

Pos logit contributions
ANE+1.400
awan+1.343
+1.322
+1.306
UA+1.305
Neg logit contributions
ertodd-1.456
ysis-1.178
ered-1.121
verts-1.119
 quo-1.100
Token from
Token ID422
Feature activation+8.71e-01

Pos logit contributions
ertodd+1.537
ysis+1.241
verts+1.186
ered+1.180
 quo+1.161
Neg logit contributions
ANE-1.645
awan-1.575
-1.558
-1.539
 srf-1.536
Token the
Token ID262
Feature activation+1.54e-01

Pos logit contributions
ertodd+2.363
ysis+1.841
verts+1.790
ered+1.783
 quo+1.743
Neg logit contributions
ANE-2.742
awan-2.646
-2.608
-2.605
EMENT-2.573
Token bridge
Token ID7696
Feature activation-1.25e+00

Pos logit contributions
ertodd+0.491
ysis+0.401
verts+0.386
ered+0.384
 quo+0.378
Neg logit contributions
ANE-0.421
awan-0.402
-0.395
-0.392
 srf-0.389
Token
Token ID30325
Feature activation-2.64e+00

Pos logit contributions
ANE+3.322
awan+3.178
+3.097
UA+3.072
+3.059
Neg logit contributions
ertodd-4.063
ysis-3.315
verts-3.162
ered-3.146
 quo-3.103
Token
Token ID231
Feature activation-6.21e-01

Pos logit contributions
ANE+4.600
awan+4.272
RAW+4.206
UA+4.199
+4.178
Neg logit contributions
ertodd-10.563
ysis-9.019
verts-8.636
 quo-8.579
ered-8.575
Token )
Token ID1267
Feature activation+9.67e-01

Pos logit contributions
ANE+1.216
awan+1.143
+1.108
UA+1.093
+1.088
Neg logit contributions
ertodd-2.462
ysis-2.090
verts-2.017
ered-2.009
 quo-1.987
Token I
Token ID314
Feature activation-5.73e-01

Pos logit contributions
ertodd+2.637
ysis+2.145
ered+2.004
verts+1.987
 quo+1.979
Neg logit contributions
ANE-3.003
awan-2.861
-2.820
 srf-2.819
-2.804
Token
Token ID447
Feature activation-1.28e-01

Pos logit contributions
ANE+1.813
awan+1.742
+1.713
UA+1.696
+1.694
Neg logit contributions
ertodd-1.584
ysis-1.244
verts-1.174
ered-1.174
 quo-1.152
Token
Token ID247
Feature activation-1.63e-02

Pos logit contributions
ANE+0.289
awan+0.274
+0.267
+0.262
UA+0.262
Neg logit contributions
ertodd-0.467
ysis-0.392
ered-0.377
verts-0.376
 quo-0.371
Token know
Token ID760
Feature activation-4.85e-01

Pos logit contributions
ANE+1.009
awan+0.970
+0.963
 srf+0.961
UA+0.953
Neg logit contributions
ertodd-0.791
ysis-0.613
ered-0.591
verts-0.580
 quo-0.577
Token this
Token ID428
Feature activation+1.28e-01

Pos logit contributions
ANE+1.493
awan+1.437
+1.411
 srf+1.406
+1.398
Neg logit contributions
ertodd-1.368
ysis-1.092
ered-1.040
verts-1.038
 quo-1.022
Token was
Token ID373
Feature activation-4.74e-01

Pos logit contributions
ertodd+0.336
ysis+0.266
verts+0.257
ered+0.255
 quo+0.252
Neg logit contributions
ANE-0.414
awan-0.400
 srf-0.397
-0.394
-0.391
Token a
Token ID257
Feature activation+3.19e-01

Pos logit contributions
ANE+1.390
awan+1.341
+1.307
 srf+1.299
+1.296
Neg logit contributions
ertodd-1.411
ysis-1.140
verts-1.087
ered-1.086
 quo-1.070
Token totally
Token ID6635
Feature activation-7.14e-01

Pos logit contributions
ertodd+1.010
ysis+0.844
ered+0.813
verts+0.812
 quo+0.804
Neg logit contributions
ANE-0.848
awan-0.816
-0.800
 srf-0.789
-0.786
Token biased
Token ID21925
Feature activation-2.63e+00

Pos logit contributions
ANE+1.827
awan+1.745
+1.703
+1.684
UA+1.683
Neg logit contributions
ertodd-2.401
ysis-1.985
verts-1.899
ered-1.896
 quo-1.870
Token decision
Token ID2551
Feature activation-2.45e-01

Pos logit contributions
ANE+7.358
awan+7.067
+6.932
EMENT+6.930
UA+6.909
Neg logit contributions
ertodd-8.138
ysis-6.359
verts-5.988
ered-5.922
 quo-5.781
Token,
Token ID11
Feature activation-1.46e-01

Pos logit contributions
ANE+0.785
awan+0.755
+0.742
 srf+0.737
+0.736
Neg logit contributions
ertodd-0.667
ysis-0.524
verts-0.497
ered-0.494
 quo-0.488
Token was
Token ID373
Feature activation-1.01e+00

Pos logit contributions
ANE+0.472
awan+0.455
+0.448
 srf+0.446
+0.445
Neg logit contributions
ertodd-0.386
ysis-0.304
verts-0.288
ered-0.285
 quo-0.284
Token the
Token ID262
Feature activation-6.33e-01

Pos logit contributions
ANE+2.900
awan+2.780
+2.721
UA+2.696
+2.690
Neg logit contributions
ertodd-3.061
ysis-2.461
verts-2.338
ered-2.325
 quo-2.292
Token fact
Token ID1109
Feature activation-1.08e-01

Pos logit contributions
ANE+1.853
awan+1.780
+1.743
+1.725
UA+1.724
Neg logit contributions
ertodd-1.896
ysis-1.526
verts-1.452
ered-1.443
 quo-1.423
Token
Token ID198
Feature activation-9.25e-02

Pos logit contributions
ertodd+0.554
ysis+0.424
verts+0.401
ered+0.401
 quo+0.389
Neg logit contributions
ANE-0.759
awan-0.733
 srf-0.732
-0.721
senal-0.720
TokenResults
Token ID25468
Feature activation+2.52e-01

Pos logit contributions
ANE+0.199
 srf+0.193
awan+0.191
senal+0.186
+0.184
Neg logit contributions
ertodd-0.339
ysis-0.290
verts-0.282
ered-0.281
 quo-0.273
Token and
Token ID290
Feature activation-7.99e-01

Pos logit contributions
ertodd+0.657
ysis+0.511
verts+0.479
ered+0.478
 quo+0.469
Neg logit contributions
ANE-0.834
awan-0.805
-0.790
-0.784
UA-0.783
Token achievements
Token ID16970
Feature activation-2.41e-01

Pos logit contributions
ANE+2.446
awan+2.355
+2.300
UA+2.286
EMENT+2.276
Neg logit contributions
ertodd-2.290
ysis-1.808
verts-1.708
ered-1.699
 quo-1.669
Token [
Token ID685
Feature activation-8.67e-01

Pos logit contributions
ANE+0.795
awan+0.767
+0.752
UA+0.747
+0.744
Neg logit contributions
ertodd-0.633
ysis-0.489
verts-0.459
ered-0.456
 quo-0.447
Token edit
Token ID4370
Feature activation-2.63e+00

Pos logit contributions
ANE+1.186
awan+1.086
+1.033
UA+1.016
+1.008
Neg logit contributions
ertodd-3.953
ysis-3.433
verts-3.322
ered-3.315
 quo-3.288
Token ]
Token ID2361
Feature activation-4.48e-01

Pos logit contributions
ANE+5.660
awan+5.460
RAW+5.364
pull+5.336
UA+5.329
Neg logit contributions
ertodd-9.411
ysis-7.793
ered-7.335
verts-7.295
 quo-7.281
Token
Token ID198
Feature activation-1.48e+00

Pos logit contributions
ANE+1.487
awan+1.435
+1.409
UA+1.398
+1.395
Neg logit contributions
ertodd-1.168
ysis-0.902
verts-0.847
ered-0.842
 quo-0.827
Token
Token ID198
Feature activation-1.62e+00

Pos logit contributions
ANE+4.345
awan+4.198
UA+4.131
RAW+4.069
+4.064
Neg logit contributions
ertodd-4.379
ysis-3.460
 quo-3.167
verts-3.150
gencies-3.118
TokenThe
Token ID464
Feature activation-5.01e-01

Pos logit contributions
ANE+3.624
awan+3.428
UA+3.341
+3.339
RAW+3.322
Neg logit contributions
ertodd-6.016
ysis-4.999
verts-4.774
ered-4.761
 quo-4.754
Token ion
Token ID22088
Feature activation-5.10e-01

Pos logit contributions
ANE+1.466
awan+1.407
+1.378
UA+1.365
+1.363
Neg logit contributions
ertodd-1.505
ysis-1.208
verts-1.146
ered-1.141
 quo-1.124
Token in
Token ID287
Feature activation+3.08e-01

Pos logit contributions
ANE+1.890
awan+1.808
+1.771
UA+1.751
+1.750
Neg logit contributions
ertodd-2.134
ysis-1.733
verts-1.650
ered-1.646
 quo-1.623
Token the
Token ID262
Feature activation-1.34e-01

Pos logit contributions
ertodd+0.903
ysis+0.725
verts+0.691
ered+0.686
 quo+0.677
Neg logit contributions
ANE-0.919
awan-0.880
-0.869
-0.862
 srf-0.860
Token first
Token ID717
Feature activation-8.48e-01

Pos logit contributions
ANE+0.370
awan+0.353
+0.347
+0.347
 srf+0.344
Neg logit contributions
ertodd-0.425
ysis-0.348
verts-0.332
ered-0.331
 quo-0.326
Token quarter
Token ID3860
Feature activation+3.97e-01

Pos logit contributions
ANE+2.224
awan+2.124
+2.074
UA+2.052
+2.049
Neg logit contributions
ertodd-2.804
ysis-2.301
verts-2.198
ered-2.190
 quo-2.161
Token to
Token ID284
Feature activation-5.21e-01

Pos logit contributions
ertodd+1.133
ysis+0.915
ered+0.882
verts+0.865
 quo+0.860
Neg logit contributions
ANE-1.199
awan-1.147
 srf-1.139
-1.123
-1.118
Token lobby
Token ID10866
Feature activation-2.60e+00

Pos logit contributions
ANE+1.517
awan+1.450
+1.427
UA+1.415
+1.413
Neg logit contributions
ertodd-1.571
ysis-1.268
ered-1.207
verts-1.205
 quo-1.187
Token on
Token ID319
Feature activation-8.37e-01

Pos logit contributions
ANE+7.223
awan+6.948
UA+6.780
EMENT+6.713
ARI+6.538
Neg logit contributions
ertodd-7.725
ysis-6.118
verts-5.717
gencies-5.692
 quo-5.684
Token domestic
Token ID5928
Feature activation+9.67e-01

Pos logit contributions
ANE+2.113
awan+2.019
+1.962
UA+1.948
EMENT+1.934
Neg logit contributions
ertodd-2.840
ysis-2.335
verts-2.226
ered-2.214
 quo-2.192
Token spying
Token ID23649
Feature activation+5.78e-02

Pos logit contributions
ertodd+2.685
ysis+2.180
verts+2.092
ered+2.089
 Jehovah+2.039
Neg logit contributions
ANE-2.954
 srf-2.816
awan-2.813
-2.768
-2.761
Token legislation
Token ID5520
Feature activation-3.91e-01

Pos logit contributions
ertodd+0.162
ysis+0.130
verts+0.125
ered+0.124
 quo+0.122
Neg logit contributions
ANE-0.179
awan-0.171
 srf-0.168
-0.168
-0.167
Token and
Token ID290
Feature activation+9.09e-02

Pos logit contributions
ANE+1.119
awan+1.069
+1.047
 srf+1.041
+1.037
Neg logit contributions
ertodd-1.196
ysis-0.969
verts-0.926
ered-0.925
 quo-0.910
Token
Token ID198
Feature activation-4.14e-01

Pos logit contributions
ertodd+0.104
ysis+0.080
verts+0.075
ered+0.075
 quo+0.073
Neg logit contributions
ANE-0.137
awan-0.133
-0.130
 srf-0.130
UA-0.129
TokenIndeed
Token ID17854
Feature activation+1.71e-01

Pos logit contributions
ANE+1.106
awan+1.057
 srf+1.035
+1.031
+1.020
Neg logit contributions
ertodd-1.344
ysis-1.101
verts-1.052
ered-1.051
 quo-1.033
Token,
Token ID11
Feature activation-5.49e-01

Pos logit contributions
ertodd+0.556
ysis+0.454
verts+0.434
ered+0.429
 quo+0.424
Neg logit contributions
ANE-0.457
awan-0.439
-0.428
-0.423
UA-0.423
Token about
Token ID546
Feature activation-3.20e-01

Pos logit contributions
ANE+1.705
awan+1.641
+1.609
UA+1.594
+1.592
Neg logit contributions
ertodd-1.551
ysis-1.224
verts-1.157
ered-1.151
 quo-1.132
Token an
Token ID281
Feature activation-4.82e-01

Pos logit contributions
ANE+0.968
awan+0.929
+0.909
UA+0.902
 srf+0.901
Neg logit contributions
ertodd-0.927
ysis-0.739
verts-0.702
ered-0.700
 quo-0.689
Token hour
Token ID1711
Feature activation-2.60e+00

Pos logit contributions
ANE+1.391
awan+1.335
+1.305
UA+1.296
+1.293
Neg logit contributions
ertodd-1.467
ysis-1.179
verts-1.120
ered-1.119
 quo-1.102
Token before
Token ID878
Feature activation-1.40e+00

Pos logit contributions
ANE+5.797
awan+5.644
+5.407
RAW+5.355
EMENT+5.308
Neg logit contributions
ertodd-9.128
ysis-7.479
verts-7.212
ered-6.999
 quo-6.946
Token the
Token ID262
Feature activation+4.96e-01

Pos logit contributions
ANE+4.438
awan+4.307
+4.222
RAW+4.179
UA+4.177
Neg logit contributions
ertodd-3.754
ysis-2.898
verts-2.759
ered-2.721
 quo-2.648
Token festivities
Token ID42735
Feature activation+1.34e+00

Pos logit contributions
ertodd+1.589
ysis+1.321
ered+1.261
verts+1.252
 quo+1.251
Neg logit contributions
ANE-1.323
awan-1.262
 srf-1.236
-1.230
-1.228
Token started
Token ID2067
Feature activation+4.45e-01

Pos logit contributions
ertodd+3.417
ysis+2.652
ered+2.584
 quo+2.542
verts+2.516
Neg logit contributions
ANE-4.377
 srf-4.145
awan-4.127
senal-4.126
UA-4.101
Token at
Token ID379
Feature activation-2.17e-01

Pos logit contributions
ertodd+1.345
ysis+1.088
ered+1.048
verts+1.039
 quo+1.033
Neg logit contributions
ANE-1.274
awan-1.216
-1.191
UA-1.189
 srf-1.188
Tokenstring
Token ID8841
Feature activation-5.68e-01

Pos logit contributions
ANE+1.738
awan+1.660
+1.615
UA+1.602
+1.593
Neg logit contributions
ertodd-2.407
ysis-1.992
verts-1.894
ered-1.891
 quo-1.879
Tokenformat
Token ID18982
Feature activation-2.35e-01

Pos logit contributions
ANE+1.407
awan+1.339
+1.309
UA+1.291
+1.291
Neg logit contributions
ertodd-1.957
ysis-1.625
verts-1.554
ered-1.553
 quo-1.528
Token Switch
Token ID14645
Feature activation+8.18e-01

Pos logit contributions
ANE+0.606
awan+0.577
+0.566
+0.558
UA+0.557
Neg logit contributions
ertodd-0.784
ysis-0.647
verts-0.619
ered-0.619
 quo-0.608
Token ($
Token ID7198
Feature activation-1.61e+00

Pos logit contributions
ertodd+2.481
ysis+2.007
ered+1.956
verts+1.931
 quo+1.888
Neg logit contributions
ANE-2.313
awan-2.204
-2.183
-2.178
EMENT-2.129
TokenAl
Token ID2348
Feature activation-4.30e-01

Pos logit contributions
ANE+4.016
awan+3.823
UA+3.741
+3.721
RAW+3.707
Neg logit contributions
ertodd-5.515
ysis-4.516
 quo-4.288
ered-4.275
verts-4.263
Tokenign
Token ID570
Feature activation-2.58e+00

Pos logit contributions
ANE+1.514
awan+1.462
+1.443
+1.427
UA+1.424
Neg logit contributions
ertodd-1.031
ysis-0.779
verts-0.729
ered-0.726
 quo-0.707
Token)
Token ID8
Feature activation+2.96e-01

Pos logit contributions
ANE+5.634
EMENT+5.627
awan+5.423
UA+5.344
MENT+5.245
Neg logit contributions
ertodd-9.116
ysis-7.484
verts-7.212
 Jehovah-7.181
 quo-7.105
Token {
Token ID1391
Feature activation-8.77e-02

Pos logit contributions
ertodd+0.858
ysis+0.694
ered+0.658
verts+0.656
 quo+0.645
Neg logit contributions
ANE-0.885
awan-0.851
-0.838
-0.832
UA-0.827
Token Center
Token ID3337
Feature activation-1.66e+00

Pos logit contributions
ANE+0.259
awan+0.249
+0.244
+0.242
UA+0.241
Neg logit contributions
ertodd-0.260
ysis-0.208
verts-0.199
ered-0.198
 quo-0.195
Token {
Token ID1391
Feature activation+2.92e-01

Pos logit contributions
ANE+4.248
awan+4.037
+3.933
UA+3.915
RAW+3.898
Neg logit contributions
ertodd-5.566
ysis-4.555
verts-4.325
ered-4.280
 quo-4.233
Token $
Token ID720
Feature activation-1.82e-01

Pos logit contributions
ertodd+0.877
ysis+0.713
verts+0.689
ered+0.682
 quo+0.673
Neg logit contributions
ANE-0.838
awan-0.804
-0.789
-0.783
UA-0.778
Token
Token ID198
Feature activation+1.47e-01

Pos logit contributions
ertodd+0.490
ysis+0.380
verts+0.359
ered+0.357
 quo+0.348
Neg logit contributions
ANE-0.641
awan-0.621
 srf-0.617
-0.610
-0.603
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
ertodd+0.368
ysis+0.282
verts+0.267
ered+0.266
 quo+0.258
Neg logit contributions
ANE-0.500
awan-0.483
 srf-0.481
-0.475
senal-0.473
TokenMore
Token ID5167
Feature activation+1.31e-01

Pos logit contributions
ANE+0.744
 srf+0.730
awan+0.720
senal+0.700
+0.693
Neg logit contributions
ertodd-1.114
ysis-0.938
verts-0.911
ered-0.906
 quo-0.881
Token than
Token ID621
Feature activation-1.11e-01

Pos logit contributions
ertodd+0.392
ysis+0.320
verts+0.309
ered+0.307
 quo+0.301
Neg logit contributions
ANE-0.376
awan-0.361
-0.355
 srf-0.351
-0.349
Token an
Token ID281
Feature activation-5.77e-02

Pos logit contributions
ANE+0.334
awan+0.321
+0.316
 srf+0.314
+0.313
Neg logit contributions
ertodd-0.318
ysis-0.257
ered-0.243
verts-0.243
 quo-0.239
Token hour
Token ID1711
Feature activation-2.55e+00

Pos logit contributions
ANE+0.163
awan+0.156
 srf+0.154
+0.153
UA+0.153
Neg logit contributions
ertodd-0.177
ysis-0.143
ered-0.138
verts-0.137
 quo-0.136
Token before
Token ID878
Feature activation-1.16e+00

Pos logit contributions
ANE+6.060
awan+5.925
UA+5.577
+5.565
EMENT+5.565
Neg logit contributions
ertodd-8.656
ysis-7.023
verts-6.692
 Jehovah-6.495
 quo-6.478
Token kick
Token ID4829
Feature activation+3.04e-01

Pos logit contributions
ANE+3.579
awan+3.452
+3.366
UA+3.358
EMENT+3.331
Neg logit contributions
ertodd-3.268
ysis-2.553
verts-2.401
ered-2.400
 quo-2.354
Token-
Token ID12
Feature activation-3.60e-01

Pos logit contributions
ertodd+0.754
ysis+0.574
verts+0.537
ered+0.534
 quo+0.524
Neg logit contributions
ANE-1.045
awan-1.009
-0.992
UA-0.984
-0.983
Tokenoff
Token ID2364
Feature activation+6.46e-01

Pos logit contributions
ANE+1.116
awan+1.075
+1.053
UA+1.044
+1.042
Neg logit contributions
ertodd-1.020
ysis-0.805
verts-0.760
ered-0.757
 quo-0.745
Token Bruce
Token ID11088
Feature activation+2.88e-01

Pos logit contributions
ertodd+1.861
ysis+1.514
verts+1.452
ered+1.449
 quo+1.418
Neg logit contributions
ANE-1.915
awan-1.838
 srf-1.822
-1.822
-1.792
Token miles
Token ID4608
Feature activation-1.19e+00

Pos logit contributions
ertodd+0.331
ysis+0.279
verts+0.269
ered+0.268
 quo+0.265
Neg logit contributions
ANE-0.186
awan-0.175
-0.171
UA-0.168
-0.168
Token.
Token ID13
Feature activation-5.31e-01

Pos logit contributions
ANE+2.865
awan+2.729
+2.660
UA+2.624
EMENT+2.610
Neg logit contributions
ertodd-4.162
ysis-3.455
verts-3.304
ered-3.263
 quo-3.241
Token Eas
Token ID38647
Feature activation-1.08e+00

Pos logit contributions
ANE+1.678
awan+1.617
+1.585
UA+1.571
+1.570
Neg logit contributions
ertodd-1.463
ysis-1.149
verts-1.086
ered-1.084
 quo-1.063
Tokenily
Token ID813
Feature activation-5.55e-01

Pos logit contributions
ANE+2.971
awan+2.878
+2.785
+2.772
EMENT+2.753
Neg logit contributions
ertodd-3.365
ysis-2.762
verts-2.605
 quo-2.540
 Jehovah-2.533
Token the
Token ID262
Feature activation-2.33e-01

Pos logit contributions
ANE+1.775
awan+1.708
+1.676
UA+1.665
+1.660
Neg logit contributions
ertodd-1.509
ysis-1.183
verts-1.127
ered-1.127
 quo-1.107
Token hardest
Token ID17612
Feature activation-2.55e+00

Pos logit contributions
ANE+0.561
awan+0.536
+0.521
 srf+0.517
+0.516
Neg logit contributions
ertodd-0.813
ysis-0.680
verts-0.659
ered-0.657
 quo-0.651
Token day
Token ID1110
Feature activation-4.62e-01

Pos logit contributions
ANE+6.618
awan+6.222
+6.179
RAW+6.086
UA+6.069
Neg logit contributions
ertodd-8.229
ysis-6.633
verts-6.248
gencies-6.078
ered-6.069
Token of
Token ID286
Feature activation-5.65e-01

Pos logit contributions
ANE+1.395
awan+1.341
+1.313
UA+1.304
+1.300
Neg logit contributions
ertodd-1.343
ysis-1.071
verts-1.015
ered-1.015
 quo-0.997
Token the
Token ID262
Feature activation-5.28e-01

Pos logit contributions
ANE+1.829
awan+1.762
+1.729
UA+1.715
+1.712
Neg logit contributions
ertodd-1.521
ysis-1.185
verts-1.115
ered-1.109
 quo-1.090
Token trip
Token ID5296
Feature activation-7.51e-01

Pos logit contributions
ANE+1.494
awan+1.430
+1.397
UA+1.386
+1.385
Neg logit contributions
ertodd-1.633
ysis-1.323
verts-1.262
ered-1.257
 quo-1.240
Token,
Token ID11
Feature activation-7.52e-01

Pos logit contributions
ANE+2.036
awan+1.948
+1.904
UA+1.886
+1.881
Neg logit contributions
ertodd-2.411
ysis-1.967
verts-1.876
ered-1.871
 quo-1.844
Token a
Token ID257
Feature activation-2.00e-01

Pos logit contributions
ANE+1.726
awan+1.662
+1.630
UA+1.616
+1.614
Neg logit contributions
ertodd-1.471
ysis-1.152
verts-1.086
ered-1.081
 quo-1.063
Token chief
Token ID4039
Feature activation-5.89e-02

Pos logit contributions
ANE+0.578
awan+0.551
+0.544
UA+0.537
+0.536
Neg logit contributions
ertodd-0.603
ysis-0.488
verts-0.465
ered-0.464
 quo-0.457
Token of
Token ID286
Feature activation+3.72e-03

Pos logit contributions
ANE+0.178
awan+0.170
+0.168
 srf+0.166
UA+0.166
Neg logit contributions
ertodd-0.170
ysis-0.137
ered-0.130
verts-0.129
 quo-0.127
Token B
Token ID347
Feature activation+2.08e-01

Pos logit contributions
ertodd+0.010
ysis+0.007
verts+0.007
ered+0.007
 quo+0.007
Neg logit contributions
ANE-0.013
awan-0.012
-0.012
UA-0.012
-0.012
Tokenani
Token ID3216
Feature activation-2.70e-01

Pos logit contributions
ertodd+0.757
ysis+0.634
verts+0.608
ered+0.607
 quo+0.600
Neg logit contributions
ANE-0.476
awan-0.451
-0.440
UA-0.435
-0.434
Token Nad
Token ID21877
Feature activation-2.53e+00

Pos logit contributions
ANE+0.869
awan+0.836
+0.822
UA+0.814
+0.813
Neg logit contributions
ertodd-0.731
ysis-0.571
verts-0.538
ered-0.536
 quo-0.527
Tokenir
Token ID343
Feature activation-1.21e+00

Pos logit contributions
awan+6.658
ANE+6.584
UA+6.237
RAW+6.126
+6.073
Neg logit contributions
ertodd-7.988
ysis-6.205
verts-5.959
ered-5.830
 quo-5.787
Token and
Token ID290
Feature activation-3.65e-01

Pos logit contributions
ANE+3.394
awan+3.311
+3.190
UA+3.182
RAW+3.167
Neg logit contributions
ertodd-3.745
ysis-2.980
verts-2.838
ered-2.812
 quo-2.766
Token Saf
Token ID6895
Feature activation-1.04e+00

Pos logit contributions
ANE+1.163
awan+1.118
+1.099
UA+1.088
+1.087
Neg logit contributions
ertodd-0.997
ysis-0.783
verts-0.738
ered-0.736
 quo-0.724
Tokeniyah
Token ID46398
Feature activation-1.17e-01

Pos logit contributions
ANE+2.720
awan+2.656
UA+2.527
+2.526
RAW+2.503
Neg logit contributions
ertodd-3.426
ysis-2.790
verts-2.655
ered-2.610
 quo-2.601
Token
Token ID447
Feature activation-4.21e-01

Pos logit contributions
ANE+0.340
awan+0.325
+0.319
UA+0.316
 srf+0.316
Neg logit contributions
ertodd-0.352
ysis-0.284
verts-0.270
ered-0.269
 quo-0.266
Token Soviets
Token ID31062
Feature activation-2.08e-01

Pos logit contributions
ANE+0.106
awan+0.102
+0.100
UA+0.099
+0.099
Neg logit contributions
ertodd-0.100
ysis-0.080
verts-0.076
ered-0.075
 quo-0.074
Token,
Token ID11
Feature activation-2.51e-01

Pos logit contributions
ANE+0.640
awan+0.615
+0.603
UA+0.598
+0.596
Neg logit contributions
ertodd-0.594
ysis-0.471
verts-0.446
ered-0.444
 quo-0.437
Token
Token ID447
Feature activation-2.40e-01

Pos logit contributions
ANE+0.804
awan+0.774
+0.759
UA+0.753
+0.752
Neg logit contributions
ertodd-0.682
ysis-0.533
verts-0.503
ered-0.501
 quo-0.493
Token
Token ID251
Feature activation-9.14e-01

Pos logit contributions
ANE+0.584
awan+0.555
+0.542
UA+0.536
+0.534
Neg logit contributions
ertodd-0.837
ysis-0.693
verts-0.665
ered-0.662
 quo-0.653
Token Lad
Token ID12862
Feature activation+4.38e-02

Pos logit contributions
ANE+2.844
awan+2.752
+2.707
UA+2.672
+2.667
Neg logit contributions
ertodd-2.559
ysis-2.002
verts-1.884
ered-1.860
 quo-1.812
Tokenisl
Token ID3044
Feature activation-2.53e+00

Pos logit contributions
ertodd+0.153
ysis+0.127
verts+0.122
ered+0.122
 quo+0.119
Neg logit contributions
ANE-0.107
awan-0.101
-0.100
-0.098
 srf-0.098
Tokenav
Token ID615
Feature activation-1.25e+00

Pos logit contributions
ANE+5.120
awan+5.034
UA+4.659
RAW+4.591
+4.509
Neg logit contributions
ertodd-9.749
ysis-8.145
verts-7.850
 quo-7.773
ered-7.689
Token Sm
Token ID2439
Feature activation-7.00e-01

Pos logit contributions
ANE+3.799
awan+3.679
+3.604
UA+3.586
+3.576
Neg logit contributions
ertodd-3.579
ysis-2.791
verts-2.637
ered-2.595
 quo-2.579
Tokenol
Token ID349
Feature activation+8.29e-01

Pos logit contributions
ANE+1.805
awan+1.751
UA+1.666
RAW+1.657
EMENT+1.655
Neg logit contributions
ertodd-2.337
ysis-1.905
verts-1.815
 quo-1.805
ered-1.792
Tokenj
Token ID73
Feature activation-3.35e-02

Pos logit contributions
ertodd+2.715
ysis+2.225
verts+2.149
ered+2.142
 quo+2.088
Neg logit contributions
ANE-2.176
-2.060
 srf-2.039
awan-2.038
-2.028
Tokenak
Token ID461
Feature activation-5.20e-01

Pos logit contributions
ANE+0.089
awan+0.085
+0.084
 srf+0.083
UA+0.083
Neg logit contributions
ertodd-0.109
ysis-0.090
ered-0.086
verts-0.086
 quo-0.084
Token cancer
Token ID4890
Feature activation+9.04e-01

Pos logit contributions
ANE+0.552
awan+0.530
+0.519
UA+0.513
+0.512
Neg logit contributions
ertodd-0.608
ysis-0.495
verts-0.470
ered-0.469
 quo-0.462
Token and
Token ID290
Feature activation+1.14e-02

Pos logit contributions
ertodd+2.860
ysis+2.358
ered+2.230
verts+2.215
 quo+2.202
Neg logit contributions
ANE-2.447
awan-2.352
-2.292
UA-2.286
 srf-2.284
Token one
Token ID530
Feature activation-3.07e-01

Pos logit contributions
ertodd+0.032
ysis+0.026
ered+0.025
verts+0.024
 Jehovah+0.024
Neg logit contributions
ANE-0.035
awan-0.034
-0.033
 srf-0.033
UA-0.033
Token of
Token ID286
Feature activation+2.95e-02

Pos logit contributions
ANE+0.910
awan+0.873
+0.855
UA+0.848
+0.846
Neg logit contributions
ertodd-0.912
ysis-0.730
verts-0.692
ered-0.689
 quo-0.679
Token the
Token ID262
Feature activation-3.22e-01

Pos logit contributions
ertodd+0.078
ysis+0.061
verts+0.057
ered+0.057
 quo+0.056
Neg logit contributions
ANE-0.097
awan-0.093
-0.091
UA-0.091
-0.091
Token hardest
Token ID17612
Feature activation-2.53e+00

Pos logit contributions
ANE+0.818
awan+0.782
+0.764
UA+0.755
+0.753
Neg logit contributions
ertodd-1.083
ysis-0.899
verts-0.860
ered-0.857
 quo-0.846
Token things
Token ID1243
Feature activation-1.67e-01

Pos logit contributions
ANE+5.862
+5.415
awan+5.403
EMENT+5.401
+5.341
Neg logit contributions
ertodd-8.872
ysis-7.127
verts-6.872
ered-6.763
 quo-6.703
Token I
Token ID314
Feature activation-9.45e-01

Pos logit contributions
ANE+0.520
awan+0.501
+0.491
UA+0.488
 srf+0.487
Neg logit contributions
ertodd-0.469
ysis-0.372
verts-0.350
ered-0.350
 quo-0.344
Token have
Token ID423
Feature activation-3.30e-01

Pos logit contributions
ANE+2.797
awan+2.691
+2.632
+2.611
UA+2.601
Neg logit contributions
ertodd-2.794
ysis-2.237
verts-2.122
ered-2.095
 quo-2.068
Token dealt
Token ID11829
Feature activation-2.62e-01

Pos logit contributions
ANE+0.963
awan+0.924
+0.905
 srf+0.898
UA+0.898
Neg logit contributions
ertodd-0.993
ysis-0.798
ered-0.761
verts-0.757
 quo-0.747
Token with
Token ID351
Feature activation-1.09e+00

Pos logit contributions
ANE+0.713
awan+0.682
+0.662
+0.661
UA+0.659
Neg logit contributions
ertodd-0.841
ysis-0.680
verts-0.656
ered-0.641
 quo-0.637
Token!
Token ID0
Feature activation+9.59e-01

Pos logit contributions
ertodd+3.013
ysis+2.393
verts+2.291
ered+2.289
 Jehovah+2.240
Neg logit contributions
ANE-3.224
awan-3.159
-3.092
 srf-3.055
-3.042
Token
Token ID198
Feature activation-2.33e-02

Pos logit contributions
ertodd+2.444
ysis+1.878
verts+1.781
ered+1.778
 Jehovah+1.727
Neg logit contributions
ANE-3.178
awan-3.110
-3.028
 srf-3.012
-2.995
Token
Token ID198
Feature activation-4.57e-01

Pos logit contributions
ANE+0.078
awan+0.075
+0.074
 srf+0.073
UA+0.073
Neg logit contributions
ertodd-0.060
ysis-0.046
verts-0.043
ered-0.043
 quo-0.042
TokenBob
Token ID18861
Feature activation+1.30e-01

Pos logit contributions
ANE+1.138
awan+1.084
+1.058
UA+1.047
+1.044
Neg logit contributions
ertodd-1.572
ysis-1.300
verts-1.243
ered-1.238
 quo-1.224
Tokenbi
Token ID8482
Feature activation-4.57e-01

Pos logit contributions
ertodd+0.369
ysis+0.294
verts+0.279
ered+0.277
 quo+0.271
Neg logit contributions
ANE-0.397
awan-0.382
-0.376
-0.372
UA-0.371
Token Krist
Token ID14912
Feature activation-2.52e+00

Pos logit contributions
ANE+1.365
awan+1.308
+1.294
 srf+1.273
+1.269
Neg logit contributions
ertodd-1.323
ysis-1.087
ered-1.021
verts-1.020
 quo-1.001
Tokenina
Token ID1437
Feature activation-9.04e-01

Pos logit contributions
ANE+6.413
awan+6.359
RAW+5.928
UA+5.814
pull+5.752
Neg logit contributions
ertodd-8.046
ysis-6.416
verts-6.106
 quo-6.095
 Jehovah-6.043
Token celebrates
Token ID24538
Feature activation-3.81e-01

Pos logit contributions
ANE+2.812
awan+2.716
+2.653
UA+2.638
+2.627
Neg logit contributions
ertodd-2.543
ysis-1.994
verts-1.874
ered-1.865
 quo-1.843
Token Whitney
Token ID34701
Feature activation-4.39e-01

Pos logit contributions
ANE+1.137
awan+1.092
+1.071
UA+1.061
+1.059
Neg logit contributions
ertodd-1.116
ysis-0.894
verts-0.848
ered-0.845
 quo-0.831
Token Houston
Token ID6995
Feature activation-4.20e-01

Pos logit contributions
ANE+1.189
awan+1.135
+1.111
UA+1.100
+1.098
Neg logit contributions
ertodd-1.415
ysis-1.153
verts-1.093
ered-1.091
 quo-1.078
Token's
Token ID338
Feature activation+3.41e-01

Pos logit contributions
ANE+1.193
awan+1.144
+1.120
UA+1.109
+1.107
Neg logit contributions
ertodd-1.292
ysis-1.044
verts-0.992
ered-0.988
 quo-0.974
Token 1
Token ID352
Feature activation+2.02e-01

Pos logit contributions
ertodd+2.293
ysis+1.864
ered+1.767
 quo+1.749
verts+1.735
Neg logit contributions
ANE-2.703
awan-2.583
-2.561
-2.548
 srf-2.539
Token-
Token ID12
Feature activation-4.90e-01

Pos logit contributions
ertodd+0.609
ysis+0.497
ered+0.475
verts+0.470
 quo+0.462
Neg logit contributions
ANE-0.577
awan-0.555
-0.544
-0.543
 srf-0.541
Token0
Token ID15
Feature activation-6.80e-02

Pos logit contributions
ANE+1.039
awan+0.976
+0.956
 srf+0.953
+0.944
Neg logit contributions
ertodd-1.842
ysis-1.575
ered-1.525
verts-1.523
 quo-1.497
Token [
Token ID685
Feature activation-6.21e-02

Pos logit contributions
ANE+0.212
awan+0.203
+0.199
+0.198
UA+0.198
Neg logit contributions
ertodd-0.191
ysis-0.151
verts-0.143
ered-0.143
 quo-0.140
TokenEvent
Token ID9237
Feature activation+2.03e-01

Pos logit contributions
ANE+0.132
awan+0.125
+0.120
 srf+0.120
+0.119
Neg logit contributions
ertodd-0.233
ysis-0.198
verts-0.192
ered-0.191
 quo-0.189
Token "
Token ID366
Feature activation-2.51e+00

Pos logit contributions
ertodd+0.546
ysis+0.433
verts+0.413
ered+0.408
 quo+0.402
Neg logit contributions
ANE-0.653
awan-0.627
-0.616
UA-0.610
-0.609
Token78
Token ID3695
Feature activation-2.76e-01

Pos logit contributions
ANE+5.527
awan+5.274
+5.256
UA+5.244
RAW+5.241
Neg logit contributions
ertodd-9.081
ysis-7.505
verts-7.107
 quo-7.106
ered-7.056
Tokenth
Token ID400
Feature activation-1.16e+00

Pos logit contributions
ANE+0.788
awan+0.756
+0.740
UA+0.732
+0.731
Neg logit contributions
ertodd-0.848
ysis-0.685
verts-0.651
ered-0.648
 quo-0.639
Token Tata
Token ID49963
Feature activation-9.97e-02

Pos logit contributions
ANE+3.542
awan+3.385
+3.328
UA+3.309
RAW+3.296
Neg logit contributions
ertodd-3.371
ysis-2.656
verts-2.511
ered-2.496
 quo-2.462
Token Steel
Token ID7851
Feature activation-7.55e-01

Pos logit contributions
ANE+0.298
awan+0.287
+0.281
UA+0.278
+0.278
Neg logit contributions
ertodd-0.293
ysis-0.234
verts-0.221
ered-0.220
 quo-0.217
Token Chess
Token ID25774
Feature activation-4.15e-01

Pos logit contributions
ANE+2.270
awan+2.185
+2.139
UA+2.120
+2.108
Neg logit contributions
ertodd-2.205
ysis-1.754
verts-1.658
ered-1.642
 quo-1.626
Token(
Token ID7
Feature activation-1.24e+00

Pos logit contributions
ANE+1.227
awan+1.176
+1.142
UA+1.134
RAW+1.131
Neg logit contributions
ertodd-1.578
ysis-1.290
verts-1.231
ered-1.223
 quo-1.214
Token0
Token ID15
Feature activation-5.96e-01

Pos logit contributions
ANE+3.679
awan+3.537
+3.468
UA+3.459
RAW+3.441
Neg logit contributions
ertodd-3.628
ysis-2.881
verts-2.719
ered-2.708
 quo-2.686
Token,
Token ID11
Feature activation+1.52e-01

Pos logit contributions
ANE+1.562
awan+1.492
+1.455
UA+1.442
+1.437
Neg logit contributions
ertodd-1.972
ysis-1.616
verts-1.542
ered-1.534
 quo-1.518
Token0
Token ID15
Feature activation-5.77e-01

Pos logit contributions
ertodd+0.556
ysis+0.471
verts+0.455
ered+0.452
 quo+0.444
Neg logit contributions
ANE-0.342
awan-0.324
-0.314
 srf-0.311
-0.309
Token,
Token ID11
Feature activation-2.72e-01

Pos logit contributions
ANE+1.491
awan+1.426
+1.387
UA+1.377
+1.368
Neg logit contributions
ertodd-1.927
ysis-1.583
verts-1.511
ered-1.504
 quo-1.490
Token($
Token ID16763
Feature activation-2.51e+00

Pos logit contributions
ANE+0.584
awan+0.552
+0.536
 srf+0.529
+0.528
Neg logit contributions
ertodd-1.025
ysis-0.867
verts-0.837
ered-0.833
 quo-0.820
TokenSR
Token ID12562
Feature activation-1.21e+00

Pos logit contributions
ANE+4.959
UA+4.706
awan+4.562
RAW+4.529
+4.407
Neg logit contributions
ertodd-9.707
ysis-8.044
 quo-7.875
 Jehovah-7.770
ered-7.668
Token.
Token ID13
Feature activation-1.23e+00

Pos logit contributions
ANE+2.718
awan+2.592
UA+2.499
+2.496
RAW+2.485
Neg logit contributions
ertodd-4.367
ysis-3.661
ered-3.513
verts-3.511
 quo-3.479
TokenWidth
Token ID30916
Feature activation-1.06e+00

Pos logit contributions
ANE+2.142
awan+1.982
UA+1.922
+1.916
RAW+1.902
Neg logit contributions
ertodd-5.199
ysis-4.427
ered-4.243
 quo-4.238
verts-4.231
Token),
Token ID828
Feature activation+3.70e-01

Pos logit contributions
ANE+2.632
awan+2.507
+2.444
UA+2.430
RAW+2.420
Neg logit contributions
ertodd-3.592
ysis-2.960
verts-2.812
ered-2.806
 quo-2.780
Token($
Token ID16763
Feature activation-1.91e+00

Pos logit contributions
ertodd+1.365
ysis+1.151
verts+1.109
ered+1.106
 quo+1.090
Neg logit contributions
ANE-0.821
awan-0.779
-0.754
 srf-0.743
-0.743
Token the
Token ID262
Feature activation-9.06e-02

Pos logit contributions
ertodd+2.092
ysis+1.650
ered+1.583
verts+1.547
 quo+1.532
Neg logit contributions
ANE-2.642
awan-2.474
-2.468
UA-2.463
 srf-2.460
Token bye
Token ID33847
Feature activation-1.56e-01

Pos logit contributions
ANE+0.257
awan+0.245
+0.240
UA+0.239
+0.238
Neg logit contributions
ertodd-0.280
ysis-0.228
verts-0.217
ered-0.217
 quo-0.214
Token week
Token ID1285
Feature activation-3.54e-01

Pos logit contributions
ANE+0.416
awan+0.394
+0.390
 srf+0.385
+0.384
Neg logit contributions
ertodd-0.510
ysis-0.418
verts-0.405
ered-0.401
 quo-0.397
Token,
Token ID11
Feature activation+1.80e-01

Pos logit contributions
ANE+0.999
awan+0.951
+0.938
 srf+0.927
UA+0.925
Neg logit contributions
ertodd-1.100
ysis-0.896
ered-0.855
verts-0.855
 quo-0.845
Token because
Token ID780
Feature activation-9.30e-02

Pos logit contributions
ertodd+0.523
ysis+0.424
verts+0.401
ered+0.400
 quo+0.400
Neg logit contributions
ANE-0.540
awan-0.513
-0.507
RAW-0.502
 srf-0.502
Token Jord
Token ID38317
Feature activation-2.50e+00

Pos logit contributions
ANE+0.299
awan+0.287
+0.283
 srf+0.280
UA+0.280
Neg logit contributions
ertodd-0.251
ysis-0.197
ered-0.186
verts-0.186
 quo-0.183
Tokeny
Token ID88
Feature activation-7.46e-01

Pos logit contributions
ANE+6.162
awan+5.959
UA+5.607
+5.522
EMENT+5.476
Neg logit contributions
ertodd-8.568
ysis-6.994
verts-6.757
 quo-6.592
 Jehovah-6.559
Token Nelson
Token ID12996
Feature activation-1.36e+00

Pos logit contributions
ANE+1.766
awan+1.677
+1.638
+1.619
UA+1.614
Neg logit contributions
ertodd-2.648
ysis-2.209
verts-2.121
ered-2.117
 quo-2.092
Token awaits
Token ID37180
Feature activation-2.08e-02

Pos logit contributions
ANE+4.170
awan+4.081
+3.957
+3.930
UA+3.923
Neg logit contributions
ertodd-3.806
ysis-2.942
verts-2.771
ered-2.721
 quo-2.656
Token.
Token ID13
Feature activation-1.47e-01

Pos logit contributions
ANE+0.064
awan+0.061
+0.060
 srf+0.060
+0.059
Neg logit contributions
ertodd-0.059
ysis-0.048
ered-0.045
verts-0.045
 quo-0.045
Token
Token ID198
Feature activation+2.51e-01

Pos logit contributions
ANE+0.476
awan+0.459
+0.450
UA+0.446
+0.446
Neg logit contributions
ertodd-0.397
ysis-0.310
verts-0.292
ered-0.290
 quo-0.285
Token neurons
Token ID16890
Feature activation+2.83e-01

Pos logit contributions
ANE+0.202
awan+0.194
+0.190
UA+0.188
+0.188
Neg logit contributions
ertodd-0.206
ysis-0.165
verts-0.157
ered-0.156
 quo-0.154
Token activated
Token ID13906
Feature activation+5.98e-01

Pos logit contributions
ertodd+0.760
ysis+0.596
ered+0.567
verts+0.562
 quo+0.550
Neg logit contributions
ANE-0.917
awan-0.879
-0.865
 srf-0.861
UA-0.860
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
ertodd+1.904
ysis+1.552
verts+1.501
ered+1.499
 quo+1.482
Neg logit contributions
ANE-1.625
awan-1.552
-1.512
UA-1.496
RAW-1.494
Token
Token ID198
Feature activation+1.06e-01

Pos logit contributions
ANE+0.595
awan+0.573
+0.563
UA+0.559
+0.557
Neg logit contributions
ertodd-0.511
ysis-0.399
verts-0.375
ered-0.373
 quo-0.369
Token
Token ID198
Feature activation-3.68e-01

Pos logit contributions
ertodd+0.270
ysis+0.207
verts+0.195
ered+0.195
 quo+0.190
Neg logit contributions
ANE-0.358
awan-0.345
-0.339
 srf-0.339
-0.336
TokenKrist
Token ID40756
Feature activation-2.50e+00

Pos logit contributions
ANE+0.954
awan+0.912
+0.889
 srf+0.882
+0.878
Neg logit contributions
ertodd-1.226
ysis-1.008
verts-0.965
ered-0.961
 quo-0.946
Tokenofer
Token ID30288
Feature activation-1.09e+00

Pos logit contributions
ANE+6.821
awan+6.766
UA+6.371
pull+6.239
RAW+6.223
Neg logit contributions
ertodd-7.475
ysis-5.839
 quo-5.699
verts-5.614
 Jehovah-5.454
Token B
Token ID347
Feature activation-4.22e-01

Pos logit contributions
ANE+3.426
awan+3.328
UA+3.240
+3.231
EMENT+3.208
Neg logit contributions
ertodd-2.983
ysis-2.285
verts-2.139
 quo-2.127
ered-2.121
Tokenouch
Token ID7673
Feature activation+3.67e-01

Pos logit contributions
ANE+1.187
awan+1.139
+1.104
UA+1.099
EMENT+1.092
Neg logit contributions
ertodd-1.318
ysis-1.063
verts-1.013
ered-1.003
 quo-0.995
Tokenard
Token ID446
Feature activation+5.63e-01

Pos logit contributions
ertodd+1.252
ysis+1.046
ered+1.011
verts+1.005
 quo+0.978
Neg logit contributions
ANE-0.911
-0.857
 srf-0.854
-0.848
awan-0.843
Token,
Token ID11
Feature activation+6.38e-01

Pos logit contributions
ertodd+1.691
ysis+1.373
ered+1.310
verts+1.304
 quo+1.276
Neg logit contributions
ANE-1.630
awan-1.551
-1.535
 srf-1.516
-1.513
Token a
Token ID257
Feature activation+3.08e-02

Pos logit contributions
ANE+0.506
awan+0.486
+0.479
UA+0.476
 srf+0.474
Neg logit contributions
ertodd-0.411
ysis-0.320
verts-0.306
ered-0.302
 quo-0.298
Token premiere
Token ID19245
Feature activation+6.86e-01

Pos logit contributions
ertodd+0.096
ysis+0.079
verts+0.075
ered+0.075
 quo+0.074
Neg logit contributions
ANE-0.086
awan-0.082
-0.081
UA-0.080
EMENT-0.079
Token ninja
Token ID37049
Feature activation+4.72e-01

Pos logit contributions
ertodd+1.900
ysis+1.573
ered+1.481
verts+1.469
 quo+1.467
Neg logit contributions
ANE-2.072
awan-1.967
-1.964
 srf-1.943
UA-1.941
Token in
Token ID287
Feature activation+4.54e-01

Pos logit contributions
ertodd+1.441
ysis+1.181
ered+1.129
verts+1.125
 quo+1.114
Neg logit contributions
ANE-1.331
-1.254
awan-1.252
UA-1.239
 srf-1.238
Token the
Token ID262
Feature activation+1.73e-01

Pos logit contributions
ertodd+1.181
ysis+0.920
verts+0.875
ered+0.865
 quo+0.852
Neg logit contributions
ANE-1.491
awan-1.434
-1.409
UA-1.405
-1.403
Token Foot
Token ID7870
Feature activation+1.98e+00

Pos logit contributions
ertodd+0.503
ysis+0.407
ered+0.385
verts+0.384
 quo+0.381
Neg logit contributions
ANE-0.516
awan-0.493
-0.487
UA-0.483
 srf-0.483
Token,
Token ID11
Feature activation+2.95e-02

Pos logit contributions
ertodd+3.387
ysis+2.289
ered+2.239
verts+2.096
 quo+2.020
Neg logit contributions
ANE-8.025
 srf-7.781
-7.734
awan-7.691
-7.660
Token and
Token ID290
Feature activation+1.31e-01

Pos logit contributions
ertodd+0.082
ysis+0.066
verts+0.063
ered+0.062
 quo+0.062
Neg logit contributions
ANE-0.091
awan-0.087
-0.086
UA-0.085
EMENT-0.085
Token as
Token ID355
Feature activation+3.48e-01

Pos logit contributions
ertodd+0.353
ysis+0.279
ered+0.267
verts+0.265
 quo+0.262
Neg logit contributions
ANE-0.420
awan-0.401
-0.395
UA-0.393
 srf-0.393
Token a
Token ID257
Feature activation+5.50e-02

Pos logit contributions
ertodd+0.898
ysis+0.699
verts+0.659
ered+0.656
 quo+0.648
Neg logit contributions
ANE-1.156
awan-1.107
-1.093
UA-1.088
 srf-1.087
Token reward
Token ID6721
Feature activation+7.22e-01

Pos logit contributions
ertodd+0.169
ysis+0.137
verts+0.131
ered+0.131
 quo+0.130
Neg logit contributions
ANE-0.156
awan-0.148
-0.147
UA-0.145
 srf-0.144
Token option
Token ID3038
Feature activation-1.39e-01

Pos logit contributions
ertodd+1.332
ysis+1.076
ered+1.019
verts+1.016
 quo+1.001
Neg logit contributions
ANE-1.458
awan-1.402
-1.378
 srf-1.361
UA-1.355
Token
Token ID447
Feature activation+3.02e-02

Pos logit contributions
ANE+0.473
awan+0.457
+0.448
UA+0.445
+0.445
Neg logit contributions
ertodd-0.353
ysis-0.270
verts-0.253
ered-0.251
 quo-0.246
Token
Token ID247
Feature activation+2.26e-01

Pos logit contributions
ertodd+0.112
ysis+0.094
verts+0.091
ered+0.090
 quo+0.089
Neg logit contributions
ANE-0.067
awan-0.063
-0.061
UA-0.061
-0.061
Token adopted
Token ID8197
Feature activation+7.45e-01

Pos logit contributions
ertodd+0.629
ysis+0.497
verts+0.471
ered+0.469
 quo+0.462
Neg logit contributions
ANE-0.710
awan-0.681
-0.669
 srf-0.662
UA-0.662
Token by
Token ID416
Feature activation-3.93e-02

Pos logit contributions
ertodd+2.200
ysis+1.762
verts+1.697
ered+1.696
 quo+1.679
Neg logit contributions
ANE-2.212
awan-2.092
 srf-2.062
-2.060
UA-2.046
Token Pu
Token ID11634
Feature activation+1.75e+00

Pos logit contributions
ANE+0.123
awan+0.119
+0.116
UA+0.115
+0.115
Neg logit contributions
ertodd-0.110
ysis-0.087
verts-0.082
ered-0.081
 quo-0.080
Tokenig
Token ID328
Feature activation-6.63e-01

Pos logit contributions
ertodd+4.738
ysis+3.766
ered+3.693
verts+3.661
 quo+3.497
Neg logit contributions
ANE-5.458
senal-5.408
 srf-5.384
-5.269
-5.142
Tokendem
Token ID9536
Feature activation-5.00e-01

Pos logit contributions
ANE+1.333
awan+1.266
+1.219
UA+1.206
+1.201
Neg logit contributions
ertodd-2.587
ysis-2.193
verts-2.108
ered-2.102
 quo-2.083
Tokenont
Token ID756
Feature activation-7.16e-01

Pos logit contributions
ANE+1.527
awan+1.478
+1.439
UA+1.427
+1.423
Neg logit contributions
ertodd-1.433
ysis-1.137
verts-1.074
ered-1.065
 quo-1.053
Token and
Token ID290
Feature activation+3.98e-01

Pos logit contributions
ANE+2.195
awan+2.136
+2.091
UA+2.075
+2.071
Neg logit contributions
ertodd-2.008
ysis-1.586
verts-1.486
ered-1.480
 quo-1.452
Token his
Token ID465
Feature activation+8.26e-02

Pos logit contributions
ertodd+1.044
ysis+0.807
verts+0.767
ered+0.767
 quo+0.750
Neg logit contributions
ANE-1.311
awan-1.257
-1.242
 srf-1.224
-1.224
Token insofar
Token ID44061
Feature activation+2.81e-01

Pos logit contributions
ertodd+0.464
ysis+0.379
ered+0.364
verts+0.358
 quo+0.354
Neg logit contributions
ANE-0.444
awan-0.424
-0.421
 srf-0.418
-0.413
Token as
Token ID355
Feature activation+6.80e-01

Pos logit contributions
ertodd+0.795
ysis+0.636
ered+0.612
verts+0.605
 quo+0.596
Neg logit contributions
ANE-0.862
awan-0.823
-0.815
 srf-0.814
-0.805
Token mobile
Token ID5175
Feature activation+3.33e-01

Pos logit contributions
ertodd+1.729
ysis+1.361
ered+1.293
verts+1.292
 quo+1.285
Neg logit contributions
ANE-2.241
awan-2.164
 srf-2.156
-2.154
-2.118
Token teachers
Token ID7799
Feature activation+2.41e-01

Pos logit contributions
ertodd+0.937
ysis+0.759
verts+0.716
ered+0.716
 quo+0.702
Neg logit contributions
ANE-1.014
awan-0.977
-0.966
 srf-0.958
-0.958
Token are
Token ID389
Feature activation+3.58e-01

Pos logit contributions
ertodd+0.640
ysis+0.500
ered+0.478
verts+0.475
 quo+0.468
Neg logit contributions
ANE-0.781
awan-0.753
-0.749
 srf-0.742
UA-0.735
Token short
Token ID1790
Feature activation+1.85e+00

Pos logit contributions
ertodd+1.019
ysis+0.825
ered+0.794
verts+0.793
 quo+0.788
Neg logit contributions
ANE-1.073
awan-1.039
-1.029
 srf-1.025
-1.004
Tokenchanged
Token ID40985
Feature activation+4.64e-01

Pos logit contributions
ertodd+4.737
ered+3.833
ysis+3.798
verts+3.728
 quo+3.636
Neg logit contributions
ANE-5.867
awan-5.712
-5.609
-5.567
 srf-5.565
Token by
Token ID416
Feature activation+2.98e-01

Pos logit contributions
ertodd+1.427
ysis+1.167
ered+1.122
verts+1.111
 quo+1.110
Neg logit contributions
ANE-1.301
awan-1.243
 srf-1.230
-1.229
senal-1.211
Token teacher
Token ID4701
Feature activation-3.81e-01

Pos logit contributions
ertodd+0.851
ysis+0.686
verts+0.656
ered+0.651
 quo+0.644
Neg logit contributions
ANE-0.897
awan-0.863
-0.857
 srf-0.851
-0.850
Token pensions
Token ID27581
Feature activation+1.61e-01

Pos logit contributions
ANE+1.175
awan+1.130
+1.108
UA+1.098
+1.096
Neg logit contributions
ertodd-1.084
ysis-0.858
verts-0.812
ered-0.808
 quo-0.795
Token.
Token ID13
Feature activation-7.97e-02

Pos logit contributions
ertodd+0.537
ysis+0.442
verts+0.424
ered+0.423
 quo+0.420
Neg logit contributions
ANE-0.418
awan-0.398
-0.389
 srf-0.386
UA-0.385
Token In
Token ID554
Feature activation+3.14e-01

Pos logit contributions
ANE+0.653
awan+0.628
+0.619
 srf+0.613
+0.612
Neg logit contributions
ertodd-0.505
ysis-0.392
verts-0.370
ered-0.367
 quo-0.358
Token Public
Token ID5094
Feature activation+7.22e-01

Pos logit contributions
ertodd+0.885
ysis+0.705
verts+0.678
ered+0.670
 Jehovah+0.649
Neg logit contributions
ANE-0.968
awan-0.933
-0.920
 srf-0.914
EMENT-0.910
Token-
Token ID12
Feature activation+5.07e-01

Pos logit contributions
ertodd+1.886
ysis+1.485
verts+1.392
ered+1.390
 quo+1.347
Neg logit contributions
ANE-2.371
awan-2.282
-2.242
 srf-2.235
-2.222
TokenWrit
Token ID20257
Feature activation-7.62e-01

Pos logit contributions
ertodd+1.878
ysis+1.594
verts+1.553
ered+1.548
 Jehovah+1.511
Neg logit contributions
ANE-1.061
 srf-1.034
awan-1.022
senal-0.977
-0.976
Tokenters
Token ID1010
Feature activation+1.50e+00

Pos logit contributions
ANE+2.523
awan+2.435
+2.389
UA+2.369
+2.365
Neg logit contributions
ertodd-1.989
ysis-1.535
verts-1.440
ered-1.431
 quo-1.410
Token Strike
Token ID12282
Feature activation+1.82e+00

Pos logit contributions
ertodd+4.178
ysis+3.439
ered+3.268
verts+3.245
 quo+3.161
Neg logit contributions
ANE-4.405
 srf-4.222
awan-4.216
-4.172
-4.159
Token 2008
Token ID3648
Feature activation-1.36e-01

Pos logit contributions
ertodd+4.578
ysis+3.682
ered+3.617
verts+3.503
 Jehovah+3.462
Neg logit contributions
ANE-5.725
 srf-5.583
-5.517
awan-5.491
-5.458
Token01
Token ID486
Feature activation+2.26e-01

Pos logit contributions
ANE+0.352
awan+0.335
+0.327
UA+0.323
+0.323
Neg logit contributions
ertodd-0.456
ysis-0.375
verts-0.358
ered-0.357
 quo-0.352
Token04
Token ID3023
Feature activation+1.42e+00

Pos logit contributions
ertodd+0.617
ysis+0.486
verts+0.460
ered+0.459
 quo+0.450
Neg logit contributions
ANE-0.714
awan-0.689
 srf-0.681
-0.672
-0.666
Token O
Token ID440
Feature activation+1.40e-01

Pos logit contributions
ertodd+4.069
ysis+3.295
verts+3.115
ered+3.108
 quo+3.068
Neg logit contributions
ANE-4.211
awan-4.075
 srf-3.999
-3.966
-3.936
Token&
Token ID5
Feature activation-6.66e-01

Pos logit contributions
ertodd+0.417
ysis+0.336
verts+0.320
ered+0.320
 quo+0.312
Neg logit contributions
ANE-0.407
 srf-0.394
awan-0.393
-0.388
senal-0.385
Token electing
Token ID46913
Feature activation-8.10e-01

Pos logit contributions
ANE+0.629
awan+0.602
+0.592
UA+0.587
 srf+0.586
Neg logit contributions
ertodd-0.622
ysis-0.500
verts-0.475
ered-0.472
 quo-0.469
Token a
Token ID257
Feature activation-3.90e-01

Pos logit contributions
ANE+2.514
awan+2.425
+2.369
UA+2.351
+2.345
Neg logit contributions
ertodd-2.283
ysis-1.786
verts-1.686
ered-1.676
 quo-1.637
Token president
Token ID1893
Feature activation+2.79e-01

Pos logit contributions
ANE+1.118
awan+1.071
+1.049
UA+1.039
+1.037
Neg logit contributions
ertodd-1.194
ysis-0.963
verts-0.916
ered-0.912
 quo-0.900
Token would
Token ID561
Feature activation+1.84e-01

Pos logit contributions
ertodd+0.772
ysis+0.608
verts+0.576
ered+0.575
 quo+0.569
Neg logit contributions
ANE-0.883
awan-0.846
-0.830
 srf-0.829
UA-0.825
Token be
Token ID307
Feature activation-2.33e-02

Pos logit contributions
ertodd+0.503
ysis+0.393
ered+0.376
verts+0.372
 quo+0.366
Neg logit contributions
ANE-0.590
awan-0.566
-0.557
UA-0.556
 srf-0.553
Token indul
Token ID19441
Feature activation+1.86e+00

Pos logit contributions
ANE+0.068
awan+0.065
+0.064
 srf+0.064
UA+0.063
Neg logit contributions
ertodd-0.070
ysis-0.057
ered-0.054
verts-0.054
 quo-0.053
Tokenging
Token ID2667
Feature activation+6.64e-01

Pos logit contributions
ertodd+5.563
ysis+4.467
ered+4.361
verts+4.334
 quo+4.127
Neg logit contributions
ANE-5.387
 srf-5.098
-5.097
-5.079
awan-5.070
Token in
Token ID287
Feature activation-3.36e-02

Pos logit contributions
ertodd+1.963
ysis+1.585
ered+1.526
verts+1.519
 quo+1.502
Neg logit contributions
ANE-1.948
awan-1.857
-1.830
 srf-1.820
UA-1.817
Token the
Token ID262
Feature activation-2.65e-02

Pos logit contributions
ANE+0.102
awan+0.097
+0.096
UA+0.095
 srf+0.095
Neg logit contributions
ertodd-0.097
ysis-0.078
verts-0.074
ered-0.073
 quo-0.073
Token very
Token ID845
Feature activation-7.45e-01

Pos logit contributions
ANE+0.072
awan+0.069
+0.067
 srf+0.067
UA+0.067
Neg logit contributions
ertodd-0.085
ysis-0.069
verts-0.066
ered-0.066
 quo-0.066
Token reflex
Token ID24133
Feature activation+1.39e+00

Pos logit contributions
ANE+2.053
awan+1.966
+1.922
UA+1.902
+1.900
Neg logit contributions
ertodd-2.363
ysis-1.919
verts-1.827
ered-1.819
 quo-1.792
Token from
Token ID422
Feature activation+1.28e-02

Pos logit contributions
ANE+1.351
awan+1.289
+1.262
UA+1.247
+1.246
Neg logit contributions
ertodd-1.721
ysis-1.410
verts-1.346
ered-1.335
 quo-1.318
Token an
Token ID281
Feature activation-1.15e-01

Pos logit contributions
ertodd+0.036
ysis+0.028
verts+0.026
ered+0.026
 quo+0.026
Neg logit contributions
ANE-0.041
awan-0.039
-0.038
-0.038
UA-0.038
Token interpretation
Token ID10794
Feature activation-7.93e-01

Pos logit contributions
ANE+0.308
awan+0.293
+0.288
+0.287
 srf+0.287
Neg logit contributions
ertodd-0.369
ysis-0.303
ered-0.290
verts-0.286
 quo-0.285
Token of
Token ID286
Feature activation-3.92e-01

Pos logit contributions
ANE+2.376
awan+2.286
+2.242
UA+2.224
+2.212
Neg logit contributions
ertodd-2.325
ysis-1.837
verts-1.738
ered-1.721
 quo-1.686
Token the
Token ID262
Feature activation-4.29e-01

Pos logit contributions
ANE+1.285
awan+1.241
+1.218
UA+1.206
+1.204
Neg logit contributions
ertodd-1.039
ysis-0.805
verts-0.756
ered-0.752
 quo-0.737
Token word
Token ID1573
Feature activation+5.75e-01

Pos logit contributions
ANE+1.201
awan+1.147
+1.121
UA+1.113
+1.111
Neg logit contributions
ertodd-1.343
ysis-1.093
verts-1.041
ered-1.037
 quo-1.027
Token
Token ID564
Feature activation-4.78e-01

Pos logit contributions
ertodd+1.623
ysis+1.318
ered+1.249
verts+1.248
 quo+1.245
Neg logit contributions
ANE-1.758
awan-1.666
-1.637
UA-1.634
 srf-1.629
Token
Token ID250
Feature activation+2.21e-01

Pos logit contributions
ANE+1.140
awan+1.083
+1.058
+1.046
UA+1.044
Neg logit contributions
ertodd-1.692
ysis-1.403
verts-1.350
ered-1.337
 quo-1.323
Tokend
Token ID67
Feature activation+3.60e-01

Pos logit contributions
ertodd+0.769
ysis+0.647
ered+0.624
verts+0.621
 quo+0.611
Neg logit contributions
ANE-0.530
awan-0.501
 srf-0.488
-0.488
UA-0.484
Tokenisson
Token ID30927
Feature activation-6.70e-01

Pos logit contributions
ertodd+1.127
ysis+0.934
ered+0.890
verts+0.881
 quo+0.875
Neg logit contributions
ANE-0.989
awan-0.935
-0.933
 srf-0.928
-0.924
Tokenant
Token ID415
Feature activation-2.38e-01

Pos logit contributions
ANE+1.989
awan+1.912
+1.870
UA+1.852
+1.851
Neg logit contributions
ertodd-1.978
ysis-1.578
verts-1.498
ered-1.489
 quo-1.468
Token trade
Token ID3292
Feature activation+2.58e-01

Pos logit contributions
ertodd+1.517
ysis+1.242
verts+1.171
ered+1.168
 quo+1.168
Neg logit contributions
ANE-1.637
awan-1.578
-1.539
RAW-1.538
 srf-1.527
Token asset
Token ID11171
Feature activation-1.02e+00

Pos logit contributions
ertodd+0.843
ysis+0.689
verts+0.666
ered+0.665
 quo+0.660
Neg logit contributions
ANE-0.677
awan-0.645
-0.632
-0.622
RAW-0.621
Token.
Token ID13
Feature activation-1.85e-01

Pos logit contributions
ANE+2.754
awan+2.643
+2.575
+2.551
UA+2.547
Neg logit contributions
ertodd-3.278
ysis-2.674
verts-2.535
ered-2.525
 quo-2.483
Token And
Token ID843
Feature activation+4.47e-01

Pos logit contributions
ANE+0.603
awan+0.582
+0.571
UA+0.566
+0.565
Neg logit contributions
ertodd-0.492
ysis-0.382
verts-0.360
ered-0.358
 quo-0.351
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
ertodd+1.248
ysis+0.993
ered+0.952
verts+0.945
 quo+0.940
Neg logit contributions
ANE-1.381
awan-1.321
-1.310
 srf-1.297
UA-1.289
Token Padres
Token ID40188
Feature activation+2.54e-01

Pos logit contributions
ertodd+0.405
ysis+0.326
verts+0.311
ered+0.309
 quo+0.306
Neg logit contributions
ANE-0.413
awan-0.397
-0.391
-0.387
UA-0.386
Token should
Token ID815
Feature activation+3.36e-01

Pos logit contributions
ertodd+0.694
ysis+0.547
ered+0.524
verts+0.515
 quo+0.513
Neg logit contributions
ANE-0.804
awan-0.774
-0.760
-0.755
 srf-0.753
Token have
Token ID423
Feature activation+2.87e-01

Pos logit contributions
ertodd+0.905
ysis+0.709
ered+0.702
verts+0.666
 quo+0.664
Neg logit contributions
ANE-1.084
awan-1.035
UA-1.027
-1.019
 srf-1.016
Token left
Token ID1364
Feature activation-4.79e-01

Pos logit contributions
ertodd+0.811
ysis+0.650
ered+0.629
verts+0.614
 quo+0.611
Neg logit contributions
ANE-0.886
awan-0.846
-0.831
 srf-0.829
UA-0.822
Token him
Token ID683
Feature activation+4.71e-01

Pos logit contributions
ANE+1.540
awan+1.485
+1.455
UA+1.443
+1.441
Neg logit contributions
ertodd-1.297
ysis-1.010
verts-0.952
ered-0.946
 quo-0.930
Token alone
Token ID3436
Feature activation+2.43e-01

Pos logit contributions
ertodd+1.427
ysis+1.170
ered+1.130
 quo+1.114
verts+1.110
Neg logit contributions
ANE-1.359
awan-1.277
-1.269
UA-1.265
 srf-1.258
Token rates
Token ID3965
Feature activation+1.94e+00

Pos logit contributions
ertodd+2.069
ysis+1.408
verts+1.388
ered+1.334
 quo+1.250
Neg logit contributions
ANE-5.807
awan-5.645
-5.531
 srf-5.511
senal-5.483
Token,
Token ID11
Feature activation+2.59e-01

Pos logit contributions
ertodd+4.860
ered+3.992
ysis+3.971
 quo+3.952
verts+3.900
Neg logit contributions
ANE-6.050
 srf-5.887
awan-5.852
senal-5.735
-5.705
Token or
Token ID393
Feature activation-3.43e-01

Pos logit contributions
ertodd+0.665
ysis+0.519
verts+0.492
ered+0.491
 quo+0.483
Neg logit contributions
ANE-0.861
awan-0.832
-0.818
-0.812
 srf-0.810
Token at
Token ID379
Feature activation-3.21e-01

Pos logit contributions
ANE+0.991
awan+0.950
+0.932
 srf+0.923
+0.922
Neg logit contributions
ertodd-1.033
ysis-0.843
verts-0.803
ered-0.801
 quo-0.789
Token a
Token ID257
Feature activation-1.26e-03

Pos logit contributions
ANE+1.001
awan+0.962
+0.945
+0.938
 srf+0.934
Neg logit contributions
ertodd-0.896
ysis-0.713
verts-0.677
ered-0.674
 quo-0.662
Token refresh
Token ID14976
Feature activation+4.67e-01

Pos logit contributions
ANE+0.004
awan+0.004
+0.004
+0.003
 srf+0.003
Neg logit contributions
ertodd-0.004
ysis-0.003
ered-0.003
verts-0.003
 quo-0.003
Token rate
Token ID2494
Feature activation+1.10e+00

Pos logit contributions
ertodd+0.933
ysis+0.678
ered+0.648
verts+0.631
 quo+0.625
Neg logit contributions
ANE-1.809
awan-1.751
-1.725
-1.714
 srf-1.708
Token more
Token ID517
Feature activation+2.11e-01

Pos logit contributions
ertodd+2.876
ysis+2.341
ered+2.304
 quo+2.279
verts+2.232
Neg logit contributions
ANE-3.461
awan-3.346
 srf-3.317
-3.305
senal-3.302
Token likely
Token ID1884
Feature activation+3.27e-01

Pos logit contributions
ertodd+0.634
ysis+0.511
verts+0.504
ered+0.503
 quo+0.495
Neg logit contributions
ANE-0.607
awan-0.580
-0.570
 srf-0.566
-0.564
Token achieved
Token ID8793
Feature activation-4.24e-01

Pos logit contributions
ertodd+0.993
ysis+0.805
ered+0.787
verts+0.774
 quo+0.768
Neg logit contributions
ANE-0.934
awan-0.897
-0.872
 srf-0.871
-0.865
Token during
Token ID1141
Feature activation-5.57e-01

Pos logit contributions
ANE+1.199
awan+1.149
+1.125
UA+1.111
+1.110
Neg logit contributions
ertodd-1.312
ysis-1.062
verts-1.013
ered-1.011
 quo-0.996
Token Why
Token ID4162
Feature activation+3.27e-03

Pos logit contributions
ertodd+0.358
ysis+0.279
verts+0.263
ered+0.261
 quo+0.257
Neg logit contributions
ANE-0.447
awan-0.432
 srf-0.425
-0.423
UA-0.419
Token don
Token ID836
Feature activation-7.18e-01

Pos logit contributions
ertodd+0.009
ysis+0.007
verts+0.007
ered+0.007
 quo+0.007
Neg logit contributions
ANE-0.010
awan-0.010
-0.010
 srf-0.010
UA-0.010
Token
Token ID447
Feature activation+4.69e-01

Pos logit contributions
ANE+2.267
awan+2.183
+2.146
+2.130
UA+2.128
Neg logit contributions
ertodd-1.989
ysis-1.559
verts-1.459
ered-1.449
 quo-1.440
Token
Token ID247
Feature activation+5.07e-01

Pos logit contributions
ertodd+1.583
ysis+1.326
ered+1.278
verts+1.266
 quo+1.249
Neg logit contributions
ANE-1.171
awan-1.126
 srf-1.088
-1.083
senal-1.064
Tokent
Token ID83
Feature activation+3.98e-01

Pos logit contributions
ertodd+1.489
ysis+1.203
verts+1.142
ered+1.138
 quo+1.113
Neg logit contributions
ANE-1.516
awan-1.454
-1.426
 srf-1.418
UA-1.402
Token you
Token ID345
Feature activation+1.05e+00

Pos logit contributions
ertodd+1.047
ysis+0.823
verts+0.780
ered+0.777
 quo+0.768
Neg logit contributions
ANE-1.295
awan-1.250
-1.231
 srf-1.226
UA-1.214
Token trust
Token ID3774
Feature activation+1.92e-01

Pos logit contributions
ertodd+2.883
ysis+2.339
ered+2.259
verts+2.225
 quo+2.206
Neg logit contributions
ANE-3.205
 srf-3.104
senal-3.065
awan-3.049
UA-3.017
Token women
Token ID1466
Feature activation+1.31e-02

Pos logit contributions
ertodd+0.533
ysis+0.421
verts+0.400
ered+0.398
 quo+0.392
Neg logit contributions
ANE-0.602
awan-0.580
-0.571
 srf-0.566
-0.564
Token to
Token ID284
Feature activation+3.72e-01

Pos logit contributions
ertodd+0.038
ysis+0.030
verts+0.029
ered+0.029
 quo+0.028
Neg logit contributions
ANE-0.040
awan-0.038
-0.038
 srf-0.037
UA-0.037
Token make
Token ID787
Feature activation+1.36e-01

Pos logit contributions
ertodd+1.031
ysis+0.823
ered+0.800
verts+0.782
 quo+0.775
Neg logit contributions
ANE-1.153
awan-1.114
senal-1.108
 srf-1.102
-1.099
Token this
Token ID428
Feature activation-2.96e-01

Pos logit contributions
ertodd+0.383
ysis+0.306
ered+0.291
verts+0.289
 quo+0.285
Neg logit contributions
ANE-0.416
awan-0.401
-0.395
 srf-0.391
UA-0.390
Token,
Token ID11
Feature activation-9.36e-02

Pos logit contributions
ANE+2.515
awan+2.421
+2.368
UA+2.362
+2.347
Neg logit contributions
ertodd-2.602
ysis-2.071
verts-1.960
ered-1.946
 quo-1.915
Token transparency
Token ID13902
Feature activation-8.48e-01

Pos logit contributions
ANE+0.273
awan+0.262
+0.257
+0.254
UA+0.254
Neg logit contributions
ertodd-0.282
ysis-0.227
verts-0.216
ered-0.215
 quo-0.212
Token,
Token ID11
Feature activation+3.76e-01

Pos logit contributions
ANE+2.144
awan+2.053
+2.009
UA+2.000
+1.990
Neg logit contributions
ertodd-2.834
ysis-2.335
verts-2.211
ered-2.195
 quo-2.155
Token sound
Token ID2128
Feature activation+3.35e-01

Pos logit contributions
ertodd+1.062
ysis+0.846
verts+0.801
ered+0.799
 quo+0.791
Neg logit contributions
ANE-1.160
awan-1.113
-1.095
-1.083
UA-1.082
Tokenst
Token ID301
Feature activation-2.80e-01

Pos logit contributions
ertodd+1.264
ysis+1.072
verts+1.032
ered+1.030
 quo+1.018
Neg logit contributions
ANE-0.720
awan-0.672
-0.656
UA-0.644
 srf-0.643
Tokenaging
Token ID3039
Feature activation+7.12e-01

Pos logit contributions
ANE+0.812
awan+0.785
+0.759
UA+0.756
+0.753
Neg logit contributions
ertodd-0.843
ysis-0.676
verts-0.642
ered-0.636
 quo-0.631
Token,
Token ID11
Feature activation+1.99e-01

Pos logit contributions
ertodd+2.159
ysis+1.737
verts+1.654
ered+1.654
 quo+1.630
Neg logit contributions
ANE-2.061
awan-1.969
-1.932
 srf-1.909
UA-1.905
Token and
Token ID290
Feature activation-1.14e-01

Pos logit contributions
ertodd+0.557
ysis+0.442
verts+0.418
ered+0.416
 quo+0.410
Neg logit contributions
ANE-0.621
awan-0.595
-0.586
-0.579
UA-0.579
Token surprising
Token ID6452
Feature activation+2.24e-01

Pos logit contributions
ANE+0.318
awan+0.304
+0.298
UA+0.294
+0.294
Neg logit contributions
ertodd-0.357
ysis-0.291
verts-0.277
ered-0.276
 quo-0.272
Token bass
Token ID12702
Feature activation-2.47e-01

Pos logit contributions
ertodd+0.683
ysis+0.556
verts+0.530
ered+0.529
 quo+0.519
Neg logit contributions
ANE-0.642
awan-0.617
-0.603
 srf-0.597
-0.594
Token response
Token ID2882
Feature activation+2.76e-01

Pos logit contributions
ANE+0.730
awan+0.700
+0.685
 srf+0.677
UA+0.677
Neg logit contributions
ertodd-0.734
ysis-0.591
verts-0.561
ered-0.558
 quo-0.550
Token of
Token ID286
Feature activation-5.44e-02

Pos logit contributions
ANE+3.649
awan+3.502
+3.429
UA+3.413
+3.380
Neg logit contributions
ertodd-3.962
ysis-3.156
verts-3.009
ered-2.967
 quo-2.905
Token the
Token ID262
Feature activation+2.12e-02

Pos logit contributions
ANE+0.184
awan+0.178
+0.175
+0.174
UA+0.173
Neg logit contributions
ertodd-0.138
ysis-0.106
verts-0.100
ered-0.099
 quo-0.098
Token galaxy
Token ID16161
Feature activation-5.25e-01

Pos logit contributions
ertodd+0.067
ysis+0.055
verts+0.053
ered+0.052
 quo+0.052
Neg logit contributions
ANE-0.058
awan-0.056
-0.054
-0.054
UA-0.054
Token,
Token ID11
Feature activation-2.34e-01

Pos logit contributions
ANE+1.398
awan+1.335
+1.305
UA+1.290
+1.290
Neg logit contributions
ertodd-1.708
ysis-1.401
verts-1.336
ered-1.335
 quo-1.317
Token and
Token ID290
Feature activation-2.92e-02

Pos logit contributions
ANE+0.721
awan+0.691
+0.676
+0.675
UA+0.674
Neg logit contributions
ertodd-0.658
ysis-0.527
verts-0.499
ered-0.498
 quo-0.492
Token the
Token ID262
Feature activation-2.36e-01

Pos logit contributions
ANE+0.095
awan+0.092
+0.090
+0.090
 srf+0.090
Neg logit contributions
ertodd-0.077
ysis-0.061
verts-0.058
ered-0.057
 quo-0.056
Token Milky
Token ID34822
Feature activation+4.64e-01

Pos logit contributions
ANE+0.620
awan+0.591
+0.577
UA+0.572
+0.572
Neg logit contributions
ertodd-0.776
ysis-0.638
verts-0.610
ered-0.608
 quo-0.600
Token Way
Token ID6378
Feature activation+9.05e-02

Pos logit contributions
ertodd+1.689
ysis+1.427
verts+1.374
ered+1.367
 quo+1.341
Neg logit contributions
ANE-1.048
awan-0.981
 srf-0.980
-0.970
senal-0.967
Token is
Token ID318
Feature activation-5.16e-01

Pos logit contributions
ertodd+0.233
ysis+0.182
verts+0.173
ered+0.172
 quo+0.168
Neg logit contributions
ANE-0.299
awan-0.288
-0.284
 srf-0.283
-0.283
Token at
Token ID379
Feature activation-3.92e-02

Pos logit contributions
ANE+1.453
awan+1.389
+1.358
UA+1.349
 srf+1.349
Neg logit contributions
ertodd-1.592
ysis-1.308
ered-1.248
verts-1.241
 quo-1.224
Token least
Token ID1551
Feature activation+8.30e-02

Pos logit contributions
ANE+0.116
awan+0.110
+0.109
+0.109
UA+0.108
Neg logit contributions
ertodd-0.114
ysis-0.094
ered-0.089
verts-0.089
 quo-0.087
Token your
Token ID534
Feature activation-3.67e-01

Pos logit contributions
ANE+2.697
awan+2.598
+2.550
+2.532
UA+2.529
Neg logit contributions
ertodd-2.226
ysis-1.726
verts-1.624
ered-1.598
 quo-1.578
Token wife
Token ID3656
Feature activation-1.07e+00

Pos logit contributions
ANE+1.064
awan+1.021
+1.000
 srf+0.991
+0.989
Neg logit contributions
ertodd-1.109
ysis-0.898
verts-0.852
ered-0.851
 quo-0.836
Token is
Token ID318
Feature activation-8.92e-01

Pos logit contributions
ANE+3.352
awan+3.237
+3.168
+3.155
UA+3.145
Neg logit contributions
ertodd-2.936
ysis-2.285
verts-2.150
ered-2.130
 quo-2.098
Token the
Token ID262
Feature activation+4.07e-01

Pos logit contributions
ANE+2.625
awan+2.523
+2.471
UA+2.447
+2.439
Neg logit contributions
ertodd-2.660
ysis-2.135
verts-2.027
ered-2.020
 quo-1.988
Token kind
Token ID1611
Feature activation+1.33e+00

Pos logit contributions
ertodd+1.156
ysis+0.933
ered+0.896
verts+0.892
 Jehovah+0.883
Neg logit contributions
ANE-1.224
awan-1.179
-1.169
 srf-1.153
EMENT-1.152
Token of
Token ID286
Feature activation-2.91e-02

Pos logit contributions
ertodd+3.578
ysis+2.881
ered+2.809
verts+2.754
 quo+2.727
Neg logit contributions
ANE-4.073
awan-3.934
-3.894
 srf-3.878
UA-3.832
Token sweet
Token ID6029
Feature activation-9.95e-02

Pos logit contributions
ANE+0.074
awan+0.071
+0.069
UA+0.068
 srf+0.068
Neg logit contributions
ertodd-0.098
ysis-0.081
verts-0.078
ered-0.078
 quo-0.077
Tokenheart
Token ID11499
Feature activation+5.91e-01

Pos logit contributions
ANE+0.271
awan+0.259
+0.254
UA+0.252
 srf+0.250
Neg logit contributions
ertodd-0.317
ysis-0.259
verts-0.250
ered-0.248
 quo-0.244
Token who
Token ID508
Feature activation+4.69e-01

Pos logit contributions
ertodd+1.394
ysis+1.065
verts+1.015
ered+1.014
 quo+0.990
Neg logit contributions
ANE-2.067
awan-1.999
 srf-1.974
-1.969
UA-1.954
Token loves
Token ID10408
Feature activation+7.91e-01

Pos logit contributions
ertodd+1.212
ysis+0.947
verts+0.899
ered+0.896
 quo+0.879
Neg logit contributions
ANE-1.552
awan-1.495
 srf-1.472
-1.466
UA-1.457
Token you
Token ID345
Feature activation-2.73e-01

Pos logit contributions
ertodd+2.004
ysis+1.582
verts+1.509
ered+1.496
 Jehovah+1.471
Neg logit contributions
ANE-2.620
awan-2.528
 srf-2.483
-2.474
UA-2.473
Token established
Token ID4920
Feature activation-4.49e-01

Pos logit contributions
ertodd+0.421
ysis+0.336
verts+0.321
ered+0.318
 quo+0.315
Neg logit contributions
ANE-0.458
awan-0.436
-0.428
 srf-0.428
UA-0.426
Token notions
Token ID26226
Feature activation+5.59e-01

Pos logit contributions
ANE+1.343
awan+1.289
+1.264
UA+1.252
+1.249
Neg logit contributions
ertodd-1.316
ysis-1.052
verts-0.999
ered-0.995
 quo-0.982
Token of
Token ID286
Feature activation+2.75e-01

Pos logit contributions
ertodd+1.612
ysis+1.280
verts+1.212
ered+1.207
 quo+1.189
Neg logit contributions
ANE-1.699
awan-1.633
-1.600
UA-1.586
-1.583
Token what
Token ID644
Feature activation+6.15e-01

Pos logit contributions
ertodd+0.807
ysis+0.646
verts+0.618
ered+0.614
 quo+0.608
Neg logit contributions
ANE-0.819
awan-0.781
-0.768
UA-0.765
 srf-0.760
Token constitutes
Token ID19300
Feature activation+9.08e-02

Pos logit contributions
ertodd+1.570
ysis+1.212
verts+1.163
ered+1.148
 quo+1.142
Neg logit contributions
ANE-2.053
awan-1.960
-1.949
 srf-1.940
UA-1.929
Token the
Token ID262
Feature activation-9.64e-02

Pos logit contributions
ertodd+0.270
ysis+0.217
verts+0.206
ered+0.206
 quo+0.203
Neg logit contributions
ANE-0.267
awan-0.255
-0.251
UA-0.249
 srf-0.248
Token middle
Token ID3504
Feature activation-8.61e-01

Pos logit contributions
ANE+0.259
awan+0.246
+0.242
UA+0.240
 srf+0.238
Neg logit contributions
ertodd-0.312
ysis-0.255
verts-0.244
ered-0.243
 quo-0.240
Token class
Token ID1398
Feature activation+3.45e-01

Pos logit contributions
ANE+1.883
awan+1.799
+1.742
+1.728
UA+1.706
Neg logit contributions
ertodd-3.198
ysis-2.686
verts-2.579
ered-2.533
 Jehovah-2.510
Token,
Token ID11
Feature activation-3.09e-01

Pos logit contributions
ertodd+1.166
ysis+0.961
ered+0.928
verts+0.924
 quo+0.923
Neg logit contributions
ANE-0.877
awan-0.829
-0.813
 srf-0.809
UA-0.802
Token rather
Token ID2138
Feature activation-3.45e-01

Pos logit contributions
ANE+0.937
awan+0.899
+0.882
UA+0.874
+0.872
Neg logit contributions
ertodd-0.894
ysis-0.712
verts-0.675
ered-0.672
 quo-0.664
Token than
Token ID621
Feature activation-6.55e-01

Pos logit contributions
ANE+0.991
awan+0.948
+0.930
 srf+0.919
UA+0.919
Neg logit contributions
ertodd-1.055
ysis-0.850
verts-0.810
ered-0.807
 quo-0.796
Token with
Token ID351
Feature activation-1.48e-01

Pos logit contributions
ertodd+0.546
ysis+0.443
verts+0.421
ered+0.419
 quo+0.413
Neg logit contributions
ANE-0.487
awan-0.467
-0.456
UA-0.452
-0.451
Token homelessness
Token ID28822
Feature activation+3.86e-01

Pos logit contributions
ANE+0.439
awan+0.422
+0.414
UA+0.410
 srf+0.409
Neg logit contributions
ertodd-0.434
ysis-0.349
verts-0.330
ered-0.330
 quo-0.324
Token.
Token ID13
Feature activation+2.93e-02

Pos logit contributions
ertodd+1.207
ysis+0.987
verts+0.941
ered+0.939
 quo+0.928
Neg logit contributions
ANE-1.072
awan-1.029
-1.007
 srf-0.999
UA-0.993
Token
Token ID198
Feature activation+3.50e-01

Pos logit contributions
ertodd+0.079
ysis+0.062
ered+0.058
verts+0.058
 quo+0.057
Neg logit contributions
ANE-0.094
awan-0.091
 srf-0.090
-0.089
-0.088
Token
Token ID198
Feature activation-1.53e-01

Pos logit contributions
ertodd+0.831
ysis+0.627
ered+0.604
verts+0.598
 quo+0.572
Neg logit contributions
 srf-1.229
ANE-1.225
senal-1.215
awan-1.185
-1.165
TokenNo
Token ID2949
Feature activation-3.35e-01

Pos logit contributions
ANE+0.339
 srf+0.327
awan+0.325
senal+0.316
+0.315
Neg logit contributions
ertodd-0.557
ysis-0.470
ered-0.454
verts-0.454
 quo-0.445
Token single
Token ID2060
Feature activation+1.68e-01

Pos logit contributions
ANE+0.988
awan+0.947
+0.931
+0.920
UA+0.920
Neg logit contributions
ertodd-0.992
ysis-0.800
verts-0.758
ered-0.758
 quo-0.744
Token system
Token ID1080
Feature activation+9.45e-02

Pos logit contributions
ertodd+0.496
ysis+0.402
ered+0.385
verts+0.381
 quo+0.380
Neg logit contributions
ANE-0.494
awan-0.473
-0.468
 srf-0.466
-0.461
Token tracks
Token ID8339
Feature activation+6.64e-01

Pos logit contributions
ertodd+0.252
ysis+0.197
ered+0.186
verts+0.185
 quo+0.182
Neg logit contributions
ANE-0.308
awan-0.295
-0.291
 srf-0.289
UA-0.288
Token street
Token ID4675
Feature activation+2.13e-01

Pos logit contributions
ertodd+1.845
ysis+1.506
ered+1.438
verts+1.420
 quo+1.399
Neg logit contributions
ANE-2.039
 srf-1.955
awan-1.955
-1.936
senal-1.919
Token people
Token ID661
Feature activation+3.61e-01

Pos logit contributions
ertodd+0.592
ysis+0.473
verts+0.449
ered+0.446
 quo+0.439
Neg logit contributions
ANE-0.662
awan-0.639
-0.627
 srf-0.624
UA-0.623
Token were
Token ID547
Feature activation+3.37e-01

Pos logit contributions
ertodd+0.475
ysis+0.369
ered+0.355
verts+0.349
 quo+0.346
Neg logit contributions
ANE-0.601
 srf-0.576
awan-0.576
-0.574
senal-0.572
Token going
Token ID1016
Feature activation+1.79e+00

Pos logit contributions
ertodd+0.957
ysis+0.769
verts+0.730
ered+0.728
 quo+0.723
Neg logit contributions
ANE-1.020
awan-0.985
-0.971
 srf-0.971
-0.954
Token to
Token ID284
Feature activation+1.00e+00

Pos logit contributions
ertodd+5.191
ysis+4.160
ered+4.082
 quo+3.980
verts+3.970
Neg logit contributions
ANE-5.111
awan-4.882
-4.821
UA-4.798
RAW-4.779
Token pit
Token ID6028
Feature activation-4.43e-01

Pos logit contributions
ertodd+2.761
ered+2.190
ysis+2.188
 quo+2.130
 Jehovah+2.118
Neg logit contributions
ANE-3.076
senal-2.974
 srf-2.955
awan-2.924
-2.906
Token a
Token ID257
Feature activation+1.51e-01

Pos logit contributions
ANE+1.369
awan+1.318
+1.294
UA+1.281
+1.280
Neg logit contributions
ertodd-1.252
ysis-0.990
verts-0.938
ered-0.933
 quo-0.918
Token city
Token ID1748
Feature activation-2.80e-02

Pos logit contributions
ertodd+0.467
ysis+0.382
verts+0.367
ered+0.366
 quo+0.364
Neg logit contributions
ANE-0.421
awan-0.404
-0.400
 srf-0.397
UA-0.395
Token ordinance
Token ID19784
Feature activation+3.38e-01

Pos logit contributions
ANE+0.058
awan+0.054
+0.054
 srf+0.053
+0.053
Neg logit contributions
ertodd-0.107
ysis-0.091
ered-0.088
verts-0.088
 quo-0.087
Token against
Token ID1028
Feature activation+3.29e-01

Pos logit contributions
ertodd+1.405
ysis+1.216
ered+1.180
verts+1.176
 quo+1.168
Neg logit contributions
ANE-0.585
awan-0.539
-0.536
 srf-0.529
-0.520
Token human
Token ID1692
Feature activation+8.09e-01

Pos logit contributions
ertodd+0.873
ysis+0.682
verts+0.648
ered+0.645
 quo+0.636
Neg logit contributions
ANE-1.070
awan-1.031
-1.019
 srf-1.012
UA-1.005
Token rights
Token ID2489
Feature activation+4.64e-01

Pos logit contributions
ertodd+1.740
ysis+1.273
verts+1.171
ered+1.169
 quo+1.146
Neg logit contributions
ANE-3.044
awan-2.943
-2.898
UA-2.881
 srf-2.877
Token,
Token ID11
Feature activation+3.45e-01

Pos logit contributions
ertodd+1.384
ysis+1.119
verts+1.066
ered+1.065
 quo+1.059
Neg logit contributions
ANE-1.360
awan-1.301
-1.279
 srf-1.270
-1.259
Token which
Token ID543
Feature activation+7.11e-01

Pos logit contributions
ANE+0.309
awan+0.298
+0.292
+0.290
UA+0.290
Neg logit contributions
ertodd-0.271
ysis-0.215
verts-0.204
ered-0.203
 quo-0.201
Token includes
Token ID3407
Feature activation+5.72e-01

Pos logit contributions
ertodd+1.813
ysis+1.424
verts+1.369
ered+1.367
 quo+1.336
Neg logit contributions
ANE-2.361
awan-2.266
 srf-2.258
-2.242
-2.233
Token additional
Token ID3224
Feature activation-9.06e-01

Pos logit contributions
ertodd+1.542
ysis+1.238
ered+1.185
verts+1.179
 quo+1.149
Neg logit contributions
ANE-1.789
awan-1.736
-1.712
-1.697
 srf-1.696
Token instructions
Token ID7729
Feature activation-3.10e-01

Pos logit contributions
ANE+2.578
awan+2.470
+2.416
UA+2.395
+2.389
Neg logit contributions
ertodd-2.794
ysis-2.253
verts-2.141
ered-2.132
 quo-2.102
Token for
Token ID329
Feature activation-4.23e-03

Pos logit contributions
ANE+0.870
awan+0.832
+0.817
+0.809
 srf+0.809
Neg logit contributions
ertodd-0.958
ysis-0.782
verts-0.748
ered-0.747
 quo-0.736
Token ensuring
Token ID13359
Feature activation-1.49e+00

Pos logit contributions
ANE+0.012
awan+0.012
+0.012
+0.012
 srf+0.011
Neg logit contributions
ertodd-0.013
ysis-0.010
verts-0.010
ered-0.010
 quo-0.010
Token compatibility
Token ID17764
Feature activation+6.78e-01

Pos logit contributions
ANE+4.490
awan+4.299
UA+4.187
RAW+4.168
+4.129
Neg logit contributions
ertodd-4.410
ysis-3.386
verts-3.220
ered-3.150
 quo-3.123
Token with
Token ID351
Feature activation+2.07e-01

Pos logit contributions
ertodd+1.996
ysis+1.634
ered+1.557
verts+1.553
 quo+1.550
Neg logit contributions
ANE-1.958
awan-1.884
-1.859
 srf-1.857
-1.827
Token V
Token ID569
Feature activation+5.58e-01

Pos logit contributions
ertodd+0.593
ysis+0.473
verts+0.450
ered+0.447
 quo+0.441
Neg logit contributions
ANE-0.631
awan-0.606
-0.596
-0.591
UA-0.589
TokenOD
Token ID3727
Feature activation-7.73e-02

Pos logit contributions
ertodd+2.021
ysis+1.725
ered+1.667
verts+1.654
 quo+1.618
Neg logit contributions
ANE-1.227
awan-1.186
-1.166
 srf-1.157
-1.150
Token services
Token ID2594
Feature activation+5.51e-01

Pos logit contributions
ANE+0.214
awan+0.206
+0.201
+0.200
 srf+0.199
Neg logit contributions
ertodd-0.240
ysis-0.198
verts-0.188
ered-0.188
 quo-0.184
Tokenstri
Token ID33565
Feature activation-3.04e-01

Pos logit contributions
ertodd+1.002
ysis+0.798
verts+0.760
ered+0.760
 quo+0.742
Neg logit contributions
ANE-1.065
awan-1.021
-0.999
 srf-0.992
-0.992
Tokenps
Token ID862
Feature activation-1.69e-01

Pos logit contributions
ANE+1.381
awan+1.355
+1.327
UA+1.322
EMENT+1.322
Neg logit contributions
ertodd-0.416
ysis-0.228
 quo-0.180
verts-0.180
ered-0.172
Token runner
Token ID17490
Feature activation+3.20e-01

Pos logit contributions
ANE+0.552
awan+0.533
+0.523
UA+0.518
+0.517
Neg logit contributions
ertodd-0.447
ysis-0.346
verts-0.325
ered-0.323
 quo-0.318
Token-
Token ID12
Feature activation-5.28e-01

Pos logit contributions
ertodd+0.759
ysis+0.571
verts+0.533
ered+0.531
 quo+0.520
Neg logit contributions
ANE-1.137
awan-1.097
-1.079
-1.072
UA-1.070
Tokenup
Token ID929
Feature activation+2.73e-01

Pos logit contributions
ANE+1.722
awan+1.672
+1.637
UA+1.626
EMENT+1.613
Neg logit contributions
ertodd-1.406
ysis-1.089
verts-1.013
ered-1.008
 quo-0.994
Token Israel
Token ID2692
Feature activation-1.77e+00

Pos logit contributions
ertodd+0.681
ysis+0.523
verts+0.491
ered+0.490
 quo+0.479
Neg logit contributions
ANE-0.932
awan-0.900
-0.886
-0.880
 srf-0.878
Token (
Token ID357
Feature activation-1.18e+00

Pos logit contributions
ANE+4.606
awan+4.421
+4.325
UA+4.253
RAW+4.231
Neg logit contributions
ertodd-5.819
ysis-4.686
verts-4.504
 quo-4.399
ered-4.396
Tokenat
Token ID265
Feature activation-1.01e+00

Pos logit contributions
ANE+2.877
awan+2.736
+2.671
UA+2.648
+2.628
Neg logit contributions
ertodd-4.156
ysis-3.438
verts-3.284
ered-3.271
 quo-3.247
Token 4
Token ID604
Feature activation+6.51e-01

Pos logit contributions
ANE+2.969
awan+2.866
+2.796
UA+2.776
EMENT+2.756
Neg logit contributions
ertodd-3.043
ysis-2.389
verts-2.278
ered-2.262
 quo-2.228
Token.
Token ID13
Feature activation+5.49e-01

Pos logit contributions
ertodd+2.193
ysis+1.829
ered+1.755
verts+1.752
 quo+1.709
Neg logit contributions
ANE-1.624
awan-1.537
 srf-1.517
-1.501
-1.493
Token11
Token ID1157
Feature activation+5.90e-01

Pos logit contributions
ertodd+1.681
ysis+1.382
ered+1.337
verts+1.336
 Jehovah+1.292
Neg logit contributions
 srf-1.512
ANE-1.505
senal-1.477
awan-1.449
-1.418
Token rounds
Token ID9196
Feature activation+4.39e-01

Pos logit contributions
ertodd+0.969
ysis+0.776
ered+0.745
verts+0.744
 quo+0.724
Neg logit contributions
ANE-0.996
awan-0.962
-0.941
-0.941
 srf-0.938
Token of
Token ID286
Feature activation+4.55e-01

Pos logit contributions
ertodd+1.216
ysis+0.963
ered+0.919
verts+0.906
 quo+0.893
Neg logit contributions
ANE-1.365
awan-1.319
-1.289
-1.287
UA-1.282
Token ammunition
Token ID14271
Feature activation-4.28e-01

Pos logit contributions
ertodd+1.353
ysis+1.099
verts+1.044
ered+1.044
 quo+1.029
Neg logit contributions
ANE-1.322
awan-1.269
-1.246
-1.246
UA-1.239
Token that
Token ID326
Feature activation+3.83e-02

Pos logit contributions
ANE+1.432
awan+1.381
+1.361
+1.350
UA+1.349
Neg logit contributions
ertodd-1.102
ysis-0.852
verts-0.802
ered-0.801
 quo-0.783
Token disappeared
Token ID12120
Feature activation-3.03e-01

Pos logit contributions
ertodd+0.102
ysis+0.079
ered+0.075
verts+0.074
 quo+0.073
Neg logit contributions
ANE-0.125
awan-0.121
-0.119
-0.118
UA-0.118
Token last
Token ID938
Feature activation-1.52e+00

Pos logit contributions
ANE+0.828
awan+0.792
+0.774
UA+0.767
+0.766
Neg logit contributions
ertodd-0.965
ysis-0.786
verts-0.749
ered-0.747
 quo-0.736
Token week
Token ID1285
Feature activation-6.31e-01

Pos logit contributions
ANE+3.704
awan+3.546
+3.438
UA+3.403
+3.389
Neg logit contributions
ertodd-5.239
ysis-4.349
verts-4.067
ered-4.057
 quo-4.027
Token have
Token ID423
Feature activation+5.00e-01

Pos logit contributions
ANE+1.945
awan+1.872
+1.831
+1.815
UA+1.815
Neg logit contributions
ertodd-1.795
ysis-1.420
verts-1.334
ered-1.325
 quo-1.310
Token been
Token ID587
Feature activation-1.65e-01

Pos logit contributions
ertodd+1.294
ysis+0.997
ered+0.945
verts+0.939
 quo+0.917
Neg logit contributions
ANE-1.667
awan-1.609
-1.580
UA-1.571
 srf-1.570
Token located
Token ID5140
Feature activation-3.63e-01

Pos logit contributions
ANE+0.568
awan+0.548
+0.542
UA+0.537
 srf+0.537
Neg logit contributions
ertodd-0.411
ysis-0.313
ered-0.298
verts-0.296
 quo-0.289
Token.
Token ID13
Feature activation-3.61e-01

Pos logit contributions
ANE+0.960
awan+0.917
+0.897
UA+0.888
+0.885
Neg logit contributions
ertodd-1.190
ysis-0.975
verts-0.932
ered-0.931
 quo-0.917
Token that
Token ID326
Feature activation-1.65e-01

Pos logit contributions
ertodd+0.113
ysis+0.090
ered+0.086
verts+0.085
 quo+0.083
Neg logit contributions
ANE-0.127
awan-0.123
-0.121
 srf-0.120
-0.119
Token this
Token ID428
Feature activation+1.35e-01

Pos logit contributions
ANE+0.520
awan+0.500
+0.493
 srf+0.488
UA+0.486
Neg logit contributions
ertodd-0.454
ysis-0.358
verts-0.340
ered-0.339
 quo-0.333
Token has
Token ID468
Feature activation+4.31e-01

Pos logit contributions
ertodd+0.350
ysis+0.273
verts+0.259
ered+0.258
 quo+0.255
Neg logit contributions
ANE-0.450
awan-0.433
-0.427
 srf-0.425
UA-0.421
Token made
Token ID925
Feature activation+3.89e-01

Pos logit contributions
ertodd+1.196
ysis+0.949
ered+0.916
verts+0.903
 quo+0.890
Neg logit contributions
ANE-1.346
awan-1.297
 srf-1.274
-1.273
senal-1.258
Token it
Token ID340
Feature activation-7.71e-02

Pos logit contributions
ertodd+1.064
ysis+0.857
ered+0.829
verts+0.813
 quo+0.807
Neg logit contributions
ANE-1.209
-1.165
awan-1.157
 srf-1.146
-1.142
Token harder
Token ID7069
Feature activation-1.59e+00

Pos logit contributions
ANE+0.194
awan+0.186
+0.182
 srf+0.180
UA+0.179
Neg logit contributions
ertodd-0.260
ysis-0.216
ered-0.208
verts-0.208
 quo-0.206
Token for
Token ID329
Feature activation-1.74e-01

Pos logit contributions
ANE+3.846
awan+3.650
+3.563
+3.521
UA+3.503
Neg logit contributions
ertodd-5.436
ysis-4.484
verts-4.317
 Jehovah-4.170
ered-4.124
Token screen
Token ID3159
Feature activation+5.95e-01

Pos logit contributions
ANE+0.545
awan+0.525
+0.519
 srf+0.513
+0.512
Neg logit contributions
ertodd-0.482
ysis-0.383
ered-0.363
verts-0.363
 quo-0.356
Tokeners
Token ID364
Feature activation+1.67e+00

Pos logit contributions
ertodd+1.238
ysis+0.929
ered+0.867
verts+0.865
 quo+0.831
Neg logit contributions
ANE-2.244
awan-2.159
-2.150
 srf-2.136
senal-2.134
Token to
Token ID284
Feature activation+1.75e-01

Pos logit contributions
ertodd+4.732
ysis+3.856
ered+3.700
verts+3.612
 quo+3.591
Neg logit contributions
ANE-4.879
awan-4.680
-4.615
EMENT-4.559
 srf-4.540
Token identify
Token ID5911
Feature activation+4.55e-02

Pos logit contributions
ertodd+0.509
ysis+0.415
ered+0.402
verts+0.394
 quo+0.391
Neg logit contributions
ANE-0.520
awan-0.497
-0.496
senal-0.492
 srf-0.492
Token.
Token ID13
Feature activation-3.96e-03

Pos logit contributions
ertodd+0.479
ysis+0.395
ered+0.378
verts+0.377
 quo+0.373
Neg logit contributions
ANE-0.405
awan-0.387
-0.380
 srf-0.374
UA-0.374
Token An
Token ID1052
Feature activation-1.46e-01

Pos logit contributions
ANE+0.013
awan+0.013
+0.012
 srf+0.012
+0.012
Neg logit contributions
ertodd-0.010
ysis-0.008
verts-0.008
ered-0.008
 quo-0.007
Token example
Token ID1672
Feature activation-1.18e-01

Pos logit contributions
ANE+0.409
awan+0.393
+0.386
+0.382
 srf+0.381
Neg logit contributions
ertodd-0.454
ysis-0.368
ered-0.353
verts-0.351
 quo-0.345
Token is
Token ID318
Feature activation-1.28e+00

Pos logit contributions
ANE+0.375
awan+0.361
+0.355
 srf+0.351
+0.351
Neg logit contributions
ertodd-0.326
ysis-0.257
verts-0.244
ered-0.243
 quo-0.239
Token below
Token ID2174
Feature activation-1.30e+00

Pos logit contributions
ANE+3.923
awan+3.761
+3.691
UA+3.671
+3.662
Neg logit contributions
ertodd-3.656
ysis-2.869
verts-2.691
ered-2.674
 quo-2.654
Token (
Token ID357
Feature activation-1.64e+00

Pos logit contributions
ANE+3.528
awan+3.378
+3.295
UA+3.291
EMENT+3.268
Neg logit contributions
ertodd-4.131
ysis-3.329
verts-3.159
ered-3.132
 quo-3.093
Tokenselect
Token ID19738
Feature activation-1.54e+00

Pos logit contributions
ANE+3.960
awan+3.762
+3.674
UA+3.668
RAW+3.635
Neg logit contributions
ertodd-5.754
ysis-4.751
ered-4.504
verts-4.498
 quo-4.489
Token category
Token ID6536
Feature activation-6.25e-01

Pos logit contributions
ANE+4.974
awan+4.775
UA+4.699
+4.698
EMENT+4.658
Neg logit contributions
ertodd-4.127
ysis-3.172
verts-2.949
ered-2.903
 quo-2.899
Token -->
Token ID14610
Feature activation-4.16e-01

Pos logit contributions
ANE+1.758
awan+1.685
+1.649
UA+1.632
+1.629
Neg logit contributions
ertodd-1.942
ysis-1.573
verts-1.497
ered-1.491
 quo-1.470
Token drill
Token ID16007
Feature activation-2.34e-02

Pos logit contributions
ANE+1.190
awan+1.143
+1.118
UA+1.104
+1.103
Neg logit contributions
ertodd-1.272
ysis-1.028
verts-0.980
ered-0.975
 quo-0.961
Tokenthrough
Token ID9579
Feature activation-6.62e-01

Pos logit contributions
ANE+0.055
awan+0.053
+0.051
 srf+0.050
+0.050
Neg logit contributions
ertodd-0.083
ysis-0.070
ered-0.067
verts-0.067
 quo-0.066