TOP ACTIVATIONS
MAX = 3.023

, Hillary !" Cand idates ' teams are manufacturing
- Cl over field - Cand idate Theme Songs - Scient
that the usual Elect rom agnetic field
country since before the June referendum , according to the chair
. Elect a Draper : 303 -
50 - year - old labou rer , sigh s that
camps in northern Newfoundland and Labrador or Alberta , I think
this event . Enter The Joker .
file photo . Treasury Secretary Lew warned September 25 , 2013
the panels is composed of combust ible plastic material . A
federal government . Er n est o Gal ar
in general after the November election , as the current highly
more difficult . Cand ace Hilton said she
G ainer Contest - 08 Election - T ravis & Protect
to make the announcement on Election Day , posting photos of
it happen ? Not a day goes by that
it at El Rio on Election Night , the night we
, nature and diversity . Not eworthy : Under pass Park
1971 's Electric Warrior . Not metal but still relevant .
why not ? Not too many players go out

MIN ACTIVATIONS
MIN = -3.306

terms of a qu id pro quo , it
to have risen up in parallel fashion , in a kind
we can run it in parallel . To do this ,
accusation that he was a serial cat sl ayer .
few hours ago , on Billy Turner , the Miko Grimes
disagreement with This version had the most motion
Baylor produced -- but was fo iled by a combination of
plays the harmon ica during Gon zo 's song " I
that the NFL would provide san itized limited evidence in an
functions that will run in parallel . All these lambda function
of whose members have been accused of mass rape , was
i M ok up uni ma Ok ak
, telecommunications companies were granted retro active immunity for violating the
and slap stick moments whenever Gon gets into a fight .
category of planets known as mini - Ne pt unes .
turned criticism of its brutal version of Islam into an attack
eed has been making a version of this argument for many
op ā p ā . Pa ē ak ula
Temple Address : Da ar uk avan am ,
i pa ia ma Mei 25 , 2018 ma

INTERVAL 1.441 - 3.023
CONTAINS 0.659%

is Lean Six Sigma ? Def ining Lean Six
have that many good years left in me , and I
also wrote that sign ificantly scaling back the Clinton
doesn t support Clinton . Back during
is retiring when her term ends this year .

INTERVAL -0.142 - 1.441
CONTAINS 61.068%

to the footwear pur vey or ; 40 Wall Street ,
The messages are written , we hope , with some sense
up until after the election , and the Iranians had a
He has an 8 - by - 12 copy of that
third of the cap es that arrived to fight him .

INTERVAL -1.724 - -0.142
CONTAINS 38.091%

C omet Song ) for the film M oom ins and
In the end this would be the start of a
10 : 47 ] < met ros xual th ug >
of truly believing in your own ability is substantial , and
to haul up any spe ared m ogg ies . Did

INTERVAL -3.306 - -1.724
CONTAINS 0.182%

- K ahn . <|endoftext|> SAN FR ANC IS CO -
anners - favorite favorite favorite favorite favorite - December 5 ,
i n ō ka p ā h ana i
University of Pennsylvania , and Milan Va ish nav , a
s ra ison d et re is
Token,
Token ID11
Feature activation-3.50e-02

Pos logit contributions
orio+0.035
acular+0.032
enegger+0.032
orious+0.031
 gears+0.030
Neg logit contributions
 derog-0.029
 curs-0.028
beit-0.026
 perpet-0.025
��-0.024
Token Hillary
Token ID5073
Feature activation+3.74e-01

Pos logit contributions
 derog+0.138
 curs+0.133
beit+0.124
 perpet+0.122
��+0.116
Neg logit contributions
orio-0.166
acular-0.156
enegger-0.154
orious-0.150
 gears-0.146
Token!"
Token ID2474
Feature activation-4.64e-02

Pos logit contributions
orio+1.799
acular+1.704
enegger+1.673
orious+1.640
 gears+1.606
Neg logit contributions
 derog-1.436
 curs-1.374
beit-1.292
 perpet-1.241
��-1.231
Token
Token ID198
Feature activation+2.29e-01

Pos logit contributions
 derog+0.171
 curs+0.164
beit+0.153
 perpet+0.150
��+0.142
Neg logit contributions
orio-0.232
acular-0.219
enegger-0.217
orious-0.212
 gears-0.205
Token
Token ID198
Feature activation+3.48e-03

Pos logit contributions
orio+1.187
enegger+1.116
acular+1.111
orious+1.078
 gears+1.052
Neg logit contributions
 derog-0.800
 curs-0.776
beit-0.716
 perpet-0.712
-0.659
TokenCand
Token ID41572
Feature activation+3.02e+00

Pos logit contributions
orio+0.016
acular+0.015
enegger+0.015
orious+0.015
 gears+0.014
Neg logit contributions
 derog-0.014
 curs-0.013
beit-0.012
 perpet-0.012
��-0.012
Tokenidates
Token ID37051
Feature activation+1.23e+00

Pos logit contributions
orio+9.992
acular+8.714
orious+8.479
rain+7.817
enegger+7.593
Neg logit contributions
 derog-14.676
 curs-13.547
��-13.155
 perpet-12.672
beit-12.535
Token'
Token ID6
Feature activation+3.00e-01

Pos logit contributions
orio+5.595
acular+5.275
orious+5.123
enegger+5.083
 gears+5.034
Neg logit contributions
 derog-4.567
 curs-4.377
beit-4.280
��-4.214
 perpet-3.916
Token teams
Token ID3466
Feature activation-5.37e-01

Pos logit contributions
orio+1.430
acular+1.348
enegger+1.326
orious+1.300
 gears+1.280
Neg logit contributions
 derog-1.160
 curs-1.100
beit-1.055
 perpet-1.015
��-1.008
Token are
Token ID389
Feature activation-1.46e-01

Pos logit contributions
 derog+1.945
 curs+1.878
 perpet+1.721
beit+1.718
��+1.568
Neg logit contributions
orio-2.739
acular-2.567
enegger-2.555
orious-2.481
 gears-2.392
Token manufacturing
Token ID9138
Feature activation-2.24e-01

Pos logit contributions
 derog+0.605
 curs+0.585
beit+0.548
 perpet+0.540
��+0.515
Neg logit contributions
orio-0.665
acular-0.620
enegger-0.614
orious-0.598
 gears-0.578
Token-
Token ID12
Feature activation-3.95e-01

Pos logit contributions
 derog+0.663
 curs+0.643
beit+0.594
 perpet+0.591
+0.544
Neg logit contributions
orio-1.571
enegger-1.500
acular-1.481
orious-1.440
 gears-1.428
TokenCl
Token ID2601
Feature activation+8.41e-01

Pos logit contributions
 derog+1.569
 curs+1.514
beit+1.409
 perpet+1.392
��+1.320
Neg logit contributions
orio-1.875
acular-1.755
enegger-1.738
orious-1.694
 gears-1.635
Tokenover
Token ID2502
Feature activation-3.19e-01

Pos logit contributions
orio+3.435
acular+3.161
orious+3.075
enegger+2.967
reetings+2.837
Neg logit contributions
 derog-3.986
 curs-3.818
beit-3.582
 perpet-3.573
��-3.465
Tokenfield
Token ID3245
Feature activation+1.83e-01

Pos logit contributions
 derog+1.289
 curs+1.245
beit+1.160
 perpet+1.148
��+1.089
Neg logit contributions
orio-1.492
acular-1.396
enegger-1.382
orious-1.346
 gears-1.300
Token-
Token ID12
Feature activation+2.68e-01

Pos logit contributions
orio+0.920
acular+0.883
enegger+0.867
orious+0.846
 gears+0.814
Neg logit contributions
 derog-0.671
 curs-0.644
beit-0.589
 perpet-0.581
��-0.559
TokenCand
Token ID41572
Feature activation+2.91e+00

Pos logit contributions
orio+1.231
acular+1.157
enegger+1.134
orious+1.118
rain+1.066
Neg logit contributions
 derog-1.113
 curs-1.068
beit-0.980
 perpet-0.973
��-0.935
Tokenidate
Token ID20540
Feature activation+1.43e+00

Pos logit contributions
orio+10.739
acular+9.637
orious+9.486
rain+8.840
enegger+8.769
Neg logit contributions
 derog-13.166
 curs-12.275
��-11.574
 perpet-11.432
beit-11.280
Token Theme
Token ID26729
Feature activation-6.18e-01

Pos logit contributions
orio+6.678
acular+6.355
orious+6.093
enegger+6.083
rain+5.860
Neg logit contributions
 derog-5.314
 curs-5.100
beit-4.636
 perpet-4.609
��-4.596
Token Songs
Token ID31772
Feature activation-3.50e-01

Pos logit contributions
 derog+2.596
 curs+2.509
beit+2.333
 perpet+2.310
��+2.195
Neg logit contributions
orio-2.807
acular-2.626
enegger-2.592
orious-2.524
 gears-2.430
Token-
Token ID12
Feature activation+1.64e-01

Pos logit contributions
 derog+1.161
 curs+1.111
beit+1.005
 perpet+0.990
��+0.936
Neg logit contributions
orio-1.910
acular-1.819
enegger-1.786
orious-1.764
 gears-1.692
TokenScient
Token ID23010
Feature activation+9.62e-01

Pos logit contributions
orio+0.754
acular+0.708
enegger+0.694
orious+0.683
rain+0.649
Neg logit contributions
 derog-0.682
 curs-0.654
beit-0.603
 perpet-0.598
��-0.574
Token that
Token ID326
Feature activation+8.21e-01

Pos logit contributions
orio+1.027
acular+0.972
enegger+0.958
orious+0.936
 gears+0.913
Neg logit contributions
 derog-0.767
 curs-0.741
beit-0.684
 perpet-0.668
��-0.646
Token the
Token ID262
Feature activation+2.92e-01

Pos logit contributions
orio+3.923
acular+3.723
enegger+3.618
orious+3.579
 gears+3.496
Neg logit contributions
 derog-3.058
 curs-2.977
beit-2.770
 perpet-2.626
��-2.618
Token usual
Token ID6678
Feature activation-4.40e-01

Pos logit contributions
orio+1.401
acular+1.311
enegger+1.282
orious+1.265
 gears+1.227
Neg logit contributions
 derog-1.129
 curs-1.086
beit-1.034
 perpet-0.991
��-0.967
Token
Token ID564
Feature activation-7.37e-01

Pos logit contributions
 derog+1.825
 curs+1.765
beit+1.650
 perpet+1.631
��+1.549
Neg logit contributions
orio-2.005
acular-1.870
enegger-1.853
orious-1.802
 gears-1.740
Token
Token ID246
Feature activation+2.31e-02

Pos logit contributions
 derog+2.454
 curs+2.366
beit+2.201
 perpet+2.145
��+2.061
Neg logit contributions
orio-3.876
acular-3.673
enegger-3.660
orious-3.541
 gears-3.449
TokenElect
Token ID19453
Feature activation+2.84e+00

Pos logit contributions
orio+0.101
acular+0.094
enegger+0.093
orious+0.090
 gears+0.087
Neg logit contributions
 derog-0.100
 curs-0.097
beit-0.091
 perpet-0.090
��-0.086
Tokenrom
Token ID398
Feature activation+4.56e-01

Pos logit contributions
orio+10.996
acular+10.629
orious+9.799
rain+9.686
ronics+9.289
Neg logit contributions
 derog-11.432
 curs-10.462
beit-10.389
 perpet-9.960
��-9.383
Tokenagnetic
Token ID25145
Feature activation+3.55e-01

Pos logit contributions
orio+1.619
acular+1.504
enegger+1.448
orious+1.418
rain+1.349
Neg logit contributions
 derog-2.330
 curs-2.287
beit-2.156
 perpet-2.128
��-2.076
Token field
Token ID2214
Feature activation+1.42e-01

Pos logit contributions
orio+1.685
acular+1.589
enegger+1.554
orious+1.518
 gears+1.500
Neg logit contributions
 derog-1.373
 curs-1.324
beit-1.243
 perpet-1.200
��-1.160
Token
Token ID447
Feature activation+1.51e-01

Pos logit contributions
orio+0.704
acular+0.665
enegger+0.656
orious+0.642
 gears+0.626
Neg logit contributions
 derog-0.523
 curs-0.504
beit-0.470
 perpet-0.454
��-0.439
Token
Token ID247
Feature activation-8.02e-02

Pos logit contributions
orio+0.929
acular+0.883
enegger+0.877
orious+0.859
 gears+0.838
Neg logit contributions
 derog-0.390
 curs-0.369
beit-0.329
 perpet-0.323
��-0.295
Token country
Token ID1499
Feature activation+3.95e-02

Pos logit contributions
 derog+1.302
 curs+1.262
beit+1.180
 perpet+1.159
��+1.113
Neg logit contributions
orio-1.475
acular-1.384
enegger-1.363
orious-1.334
 gears-1.291
Token since
Token ID1201
Feature activation-7.42e-01

Pos logit contributions
orio+0.197
acular+0.186
enegger+0.183
orious+0.182
 gears+0.176
Neg logit contributions
 derog-0.142
 curs-0.139
beit-0.128
��-0.124
 perpet-0.123
Token before
Token ID878
Feature activation-4.97e-01

Pos logit contributions
 derog+2.530
 curs+2.436
beit+2.236
 perpet+2.227
��+2.016
Neg logit contributions
orio-3.932
acular-3.700
enegger-3.698
orious-3.568
 gears-3.466
Token the
Token ID262
Feature activation+2.93e-02

Pos logit contributions
 derog+1.740
 curs+1.672
beit+1.542
 perpet+1.524
��+1.420
Neg logit contributions
orio-2.587
acular-2.434
enegger-2.419
orious-2.354
 gears-2.284
Token June
Token ID2795
Feature activation+3.87e-01

Pos logit contributions
orio+0.140
acular+0.132
enegger+0.130
orious+0.127
 gears+0.124
Neg logit contributions
 derog-0.113
 curs-0.109
beit-0.103
 perpet-0.100
��-0.097
Token referendum
Token ID11467
Feature activation+2.79e+00

Pos logit contributions
orio+1.907
acular+1.789
enegger+1.772
orious+1.734
 gears+1.680
Neg logit contributions
 derog-1.444
 curs-1.398
beit-1.299
 perpet-1.274
��-1.227
Token,
Token ID11
Feature activation-3.20e-01

Pos logit contributions
orio+10.309
acular+10.031
orious+9.327
 gears+9.029
enegger+8.852
Neg logit contributions
 curs-10.501
��-10.420
 derog-10.411
beit-10.056
 perpet-9.289
Token according
Token ID1864
Feature activation-4.84e-01

Pos logit contributions
 derog+1.192
 curs+1.148
beit+1.064
 perpet+1.050
��+0.994
Neg logit contributions
orio-1.591
acular-1.493
enegger-1.480
orious-1.444
 gears-1.399
Token to
Token ID284
Feature activation-3.67e-01

Pos logit contributions
 derog+1.391
 curs+1.330
 perpet+1.237
beit+1.202
+1.125
Neg logit contributions
orio-2.792
enegger-2.667
acular-2.605
orious-2.529
ierrez-2.497
Token the
Token ID262
Feature activation-9.88e-02

Pos logit contributions
 derog+1.387
 curs+1.337
beit+1.242
 perpet+1.226
��+1.162
Neg logit contributions
orio-1.809
acular-1.696
enegger-1.681
orious-1.640
 gears-1.589
Token chair
Token ID5118
Feature activation+1.32e-01

Pos logit contributions
 derog+0.384
 curs+0.371
beit+0.345
 perpet+0.341
��+0.324
Neg logit contributions
orio-0.476
acular-0.446
enegger-0.442
orious-0.431
 gears-0.417
Token.
Token ID13
Feature activation+6.43e-02

Pos logit contributions
 derog+1.044
 curs+1.009
beit+0.942
 perpet+0.925
��+0.884
Neg logit contributions
orio-1.255
acular-1.177
enegger-1.164
orious-1.135
 gears-1.100
Token
Token ID447
Feature activation-1.55e-03

Pos logit contributions
orio+0.317
acular+0.298
enegger+0.294
orious+0.287
 gears+0.278
Neg logit contributions
 derog-0.244
 curs-0.234
beit-0.218
 perpet-0.213
��-0.204
Token
Token ID251
Feature activation-4.45e-01

Pos logit contributions
 derog+0.006
 curs+0.006
beit+0.005
 perpet+0.005
+0.005
Neg logit contributions
orio-0.007
acular-0.007
enegger-0.007
orious-0.007
 gears-0.007
Token
Token ID198
Feature activation-2.58e-01

Pos logit contributions
 derog+1.611
 curs+1.550
beit+1.433
 perpet+1.416
��+1.330
Neg logit contributions
orio-2.262
acular-2.125
enegger-2.109
orious-2.057
 gears-1.993
Token
Token ID198
Feature activation-4.14e-01

Pos logit contributions
 derog+0.805
 curs+0.791
 perpet+0.736
beit+0.729
+0.694
Neg logit contributions
orio-1.410
enegger-1.347
acular-1.314
orious-1.281
 gears-1.265
TokenElect
Token ID19453
Feature activation+2.74e+00

Pos logit contributions
 derog+1.640
 curs+1.588
beit+1.482
 perpet+1.463
��+1.382
Neg logit contributions
orio-1.957
acular-1.829
enegger-1.819
orious-1.765
 gears-1.712
Tokena
Token ID64
Feature activation-1.09e+00

Pos logit contributions
orio+11.381
acular+10.441
orious+10.056
enegger+9.490
rain+9.454
Neg logit contributions
 derog-10.872
 curs-9.860
beit-9.726
 perpet-9.408
��-9.277
Token Draper
Token ID48575
Feature activation+3.43e-01

Pos logit contributions
 derog+4.007
 curs+3.879
beit+3.591
 perpet+3.557
+3.342
Neg logit contributions
orio-5.358
acular-5.036
enegger-5.027
orious-4.867
 gears-4.711
Token:
Token ID25
Feature activation+3.78e-01

Pos logit contributions
orio+1.683
acular+1.569
enegger+1.558
orious+1.522
 gears+1.484
Neg logit contributions
 derog-1.299
 curs-1.250
beit-1.156
 perpet-1.136
��-1.103
Token 303
Token ID30727
Feature activation+3.82e-01

Pos logit contributions
orio+1.889
acular+1.768
enegger+1.757
orious+1.725
 gears+1.683
Neg logit contributions
 derog-1.371
 curs-1.316
beit-1.245
 perpet-1.197
��-1.176
Token-
Token ID12
Feature activation-1.79e-01

Pos logit contributions
orio+2.055
acular+1.929
enegger+1.911
orious+1.886
 gears+1.844
Neg logit contributions
 derog-1.261
 curs-1.218
beit-1.107
 perpet-1.066
��-1.060
Token 50
Token ID2026
Feature activation-1.29e-01

Pos logit contributions
orio+2.789
acular+2.612
enegger+2.558
orious+2.539
 gears+2.459
Neg logit contributions
 derog-2.127
 curs-2.032
beit-1.952
 perpet-1.885
��-1.867
Token-
Token ID12
Feature activation+5.36e-01

Pos logit contributions
 derog+0.459
 curs+0.436
beit+0.412
 perpet+0.398
��+0.375
Neg logit contributions
orio-0.676
acular-0.639
enegger-0.620
orious-0.615
 gears-0.594
Tokenyear
Token ID1941
Feature activation+4.15e-01

Pos logit contributions
orio+2.294
acular+2.131
enegger+2.056
orious+2.051
rain+1.951
Neg logit contributions
 derog-2.397
 curs-2.298
beit-2.165
 perpet-2.131
��-2.096
Token-
Token ID12
Feature activation+7.35e-01

Pos logit contributions
orio+2.133
acular+1.990
orious+1.953
enegger+1.945
 gears+1.855
Neg logit contributions
 derog-1.462
 curs-1.419
beit-1.312
 perpet-1.256
��-1.238
Tokenold
Token ID727
Feature activation+1.15e+00

Pos logit contributions
orio+2.699
acular+2.469
enegger+2.431
orious+2.359
 gears+2.237
Neg logit contributions
 derog-3.707
 curs-3.607
beit-3.402
 perpet-3.372
��-3.250
Token labou
Token ID45161
Feature activation+2.62e+00

Pos logit contributions
orio+5.505
acular+5.131
 gears+4.961
enegger+4.955
orious+4.952
Neg logit contributions
 derog-4.140
 curs-3.887
beit-3.867
��-3.829
 perpet-3.622
Tokenrer
Token ID11751
Feature activation+1.61e+00

Pos logit contributions
orio+7.224
rain+6.087
acular+5.816
orious+5.734
enegger+5.446
Neg logit contributions
 derog-13.859
 curs-13.326
��-13.148
beit-12.978
 perpet-12.830
Token,
Token ID11
Feature activation+7.95e-01

Pos logit contributions
orio+6.660
acular+6.416
 gears+6.181
enegger+6.104
orious+6.087
Neg logit contributions
 derog-6.135
 curs-6.039
��-5.942
beit-5.891
 perpet-5.411
Token sigh
Token ID19680
Feature activation+1.72e+00

Pos logit contributions
orio+3.629
acular+3.451
enegger+3.356
 gears+3.351
orious+3.308
Neg logit contributions
 derog-3.095
 curs-2.958
beit-2.833
��-2.767
 perpet-2.715
Tokens
Token ID82
Feature activation+1.24e+00

Pos logit contributions
orio+3.081
acular+3.028
orious+2.637
enegger+2.591
 gears+2.521
Neg logit contributions
 derog-10.761
 curs-10.503
��-10.209
beit-10.173
 perpet-10.014
Token that
Token ID326
Feature activation-2.29e-01

Pos logit contributions
orio+5.366
acular+5.181
enegger+5.035
orious+5.001
 gears+4.967
Neg logit contributions
 derog-4.598
��-4.564
 curs-4.546
beit-4.446
 perpet-4.196
Token camps
Token ID11665
Feature activation-3.18e-01

Pos logit contributions
orio+2.546
acular+2.408
enegger+2.345
orious+2.338
 gears+2.288
Neg logit contributions
 derog-2.030
 curs-1.962
beit-1.874
 perpet-1.785
��-1.766
Token in
Token ID287
Feature activation-4.23e-01

Pos logit contributions
 derog+1.213
 curs+1.169
beit+1.086
 perpet+1.076
��+1.013
Neg logit contributions
orio-1.550
acular-1.452
enegger-1.442
orious-1.404
 gears-1.359
Token northern
Token ID7840
Feature activation-8.94e-02

Pos logit contributions
 derog+1.536
 curs+1.480
beit+1.374
 perpet+1.345
��+1.281
Neg logit contributions
orio-2.140
acular-2.011
enegger-1.992
orious-1.947
 gears-1.891
Token Newfoundland
Token ID43867
Feature activation+1.12e+00

Pos logit contributions
 derog+0.327
 curs+0.315
beit+0.297
 perpet+0.283
��+0.280
Neg logit contributions
orio-0.444
acular-0.417
enegger-0.414
orious-0.405
 gears-0.400
Token and
Token ID290
Feature activation-6.77e-01

Pos logit contributions
orio+5.236
acular+4.934
orious+4.775
 gears+4.754
enegger+4.738
Neg logit contributions
 derog-4.217
 curs-4.052
beit-3.832
��-3.766
 perpet-3.562
Token Labrador
Token ID45246
Feature activation+2.59e+00

Pos logit contributions
 derog+3.068
 curs+2.978
beit+2.795
 perpet+2.773
��+2.639
Neg logit contributions
orio-2.827
acular-2.614
enegger-2.592
orious-2.510
 gears-2.413
Token or
Token ID393
Feature activation+3.16e-01

Pos logit contributions
orio+9.743
acular+9.259
 gears+9.097
orious+8.906
rain+8.774
Neg logit contributions
 derog-9.963
��-9.610
 curs-9.594
beit-9.175
paren-8.297
Token Alberta
Token ID15555
Feature activation+1.57e+00

Pos logit contributions
orio+1.529
acular+1.457
enegger+1.428
orious+1.402
 gears+1.380
Neg logit contributions
 derog-1.180
 curs-1.129
beit-1.071
 perpet-1.027
��-1.020
Token,
Token ID11
Feature activation+5.91e-02

Pos logit contributions
orio+6.756
acular+6.418
 gears+6.217
orious+6.140
enegger+6.067
Neg logit contributions
 derog-6.180
 curs-5.915
��-5.608
beit-5.587
 perpet-5.267
Token I
Token ID314
Feature activation-2.49e-01

Pos logit contributions
orio+0.291
acular+0.273
enegger+0.271
orious+0.264
 gears+0.256
Neg logit contributions
 derog-0.223
 curs-0.215
beit-0.199
 perpet-0.196
��-0.186
Token think
Token ID892
Feature activation-2.77e-01

Pos logit contributions
 derog+0.854
 curs+0.816
beit+0.749
 perpet+0.748
+0.679
Neg logit contributions
orio-1.315
acular-1.243
enegger-1.231
orious-1.201
 gears-1.166
Token this
Token ID428
Feature activation-6.00e-01

Pos logit contributions
 derog+2.088
 curs+2.022
beit+1.871
 perpet+1.860
��+1.744
Neg logit contributions
orio-2.571
acular-2.409
enegger-2.392
orious-2.321
 gears-2.236
Token event
Token ID1785
Feature activation+3.12e-01

Pos logit contributions
 derog+2.307
 curs+2.235
beit+2.058
 perpet+2.054
��+1.908
Neg logit contributions
orio-2.918
enegger-2.718
acular-2.712
orious-2.631
 gears-2.532
Token.
Token ID13
Feature activation+7.96e-02

Pos logit contributions
orio+1.477
acular+1.397
enegger+1.370
orious+1.342
 gears+1.315
Neg logit contributions
 derog-1.219
 curs-1.175
beit-1.093
 perpet-1.070
��-1.053
Token
Token ID198
Feature activation-5.28e-02

Pos logit contributions
orio+0.391
acular+0.367
enegger+0.363
orious+0.356
 gears+0.343
Neg logit contributions
 derog-0.304
 curs-0.291
beit-0.270
 perpet-0.267
��-0.255
Token
Token ID198
Feature activation-4.57e-02

Pos logit contributions
 derog+0.173
 curs+0.170
 perpet+0.156
beit+0.156
+0.147
Neg logit contributions
orio-0.283
enegger-0.268
acular-0.264
orious-0.257
 gears-0.253
TokenEnter
Token ID17469
Feature activation+2.59e+00

Pos logit contributions
 derog+0.191
 curs+0.184
beit+0.171
 perpet+0.170
��+0.161
Neg logit contributions
orio-0.208
acular-0.194
enegger-0.192
orious-0.188
 gears-0.180
Token The
Token ID383
Feature activation+8.29e-01

Pos logit contributions
orio+11.537
acular+11.003
orious+10.730
enegger+10.428
taining+10.252
Neg logit contributions
 derog-8.383
 curs-7.997
beit-7.636
��-7.423
 perpet-7.339
Token Joker
Token ID23582
Feature activation-2.18e-01

Pos logit contributions
orio+3.972
acular+3.716
enegger+3.639
orious+3.634
 gears+3.445
Neg logit contributions
 derog-3.214
 curs-3.056
beit-2.856
 perpet-2.801
��-2.699
Token.
Token ID13
Feature activation+8.55e-01

Pos logit contributions
 derog+0.852
 curs+0.822
beit+0.766
 perpet+0.755
��+0.720
Neg logit contributions
orio-1.043
acular-0.980
enegger-0.970
orious-0.946
 gears-0.915
Token
Token ID198
Feature activation+8.87e-01

Pos logit contributions
orio+3.954
acular+3.767
enegger+3.695
orious+3.643
 gears+3.471
Neg logit contributions
 derog-3.380
 curs-3.193
beit-2.992
 perpet-2.967
��-2.879
Token
Token ID198
Feature activation+5.60e-01

Pos logit contributions
orio+4.172
acular+3.943
enegger+3.820
orious+3.792
 gears+3.623
Neg logit contributions
 derog-3.535
 curs-3.366
beit-3.130
 perpet-3.057
��-3.037
Token file
Token ID2393
Feature activation-3.74e-01

Pos logit contributions
 derog+0.348
 curs+0.328
beit+0.295
 perpet+0.287
��+0.275
Neg logit contributions
orio-0.808
acular-0.766
enegger-0.761
orious-0.745
 gears-0.728
Token photo
Token ID4590
Feature activation-1.85e+00

Pos logit contributions
 derog+1.116
 curs+1.059
beit+0.965
 perpet+0.944
��+0.896
Neg logit contributions
orio-2.148
acular-2.035
enegger-2.018
orious-1.974
 gears-1.923
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
 derog+6.542
 curs+6.410
 perpet+5.881
beit+5.849
+5.353
Neg logit contributions
orio-8.966
acular-8.470
enegger-8.299
orious-8.230
 gears-7.913
Token Treasury
Token ID13419
Feature activation+1.47e+00

Pos logit contributions
 derog+0.446
 curs+0.426
beit+0.390
 perpet+0.383
��+0.372
Neg logit contributions
orio-0.764
acular-0.722
enegger-0.718
orious-0.701
 gears-0.681
Token Secretary
Token ID4986
Feature activation-4.94e-02

Pos logit contributions
orio+4.285
acular+3.797
 gears+3.653
orious+3.646
enegger+3.592
Neg logit contributions
 derog-7.866
 curs-7.636
��-7.527
beit-7.520
 perpet-7.194
Token Lew
Token ID8260
Feature activation+2.56e+00

Pos logit contributions
 derog+0.136
 curs+0.128
beit+0.117
 perpet+0.113
��+0.111
Neg logit contributions
orio-0.295
acular-0.280
enegger-0.276
orious-0.271
 gears-0.266
Token warned
Token ID7728
Feature activation-2.29e-01

Pos logit contributions
orio+10.172
enegger+9.973
acular+9.462
 gears+9.303
orious+8.865
Neg logit contributions
 derog-9.844
 curs-9.762
��-9.595
beit-9.013
 perpet-8.587
Token September
Token ID2693
Feature activation-3.70e-01

Pos logit contributions
 derog+0.891
 curs+0.861
beit+0.808
 perpet+0.786
��+0.767
Neg logit contributions
orio-1.100
acular-1.035
enegger-1.024
orious-0.999
 gears-0.971
Token 25
Token ID1679
Feature activation-6.67e-01

Pos logit contributions
 derog+1.143
 curs+1.088
beit+0.987
 perpet+0.982
+0.876
Neg logit contributions
orio-2.086
enegger-1.967
acular-1.967
orious-1.897
ierrez-1.838
Token,
Token ID11
Feature activation-1.53e+00

Pos logit contributions
 derog+2.539
 curs+2.447
beit+2.272
 perpet+2.245
��+2.119
Neg logit contributions
orio-3.267
acular-3.062
enegger-3.037
orious-2.959
 gears-2.864
Token 2013
Token ID2211
Feature activation-3.34e-01

Pos logit contributions
 derog+4.845
 curs+4.577
 perpet+4.248
beit+4.203
 ¶+3.722
Neg logit contributions
orio-8.258
acular-7.820
enegger-7.656
orious-7.530
 gears-7.243
Token the
Token ID262
Feature activation+5.63e-01

Pos logit contributions
orio+2.998
acular+2.801
enegger+2.785
orious+2.725
 gears+2.641
Neg logit contributions
 derog-2.713
 curs-2.611
beit-2.425
��-2.370
 perpet-2.351
Token panels
Token ID13043
Feature activation+6.80e-01

Pos logit contributions
orio+2.418
acular+2.274
enegger+2.232
orious+2.179
 gears+2.132
Neg logit contributions
 derog-2.424
 curs-2.341
beit-2.244
 perpet-2.166
��-2.147
Token is
Token ID318
Feature activation+8.16e-01

Pos logit contributions
orio+3.184
acular+3.035
enegger+2.982
orious+2.913
 gears+2.843
Neg logit contributions
 derog-2.613
 curs-2.548
beit-2.376
��-2.334
 perpet-2.284
Token composed
Token ID13160
Feature activation+4.03e-01

Pos logit contributions
orio+3.607
acular+3.437
enegger+3.350
orious+3.311
 gears+3.260
Neg logit contributions
 derog-3.216
 curs-3.107
beit-3.041
��-2.981
 perpet-2.836
Token of
Token ID286
Feature activation+7.92e-01

Pos logit contributions
orio+2.243
acular+2.195
enegger+2.130
orious+2.106
 gears+2.062
Neg logit contributions
 derog-1.168
 curs-1.129
beit-1.064
 perpet-0.991
��-0.984
Token combust
Token ID27500
Feature activation+2.55e+00

Pos logit contributions
orio+3.305
acular+3.141
enegger+3.091
 gears+3.066
orious+2.991
Neg logit contributions
 derog-3.317
 curs-3.173
beit-3.086
��-3.037
 perpet-2.922
Tokenible
Token ID856
Feature activation+7.62e-01

Pos logit contributions
orio+6.000
orious+5.515
acular+5.498
enegger+4.820
 gears+4.449
Neg logit contributions
 derog-14.536
 curs-13.993
beit-13.350
��-13.340
 perpet-12.814
Token plastic
Token ID7309
Feature activation+2.58e-01

Pos logit contributions
orio+3.141
acular+2.933
enegger+2.911
 gears+2.889
orious+2.816
Neg logit contributions
 derog-3.294
 curs-3.156
beit-3.071
��-2.975
 perpet-2.920
Token material
Token ID2587
Feature activation+9.66e-01

Pos logit contributions
orio+1.213
acular+1.139
enegger+1.133
orious+1.102
 gears+1.092
Neg logit contributions
 derog-1.012
 curs-0.975
beit-0.918
 perpet-0.895
��-0.884
Token.
Token ID13
Feature activation-4.29e-02

Pos logit contributions
orio+4.232
acular+4.034
enegger+3.970
 gears+3.872
orious+3.871
Neg logit contributions
 derog-3.842
 curs-3.751
beit-3.537
��-3.505
 perpet-3.375
Token A
Token ID317
Feature activation+5.41e-01

Pos logit contributions
 derog+0.157
 curs+0.150
beit+0.139
 perpet+0.137
��+0.131
Neg logit contributions
orio-0.217
acular-0.204
enegger-0.202
orious-0.197
 gears-0.191
Token federal
Token ID2717
Feature activation-7.99e-01

Pos logit contributions
 derog+0.641
 curs+0.619
beit+0.577
 perpet+0.568
��+0.540
Neg logit contributions
orio-0.772
acular-0.722
enegger-0.714
orious-0.697
 gears-0.675
Token government
Token ID1230
Feature activation-4.29e-02

Pos logit contributions
 derog+3.286
 curs+3.208
 perpet+2.997
beit+2.972
+2.777
Neg logit contributions
orio-3.584
acular-3.369
enegger-3.366
orious-3.214
reetings-3.064
Token.
Token ID13
Feature activation-9.55e-03

Pos logit contributions
 derog+0.164
 curs+0.158
beit+0.147
 perpet+0.144
��+0.139
Neg logit contributions
orio-0.209
acular-0.196
enegger-0.194
orious-0.190
 gears-0.184
Token
Token ID198
Feature activation+3.39e-01

Pos logit contributions
 derog+0.039
 curs+0.037
beit+0.034
 perpet+0.034
��+0.033
Neg logit contributions
orio-0.045
acular-0.042
enegger-0.042
orious-0.041
 gears-0.039
Token
Token ID198
Feature activation+1.55e-01

Pos logit contributions
orio+1.716
acular+1.610
enegger+1.601
orious+1.558
 gears+1.512
Neg logit contributions
 derog-1.232
 curs-1.188
beit-1.100
 perpet-1.087
��-1.018
TokenEr
Token ID9139
Feature activation+2.54e+00

Pos logit contributions
orio+0.686
acular+0.635
enegger+0.620
orious+0.619
rain+0.582
Neg logit contributions
 derog-0.686
 curs-0.652
beit-0.604
 perpet-0.601
��-0.581
Tokenn
Token ID77
Feature activation+4.21e-01

Pos logit contributions
orio+9.243
acular+8.323
orious+8.256
enegger+7.972
rain+7.851
Neg logit contributions
 derog-12.078
 curs-11.166
��-10.862
 perpet-10.661
 �-10.093
Tokenest
Token ID395
Feature activation+3.73e-01

Pos logit contributions
orio+2.077
acular+1.934
enegger+1.910
orious+1.874
 gears+1.783
Neg logit contributions
 derog-1.651
 curs-1.568
 perpet-1.443
beit-1.442
��-1.371
Tokeno
Token ID78
Feature activation-9.20e-01

Pos logit contributions
orio+1.862
acular+1.706
enegger+1.679
orious+1.668
 gears+1.572
Neg logit contributions
 derog-1.460
 curs-1.379
beit-1.269
 perpet-1.266
��-1.224
Token Gal
Token ID5027
Feature activation-1.15e+00

Pos logit contributions
 derog+3.205
 curs+3.110
beit+2.857
 perpet+2.830
+2.608
Neg logit contributions
orio-4.720
acular-4.473
enegger-4.440
orious-4.317
 gears-4.188
Tokenar
Token ID283
Feature activation-3.08e-01

Pos logit contributions
 derog+4.925
 curs+4.907
beit+4.666
 perpet+4.493
+4.342
Neg logit contributions
orio-4.605
enegger-4.411
acular-4.389
orious-4.165
 gears-4.097
Token in
Token ID287
Feature activation+2.21e-02

Pos logit contributions
orio+4.137
acular+3.880
enegger+3.783
 gears+3.738
orious+3.737
Neg logit contributions
 derog-3.600
 curs-3.489
beit-3.301
��-3.226
 perpet-3.143
Token general
Token ID2276
Feature activation+1.49e-02

Pos logit contributions
orio+0.106
acular+0.099
enegger+0.098
orious+0.096
 gears+0.094
Neg logit contributions
 derog-0.086
 curs-0.083
beit-0.078
 perpet-0.075
��-0.073
Token after
Token ID706
Feature activation+6.94e-01

Pos logit contributions
orio+0.072
acular+0.067
enegger+0.066
orious+0.065
 gears+0.063
Neg logit contributions
 derog-0.058
 curs-0.056
beit-0.052
 perpet-0.051
��-0.049
Token the
Token ID262
Feature activation+5.04e-01

Pos logit contributions
orio+3.154
acular+2.984
enegger+2.910
orious+2.873
 gears+2.809
Neg logit contributions
 derog-2.780
 curs-2.667
beit-2.498
 perpet-2.417
��-2.417
Token November
Token ID3389
Feature activation+6.92e-01

Pos logit contributions
orio+2.384
acular+2.239
enegger+2.203
orious+2.168
 gears+2.127
Neg logit contributions
 derog-1.952
 curs-1.867
beit-1.768
 perpet-1.714
��-1.670
Token election
Token ID3071
Feature activation+2.52e+00

Pos logit contributions
orio+3.406
acular+3.206
enegger+3.150
orious+3.129
 gears+3.055
Neg logit contributions
 derog-2.514
 curs-2.412
beit-2.257
 perpet-2.183
��-2.140
Token,
Token ID11
Feature activation+7.50e-01

Pos logit contributions
orio+8.994
acular+8.822
 gears+8.468
orious+8.401
enegger+8.141
Neg logit contributions
 derog-10.422
 curs-10.086
beit-9.705
��-9.693
 perpet-8.957
Token as
Token ID355
Feature activation+6.01e-01

Pos logit contributions
orio+3.627
acular+3.395
enegger+3.332
orious+3.278
 gears+3.231
Neg logit contributions
 derog-2.789
 curs-2.710
beit-2.511
 perpet-2.423
��-2.421
Token the
Token ID262
Feature activation+6.03e-01

Pos logit contributions
orio+2.719
acular+2.545
enegger+2.488
orious+2.451
 gears+2.434
Neg logit contributions
 derog-2.435
 curs-2.353
beit-2.195
 perpet-2.142
��-2.116
Token current
Token ID1459
Feature activation+7.89e-02

Pos logit contributions
orio+2.797
acular+2.603
enegger+2.563
orious+2.536
 gears+2.500
Neg logit contributions
 derog-2.398
 curs-2.297
beit-2.185
 perpet-2.095
��-2.059
Token highly
Token ID4047
Feature activation-3.22e-01

Pos logit contributions
orio+0.356
acular+0.331
enegger+0.328
orious+0.321
 gears+0.312
Neg logit contributions
 derog-0.329
 curs-0.317
beit-0.299
 perpet-0.293
��-0.283
Token more
Token ID517
Feature activation+2.25e-01

Pos logit contributions
 derog+1.844
 curs+1.778
beit+1.639
 perpet+1.622
��+1.522
Neg logit contributions
orio-2.594
acular-2.435
enegger-2.417
orious-2.356
 gears-2.283
Token difficult
Token ID2408
Feature activation+5.71e-01

Pos logit contributions
orio+0.949
acular+0.893
enegger+0.874
orious+0.864
 gears+0.831
Neg logit contributions
 derog-0.996
 curs-0.943
beit-0.907
 perpet-0.881
��-0.864
Token.
Token ID13
Feature activation+1.09e-01

Pos logit contributions
orio+2.525
acular+2.358
enegger+2.333
orious+2.276
 gears+2.219
Neg logit contributions
 derog-2.387
 curs-2.296
beit-2.174
��-2.105
 perpet-2.067
Token
Token ID198
Feature activation-5.22e-02

Pos logit contributions
orio+0.547
acular+0.514
enegger+0.507
orious+0.495
 gears+0.480
Neg logit contributions
 derog-0.411
 curs-0.391
beit-0.362
 perpet-0.356
��-0.342
Token
Token ID198
Feature activation-3.80e-01

Pos logit contributions
 derog+0.173
 curs+0.168
beit+0.156
 perpet+0.156
+0.146
Neg logit contributions
orio-0.279
enegger-0.264
acular-0.260
orious-0.253
 gears-0.249
TokenCand
Token ID41572
Feature activation+2.51e+00

Pos logit contributions
 derog+1.474
 curs+1.426
beit+1.329
 perpet+1.312
��+1.239
Neg logit contributions
orio-1.822
acular-1.706
enegger-1.695
orious-1.647
 gears-1.597
Tokenace
Token ID558
Feature activation-5.17e-01

Pos logit contributions
orio+9.282
acular+8.205
orious+7.874
enegger+7.503
rain+7.258
Neg logit contributions
 derog-12.220
 curs-11.135
 perpet-10.560
��-10.517
beit-10.321
Token Hilton
Token ID31248
Feature activation-8.68e-01

Pos logit contributions
 derog+1.852
 curs+1.783
beit+1.648
 perpet+1.625
��+1.527
Neg logit contributions
orio-2.647
acular-2.489
enegger-2.470
orious-2.409
 gears-2.337
Token said
Token ID531
Feature activation-3.20e-01

Pos logit contributions
 derog+3.158
 curs+3.044
beit+2.819
 perpet+2.798
��+2.590
Neg logit contributions
orio-4.341
acular-4.096
enegger-4.050
orious-3.958
 gears-3.816
Token she
Token ID673
Feature activation-7.32e-01

Pos logit contributions
 derog+1.118
 curs+1.076
beit+0.989
 perpet+0.979
��+0.916
Neg logit contributions
orio-1.667
acular-1.569
enegger-1.558
orious-1.519
 gears-1.472
Token
Token ID447
Feature activation-4.76e-01

Pos logit contributions
 derog+2.762
 curs+2.644
 perpet+2.468
beit+2.455
+2.297
Neg logit contributions
orio-3.560
acular-3.350
enegger-3.313
orious-3.236
reetings-3.102
Token G
Token ID402
Feature activation-2.04e-01

Pos logit contributions
orio+1.318
acular+1.247
enegger+1.226
orious+1.201
 gears+1.156
Neg logit contributions
 derog-1.059
 curs-1.020
beit-0.949
 perpet-0.930
��-0.891
Tokenainer
Token ID10613
Feature activation+5.94e-01

Pos logit contributions
 derog+0.971
 curs+0.943
beit+0.884
 perpet+0.876
��+0.835
Neg logit contributions
orio-0.816
acular-0.753
enegger-0.740
orious-0.722
reetings-0.690
Token Contest
Token ID27297
Feature activation+1.08e+00

Pos logit contributions
orio+3.013
acular+2.866
enegger+2.801
orious+2.772
 gears+2.656
Neg logit contributions
 derog-2.135
 curs-2.055
beit-1.868
 perpet-1.842
��-1.764
Token-
Token ID12
Feature activation+3.99e-01

Pos logit contributions
orio+5.384
acular+5.167
orious+5.057
enegger+4.967
 gears+4.695
Neg logit contributions
 derog-3.940
 curs-3.747
beit-3.378
 perpet-3.338
��-3.198
Token08
Token ID2919
Feature activation+7.73e-01

Pos logit contributions
orio+1.815
acular+1.702
enegger+1.658
orious+1.647
rain+1.562
Neg logit contributions
 derog-1.674
 curs-1.604
beit-1.479
 perpet-1.465
��-1.399
Token Election
Token ID14219
Feature activation+2.50e+00

Pos logit contributions
orio+3.839
acular+3.657
enegger+3.537
orious+3.506
 gears+3.387
Neg logit contributions
 derog-2.808
 curs-2.708
beit-2.463
 perpet-2.447
��-2.297
Token-
Token ID12
Feature activation+3.43e-01

Pos logit contributions
orio+10.981
acular+10.518
orious+10.230
enegger+9.770
rain+9.545
Neg logit contributions
 derog-8.988
 curs-8.550
beit-7.936
 perpet-7.811
��-7.581
TokenT
Token ID51
Feature activation+9.90e-01

Pos logit contributions
orio+1.575
acular+1.476
enegger+1.441
orious+1.426
rain+1.356
Neg logit contributions
 derog-1.428
 curs-1.370
beit-1.263
 perpet-1.248
��-1.197
Tokenravis
Token ID16956
Feature activation+5.00e-03

Pos logit contributions
orio+4.241
acular+3.993
orious+3.848
enegger+3.760
rain+3.593
Neg logit contributions
 derog-4.450
 curs-4.282
 perpet-3.914
beit-3.849
��-3.794
Token &
Token ID1222
Feature activation-2.68e-01

Pos logit contributions
orio+0.025
acular+0.024
enegger+0.023
orious+0.023
 gears+0.022
Neg logit contributions
 derog-0.019
 curs-0.018
beit-0.016
 perpet-0.016
��-0.016
Token Protect
Token ID21916
Feature activation+3.55e-01

Pos logit contributions
 derog+0.996
 curs+0.956
beit+0.884
 perpet+0.872
��+0.829
Neg logit contributions
orio-1.342
acular-1.259
enegger-1.250
orious-1.219
 gears-1.181
Token to
Token ID284
Feature activation+3.77e-01

Pos logit contributions
orio+3.722
acular+3.494
enegger+3.381
 gears+3.334
orious+3.319
Neg logit contributions
 derog-3.172
 curs-3.016
beit-2.923
��-2.890
 perpet-2.785
Token make
Token ID787
Feature activation+8.18e-01

Pos logit contributions
orio+1.841
acular+1.743
enegger+1.699
orious+1.674
 gears+1.651
Neg logit contributions
 derog-1.386
 curs-1.339
beit-1.269
��-1.221
 perpet-1.215
Token the
Token ID262
Feature activation+2.53e-01

Pos logit contributions
orio+3.541
acular+3.280
enegger+3.163
 gears+3.153
orious+3.145
Neg logit contributions
 derog-3.395
 curs-3.147
beit-3.111
��-3.080
 perpet-3.003
Token announcement
Token ID8009
Feature activation+1.29e-01

Pos logit contributions
orio+1.043
acular+0.967
enegger+0.948
orious+0.933
 gears+0.909
Neg logit contributions
 derog-1.148
 curs-1.105
beit-1.055
 perpet-1.033
��-1.011
Token on
Token ID319
Feature activation-1.09e-01

Pos logit contributions
orio+0.665
acular+0.633
enegger+0.621
orious+0.614
 gears+0.599
Neg logit contributions
 derog-0.442
 curs-0.425
beit-0.398
 perpet-0.385
��-0.383
Token Election
Token ID14219
Feature activation+2.50e+00

Pos logit contributions
 derog+0.402
 curs+0.383
beit+0.361
 perpet+0.352
��+0.339
Neg logit contributions
orio-0.547
acular-0.513
enegger-0.507
orious-0.498
 gears-0.485
Token Day
Token ID3596
Feature activation+1.01e+00

Pos logit contributions
orio+6.943
acular+6.684
orious+6.461
rain+6.078
ments+5.888
Neg logit contributions
 derog-12.507
 curs-11.936
beit-11.810
 perpet-11.376
��-11.296
Token,
Token ID11
Feature activation+3.80e-02

Pos logit contributions
orio+4.689
acular+4.481
orious+4.337
enegger+4.337
 gears+4.198
Neg logit contributions
 derog-3.780
 curs-3.658
beit-3.440
��-3.364
 perpet-3.292
Token posting
Token ID10754
Feature activation+7.87e-01

Pos logit contributions
orio+0.190
acular+0.179
enegger+0.176
orious+0.173
 gears+0.168
Neg logit contributions
 derog-0.140
 curs-0.134
beit-0.125
 perpet-0.122
��-0.119
Token photos
Token ID5205
Feature activation-9.76e-01

Pos logit contributions
orio+3.582
acular+3.326
enegger+3.293
orious+3.203
 gears+3.200
Neg logit contributions
 derog-3.112
 curs-2.940
beit-2.864
��-2.810
 perpet-2.767
Token of
Token ID286
Feature activation+7.44e-02

Pos logit contributions
 derog+2.876
 curs+2.744
beit+2.472
 perpet+2.448
��+2.238
Neg logit contributions
orio-5.623
acular-5.320
enegger-5.282
orious-5.166
 gears-5.022
Token it
Token ID340
Feature activation-7.82e-01

Pos logit contributions
 derog+2.453
 curs+2.367
beit+2.196
 perpet+2.178
��+2.039
Neg logit contributions
orio-3.078
acular-2.878
enegger-2.855
orious-2.779
 gears-2.689
Token happen
Token ID1645
Feature activation-5.63e-01

Pos logit contributions
 derog+2.971
 curs+2.849
 perpet+2.646
beit+2.633
+2.410
Neg logit contributions
orio-3.864
acular-3.587
enegger-3.573
orious-3.476
 gears-3.346
Token?
Token ID30
Feature activation+5.30e-01

Pos logit contributions
 derog+1.914
 curs+1.836
beit+1.686
 perpet+1.670
��+1.547
Neg logit contributions
orio-2.991
acular-2.811
enegger-2.792
orious-2.725
 gears-2.642
Token
Token ID198
Feature activation+7.21e-01

Pos logit contributions
orio+2.508
acular+2.360
enegger+2.328
orious+2.275
 gears+2.178
Neg logit contributions
 derog-2.097
 curs-1.996
beit-1.867
 perpet-1.819
��-1.794
Token
Token ID198
Feature activation+2.88e-01

Pos logit contributions
orio+3.446
acular+3.258
enegger+3.169
orious+3.136
 gears+3.002
Neg logit contributions
 derog-2.833
 curs-2.701
beit-2.510
 perpet-2.451
��-2.419
TokenNot
Token ID3673
Feature activation+2.49e+00

Pos logit contributions
orio+1.308
acular+1.223
enegger+1.199
orious+1.182
rain+1.120
Neg logit contributions
 derog-1.210
 curs-1.156
beit-1.070
 perpet-1.062
��-1.024
Token a
Token ID257
Feature activation+8.56e-01

Pos logit contributions
orio+10.460
orious+10.433
acular+10.264
enegger+9.674
 gears+9.191
Neg logit contributions
 derog-8.778
 curs-8.533
��-7.904
beit-7.895
 perpet-7.537
Token day
Token ID1110
Feature activation+4.22e-01

Pos logit contributions
orio+3.857
acular+3.646
enegger+3.560
orious+3.526
 gears+3.384
Neg logit contributions
 derog-3.414
 curs-3.252
beit-3.127
 perpet-3.035
��-2.988
Token goes
Token ID2925
Feature activation+1.32e-01

Pos logit contributions
orio+2.032
acular+1.910
enegger+1.854
orious+1.850
 gears+1.806
Neg logit contributions
 derog-1.624
 curs-1.549
beit-1.453
 perpet-1.413
��-1.409
Token by
Token ID416
Feature activation+6.43e-02

Pos logit contributions
orio+0.747
acular+0.719
orious+0.699
enegger+0.691
 gears+0.680
Neg logit contributions
 derog-0.378
 curs-0.363
beit-0.346
��-0.323
 perpet-0.320
Token that
Token ID326
Feature activation+2.56e-01

Pos logit contributions
orio+0.328
acular+0.309
enegger+0.303
orious+0.299
 gears+0.292
Neg logit contributions
 derog-0.228
 curs-0.220
beit-0.206
 perpet-0.200
��-0.195
Token it
Token ID340
Feature activation-1.35e+00

Pos logit contributions
 derog+3.945
 curs+3.799
 perpet+3.517
beit+3.508
 ¶+3.215
Neg logit contributions
orio-5.119
enegger-4.779
acular-4.775
orious-4.601
 gears-4.441
Token at
Token ID379
Feature activation-1.10e+00

Pos logit contributions
 derog+4.704
 curs+4.454
 perpet+4.173
beit+4.096
+3.747
Neg logit contributions
orio-6.942
acular-6.420
enegger-6.407
orious-6.192
reetings-6.020
Token El
Token ID2574
Feature activation+7.67e-01

Pos logit contributions
 derog+3.961
 curs+3.838
beit+3.535
 perpet+3.525
��+3.261
Neg logit contributions
orio-5.464
acular-5.128
enegger-5.079
orious-4.959
 gears-4.774
Token Rio
Token ID15338
Feature activation-1.22e+00

Pos logit contributions
orio+3.693
acular+3.406
enegger+3.325
orious+3.306
reetings+3.154
Neg logit contributions
 derog-2.994
 curs-2.781
 perpet-2.639
beit-2.589
��-2.561
Token on
Token ID319
Feature activation-5.01e-01

Pos logit contributions
 derog+4.498
 curs+4.293
 perpet+4.004
beit+4.003
+3.770
Neg logit contributions
orio-5.875
enegger-5.557
acular-5.532
orious-5.395
 gears-5.152
Token Election
Token ID14219
Feature activation+2.49e+00

Pos logit contributions
 derog+1.759
 curs+1.700
beit+1.560
 perpet+1.554
��+1.439
Neg logit contributions
orio-2.587
acular-2.438
enegger-2.422
orious-2.353
 gears-2.280
Token Night
Token ID5265
Feature activation+8.31e-02

Pos logit contributions
orio+7.191
acular+6.870
orious+6.659
rain+5.921
ments+5.907
Neg logit contributions
 derog-12.595
 curs-12.048
beit-11.877
 perpet-11.421
��-11.180
Token,
Token ID11
Feature activation-7.16e-01

Pos logit contributions
orio+0.383
acular+0.359
enegger+0.354
orious+0.346
 gears+0.334
Neg logit contributions
 derog-0.339
 curs-0.330
beit-0.308
 perpet-0.300
��-0.292
Token the
Token ID262
Feature activation+2.16e-01

Pos logit contributions
 derog+2.612
 curs+2.509
 perpet+2.331
beit+2.315
+2.115
Neg logit contributions
orio-3.594
acular-3.384
enegger-3.370
orious-3.255
 gears-3.145
Token night
Token ID1755
Feature activation-9.77e-02

Pos logit contributions
orio+1.078
acular+1.011
enegger+1.001
orious+0.979
 gears+0.950
Neg logit contributions
 derog-0.804
 curs-0.773
beit-0.719
 perpet-0.706
��-0.670
Token we
Token ID356
Feature activation+3.06e-01

Pos logit contributions
 derog+0.346
 curs+0.332
beit+0.307
 perpet+0.301
��+0.285
Neg logit contributions
orio-0.505
acular-0.475
enegger-0.471
orious-0.460
 gears-0.447
Token,
Token ID11
Feature activation+2.93e-02

Pos logit contributions
 derog+0.273
 curs+0.262
beit+0.245
 perpet+0.236
��+0.228
Neg logit contributions
orio-0.367
acular-0.347
enegger-0.343
orious-0.336
 gears-0.323
Token nature
Token ID3450
Feature activation+6.56e-01

Pos logit contributions
orio+0.135
acular+0.126
enegger+0.125
orious+0.122
 gears+0.119
Neg logit contributions
 derog-0.119
 curs-0.115
beit-0.108
 perpet-0.105
��-0.102
Token and
Token ID290
Feature activation+4.22e-01

Pos logit contributions
orio+3.075
acular+2.959
enegger+2.893
orious+2.809
 gears+2.774
Neg logit contributions
 derog-2.425
 curs-2.337
beit-2.278
��-2.123
 perpet-2.046
Token diversity
Token ID9573
Feature activation+1.65e-01

Pos logit contributions
orio+1.927
acular+1.803
enegger+1.786
orious+1.749
 gears+1.715
Neg logit contributions
 derog-1.691
 curs-1.630
beit-1.552
 perpet-1.475
��-1.474
Token.
Token ID13
Feature activation-2.10e-01

Pos logit contributions
orio+0.749
acular+0.703
enegger+0.694
orious+0.682
 gears+0.661
Neg logit contributions
 derog-0.681
 curs-0.657
beit-0.622
 perpet-0.590
��-0.585
Token Not
Token ID1892
Feature activation+2.49e+00

Pos logit contributions
 derog+0.795
 curs+0.760
beit+0.704
 perpet+0.695
��+0.662
Neg logit contributions
orio-1.043
acular-0.980
enegger-0.970
orious-0.948
 gears-0.915
Tokeneworthy
Token ID25969
Feature activation+3.66e-01

Pos logit contributions
orious+10.590
orio+10.221
acular+10.020
enegger+9.481
 surprisingly+9.025
Neg logit contributions
 derog-9.002
 curs-8.878
beit-8.233
��-7.989
 perpet-7.805
Token:
Token ID25
Feature activation+2.89e-01

Pos logit contributions
orio+1.747
acular+1.661
orious+1.610
enegger+1.609
 gears+1.574
Neg logit contributions
 derog-1.377
 curs-1.318
beit-1.223
��-1.205
 perpet-1.201
Token Under
Token ID4698
Feature activation+8.65e-01

Pos logit contributions
orio+1.425
acular+1.347
enegger+1.333
orious+1.311
 gears+1.278
Neg logit contributions
 derog-1.075
 curs-1.017
beit-0.954
 perpet-0.928
��-0.908
Tokenpass
Token ID6603
Feature activation+8.58e-01

Pos logit contributions
orio+3.627
enegger+3.305
acular+3.301
orious+3.298
 gears+3.128
Neg logit contributions
 derog-3.823
 curs-3.631
beit-3.427
 perpet-3.390
��-3.282
Token Park
Token ID3250
Feature activation-2.51e-01

Pos logit contributions
orio+3.978
acular+3.743
enegger+3.713
orious+3.617
 gears+3.536
Neg logit contributions
 derog-3.303
 curs-3.207
beit-3.025
 perpet-2.883
��-2.861
Token 1971
Token ID16382
Feature activation+9.32e-01

Pos logit contributions
orio+2.128
acular+1.999
enegger+1.978
orious+1.976
 gears+1.911
Neg logit contributions
 derog-1.493
 curs-1.429
beit-1.336
 perpet-1.293
��-1.240
Token's
Token ID338
Feature activation+1.28e-01

Pos logit contributions
orio+3.830
acular+3.623
orious+3.555
enegger+3.542
 gears+3.408
Neg logit contributions
 derog-3.984
 curs-3.911
beit-3.651
 perpet-3.530
��-3.495
Token Electric
Token ID13944
Feature activation+4.84e-01

Pos logit contributions
orio+0.637
acular+0.599
enegger+0.592
orious+0.587
 gears+0.566
Neg logit contributions
 derog-0.471
 curs-0.451
beit-0.417
 perpet-0.412
��-0.391
Token Warrior
Token ID14019
Feature activation+5.43e-01

Pos logit contributions
orio+2.211
acular+2.049
enegger+1.995
orious+1.987
reetings+1.911
Neg logit contributions
 derog-2.001
 curs-1.882
 perpet-1.768
beit-1.743
��-1.662
Token.
Token ID13
Feature activation+3.61e-01

Pos logit contributions
orio+2.420
acular+2.309
enegger+2.251
orious+2.227
 gears+2.157
Neg logit contributions
 derog-2.206
 curs-2.147
beit-1.981
 perpet-1.922
��-1.890
Token Not
Token ID1892
Feature activation+2.49e+00

Pos logit contributions
orio+1.773
acular+1.677
enegger+1.651
orious+1.628
 gears+1.561
Neg logit contributions
 derog-1.363
 curs-1.295
beit-1.204
 perpet-1.184
��-1.149
Token metal
Token ID6147
Feature activation+2.52e-01

Pos logit contributions
orious+10.634
acular+10.241
orio+10.157
enegger+9.359
 gears+9.133
Neg logit contributions
 derog-8.978
 curs-8.692
beit-8.102
��-7.968
 perpet-7.747
Token but
Token ID475
Feature activation+1.46e-01

Pos logit contributions
orio+1.208
acular+1.154
enegger+1.136
orious+1.120
 gears+1.089
Neg logit contributions
 derog-0.956
 curs-0.920
beit-0.847
 perpet-0.839
��-0.808
Token still
Token ID991
Feature activation+1.00e+00

Pos logit contributions
orio+0.676
acular+0.638
enegger+0.625
orious+0.614
 gears+0.599
Neg logit contributions
 derog-0.585
 curs-0.562
beit-0.524
 perpet-0.518
��-0.499
Token relevant
Token ID5981
Feature activation+6.68e-01

Pos logit contributions
orio+4.308
acular+4.210
orious+4.033
enegger+3.980
 gears+3.969
Neg logit contributions
 derog-4.070
 curs-3.895
beit-3.675
��-3.652
 perpet-3.580
Token.
Token ID13
Feature activation+3.15e-01

Pos logit contributions
orio+3.009
acular+2.907
enegger+2.858
 gears+2.796
orious+2.796
Neg logit contributions
 derog-2.603
 curs-2.486
beit-2.378
��-2.296
 perpet-2.274
Token why
Token ID1521
Feature activation-7.21e-02

Pos logit contributions
 derog+1.007
 curs+0.971
beit+0.899
 perpet+0.889
��+0.837
Neg logit contributions
orio-1.343
acular-1.260
enegger-1.250
orious-1.218
 gears-1.179
Token not
Token ID407
Feature activation+5.60e-01

Pos logit contributions
 derog+0.230
 curs+0.220
beit+0.202
 perpet+0.198
��+0.187
Neg logit contributions
orio-0.396
acular-0.375
enegger-0.371
orious-0.363
 gears-0.354
Token?
Token ID30
Feature activation-3.44e-02

Pos logit contributions
orio+2.638
acular+2.547
enegger+2.443
orious+2.419
 gears+2.388
Neg logit contributions
 derog-2.134
 curs-2.052
beit-1.942
��-1.839
 perpet-1.835
Token
Token ID198
Feature activation+6.01e-02

Pos logit contributions
 derog+0.129
 curs+0.124
beit+0.115
 perpet+0.113
��+0.107
Neg logit contributions
orio-0.171
acular-0.161
enegger-0.159
orious-0.156
 gears-0.150
Token
Token ID198
Feature activation-2.53e-01

Pos logit contributions
orio+0.317
enegger+0.299
acular+0.297
orious+0.288
 gears+0.283
Neg logit contributions
 derog-0.203
 curs-0.198
beit-0.183
 perpet-0.183
-0.170
TokenNot
Token ID3673
Feature activation+2.48e+00

Pos logit contributions
 derog+0.999
 curs+0.962
beit+0.894
 perpet+0.883
��+0.837
Neg logit contributions
orio-1.208
acular-1.132
enegger-1.118
orious-1.094
 gears-1.054
Token too
Token ID1165
Feature activation+8.21e-01

Pos logit contributions
orious+10.506
orio+10.232
acular+9.966
enegger+9.206
 gears+9.073
Neg logit contributions
 derog-8.933
 curs-8.808
beit-8.015
��-7.716
 perpet-7.715
Token many
Token ID867
Feature activation+3.49e-01

Pos logit contributions
orio+3.583
acular+3.382
orious+3.323
enegger+3.301
 gears+3.200
Neg logit contributions
 derog-3.357
 curs-3.238
beit-3.059
 perpet-2.998
��-2.952
Token players
Token ID1938
Feature activation+4.49e-01

Pos logit contributions
orio+1.582
acular+1.484
orious+1.438
enegger+1.436
 gears+1.421
Neg logit contributions
 derog-1.415
 curs-1.348
beit-1.306
 perpet-1.260
��-1.231
Token go
Token ID467
Feature activation+3.94e-01

Pos logit contributions
orio+2.182
acular+2.055
enegger+2.027
orious+2.003
 gears+1.953
Neg logit contributions
 derog-1.665
 curs-1.609
beit-1.516
 perpet-1.457
��-1.455
Token out
Token ID503
Feature activation-2.78e-01

Pos logit contributions
orio+1.846
acular+1.759
enegger+1.708
orious+1.708
 gears+1.674
Neg logit contributions
 derog-1.522
 curs-1.459
beit-1.393
 perpet-1.350
��-1.328
Token terms
Token ID2846
Feature activation-1.16e+00

Pos logit contributions
 derog+2.343
 curs+2.268
beit+2.085
 perpet+2.080
��+1.930
Neg logit contributions
orio-3.087
acular-2.897
enegger-2.885
orious-2.793
 gears-2.701
Token of
Token ID286
Feature activation-9.01e-02

Pos logit contributions
 derog+1.774
 curs+1.709
 perpet+1.528
beit+1.244
+1.205
Neg logit contributions
orio-8.096
enegger-7.925
acular-7.590
OPLE-7.471
reetings-7.446
Token a
Token ID257
Feature activation+1.59e-01

Pos logit contributions
 derog+0.347
 curs+0.334
beit+0.311
 perpet+0.307
��+0.290
Neg logit contributions
orio-0.437
acular-0.410
enegger-0.406
orious-0.396
 gears-0.383
Token qu
Token ID627
Feature activation+8.91e-01

Pos logit contributions
orio+0.762
acular+0.714
enegger+0.706
orious+0.689
 gears+0.666
Neg logit contributions
 derog-0.625
 curs-0.601
beit-0.561
 perpet-0.554
��-0.525
Tokenid
Token ID312
Feature activation-7.46e-01

Pos logit contributions
orio+3.578
acular+3.283
orious+3.061
enegger+2.971
rain+2.940
Neg logit contributions
 derog-4.211
 curs-4.070
��-3.828
 perpet-3.773
beit-3.766
Token pro
Token ID386
Feature activation-3.31e+00

Pos logit contributions
 derog+2.635
 curs+2.518
beit+2.344
 perpet+2.286
��+2.177
Neg logit contributions
orio-3.891
acular-3.667
enegger-3.592
orious-3.541
 gears-3.427
Token quo
Token ID18658
Feature activation-4.82e-01

Pos logit contributions
 curs+3.242
 derog+2.647
 perpet+2.115
+1.902
 mi+1.134
Neg logit contributions
enegger-23.594
orio-22.749
acular-22.394
yip-21.746
ierrez-21.743
Token,
Token ID11
Feature activation-3.52e-01

Pos logit contributions
 derog+1.789
 curs+1.726
beit+1.606
 perpet+1.573
��+1.503
Neg logit contributions
orio-2.401
acular-2.256
enegger-2.232
orious-2.182
 gears-2.115
Token it
Token ID340
Feature activation-3.63e-01

Pos logit contributions
 derog+1.285
 curs+1.234
beit+1.143
 perpet+1.127
��+1.070
Neg logit contributions
orio-1.781
acular-1.675
enegger-1.660
orious-1.621
 gears-1.572
Token
Token ID447
Feature activation-4.74e-01

Pos logit contributions
 derog+1.408
 curs+1.358
beit+1.263
 perpet+1.247
��+1.181
Neg logit contributions
orio-1.753
acular-1.642
enegger-1.628
orious-1.586
 gears-1.535
Token
Token ID247
Feature activation-4.61e-01

Pos logit contributions
 derog+1.065
 curs+1.058
beit+0.929
 perpet+0.903
��+0.838
Neg logit contributions
orio-2.980
enegger-2.914
acular-2.850
orious-2.763
reetings-2.713
Token to
Token ID284
Feature activation-7.84e-01

Pos logit contributions
 derog+1.834
 curs+1.768
beit+1.642
 perpet+1.621
��+1.533
Neg logit contributions
orio-2.364
acular-2.218
enegger-2.198
orious-2.144
 gears-2.075
Token have
Token ID423
Feature activation-7.77e-01

Pos logit contributions
 derog+2.914
 curs+2.806
beit+2.600
 perpet+2.574
��+2.406
Neg logit contributions
orio-3.907
acular-3.646
enegger-3.628
orious-3.533
 gears-3.418
Token risen
Token ID17450
Feature activation+2.69e-01

Pos logit contributions
 derog+2.976
 curs+2.889
beit+2.668
 perpet+2.656
��+2.482
Neg logit contributions
orio-3.759
acular-3.504
enegger-3.484
orious-3.398
 gears-3.259
Token up
Token ID510
Feature activation-8.69e-01

Pos logit contributions
orio+1.290
acular+1.223
enegger+1.196
orious+1.183
 gears+1.151
Neg logit contributions
 derog-1.023
 curs-0.992
beit-0.928
 perpet-0.904
��-0.882
Token in
Token ID287
Feature activation-7.99e-01

Pos logit contributions
 derog+3.121
 curs+3.002
beit+2.782
 perpet+2.757
+2.538
Neg logit contributions
orio-4.426
acular-4.121
enegger-4.110
orious-3.992
 gears-3.853
Token parallel
Token ID10730
Feature activation-3.19e+00

Pos logit contributions
 derog+3.180
 curs+3.076
beit+2.856
 perpet+2.840
��+2.663
Neg logit contributions
orio-3.764
acular-3.512
enegger-3.485
orious-3.384
 gears-3.261
Token fashion
Token ID6977
Feature activation-1.22e+00

Pos logit contributions
 derog+11.836
 curs+11.488
 perpet+10.929
beit+10.643
+10.205
Neg logit contributions
orio-13.262
enegger-11.799
acular-11.688
orious-11.507
reetings-10.996
Token,
Token ID11
Feature activation-4.06e-01

Pos logit contributions
 derog+4.401
 curs+4.231
beit+3.941
 perpet+3.929
+3.653
Neg logit contributions
orio-6.116
acular-5.669
enegger-5.648
orious-5.514
 gears-5.309
Tokenin
Token ID259
Feature activation-1.75e-01

Pos logit contributions
 derog+1.634
 curs+1.578
beit+1.473
 perpet+1.457
��+1.376
Neg logit contributions
orio-1.901
acular-1.774
enegger-1.760
orious-1.712
 gears-1.654
Token a
Token ID257
Feature activation-1.70e-01

Pos logit contributions
 derog+0.663
 curs+0.641
beit+0.597
 perpet+0.581
��+0.561
Neg logit contributions
orio-0.853
acular-0.803
enegger-0.794
orious-0.776
 gears-0.756
Token kind
Token ID1611
Feature activation-7.65e-01

Pos logit contributions
 derog+0.682
 curs+0.656
beit+0.617
 perpet+0.604
��+0.578
Neg logit contributions
orio-0.797
acular-0.748
enegger-0.737
orious-0.722
 gears-0.699
Token we
Token ID356
Feature activation-2.62e-02

Pos logit contributions
orio+3.419
acular+3.237
enegger+3.152
orious+3.125
 gears+3.097
Neg logit contributions
 derog-2.854
 curs-2.678
beit-2.554
 perpet-2.481
��-2.455
Token can
Token ID460
Feature activation-2.22e-01

Pos logit contributions
 derog+0.096
 curs+0.093
beit+0.086
 perpet+0.085
��+0.080
Neg logit contributions
orio-0.132
acular-0.124
enegger-0.123
orious-0.120
 gears-0.116
Token run
Token ID1057
Feature activation-4.60e-01

Pos logit contributions
 derog+0.793
 curs+0.762
beit+0.703
 perpet+0.695
��+0.651
Neg logit contributions
orio-1.138
acular-1.069
enegger-1.062
orious-1.035
 gears-1.002
Token it
Token ID340
Feature activation-7.01e-01

Pos logit contributions
 derog+1.762
 curs+1.700
beit+1.578
 perpet+1.559
��+1.472
Neg logit contributions
orio-2.244
acular-2.102
enegger-2.085
orious-2.031
 gears-1.965
Token in
Token ID287
Feature activation-8.69e-01

Pos logit contributions
 derog+2.475
 curs+2.386
beit+2.184
 perpet+2.165
��+1.986
Neg logit contributions
orio-3.642
acular-3.413
enegger-3.400
orious-3.304
 gears-3.189
Token parallel
Token ID10730
Feature activation-2.73e+00

Pos logit contributions
 derog+3.281
 curs+3.181
 perpet+2.925
beit+2.917
��+2.704
Neg logit contributions
orio-4.273
acular-3.982
enegger-3.975
orious-3.865
 gears-3.702
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
 derog+8.002
 curs+7.884
 perpet+7.017
beit+6.736
 ¶+6.567
Neg logit contributions
orio-14.087
enegger-13.538
acular-12.927
orious-12.824
reetings-12.568
Token To
Token ID1675
Feature activation+2.03e-01

Pos logit contributions
 derog+0.389
 curs+0.375
beit+0.345
 perpet+0.341
��+0.319
Neg logit contributions
orio-0.586
acular-0.551
enegger-0.548
orious-0.534
 gears-0.518
Token do
Token ID466
Feature activation-3.28e-01

Pos logit contributions
orio+1.036
acular+0.980
enegger+0.963
orious+0.947
 gears+0.928
Neg logit contributions
 derog-0.721
 curs-0.692
beit-0.646
 perpet-0.627
��-0.606
Token this
Token ID428
Feature activation-9.29e-01

Pos logit contributions
 derog+1.355
 curs+1.301
beit+1.225
 perpet+1.204
��+1.159
Neg logit contributions
orio-1.497
acular-1.401
enegger-1.375
orious-1.346
 gears-1.313
Token,
Token ID11
Feature activation-1.71e-01

Pos logit contributions
 derog+3.409
 curs+3.285
beit+3.037
 perpet+2.998
��+2.819
Neg logit contributions
orio-4.682
acular-4.386
enegger-4.358
orious-4.248
 gears-4.111
Token accusation
Token ID25984
Feature activation-5.85e-01

Pos logit contributions
orio+0.215
acular+0.202
enegger+0.199
orious+0.197
 gears+0.190
Neg logit contributions
 derog-0.160
 curs-0.155
beit-0.145
 perpet-0.139
��-0.136
Token that
Token ID326
Feature activation-5.89e-01

Pos logit contributions
 derog+2.261
 curs+2.180
beit+2.026
 perpet+2.003
��+1.891
Neg logit contributions
orio-2.836
acular-2.656
enegger-2.635
orious-2.565
 gears-2.482
Token he
Token ID339
Feature activation-7.23e-01

Pos logit contributions
 derog+1.866
 curs+1.786
beit+1.631
 perpet+1.608
��+1.494
Neg logit contributions
orio-3.261
acular-3.080
enegger-3.059
orious-2.988
 gears-2.904
Token was
Token ID373
Feature activation-6.74e-01

Pos logit contributions
 derog+2.692
 curs+2.588
beit+2.394
 perpet+2.383
��+2.213
Neg logit contributions
orio-3.608
acular-3.378
enegger-3.358
orious-3.266
 gears-3.157
Token a
Token ID257
Feature activation-1.68e-01

Pos logit contributions
 derog+2.738
 curs+2.645
beit+2.456
 perpet+2.455
��+2.288
Neg logit contributions
orio-3.131
acular-2.918
enegger-2.903
orious-2.807
 gears-2.716
Token serial
Token ID11389
Feature activation-2.68e+00

Pos logit contributions
 derog+0.635
 curs+0.611
beit+0.576
 perpet+0.559
��+0.537
Neg logit contributions
orio-0.823
acular-0.772
enegger-0.760
orious-0.749
 gears-0.721
Token cat
Token ID3797
Feature activation-3.98e-01

Pos logit contributions
 derog+9.435
 curs+9.071
 perpet+8.657
beit+7.800
+7.572
Neg logit contributions
orio-12.762
enegger-12.127
acular-12.049
reetings-11.353
orious-11.225
Token sl
Token ID1017
Feature activation-5.42e-01

Pos logit contributions
 derog+1.374
 curs+1.324
beit+1.231
 perpet+1.190
��+1.136
Neg logit contributions
orio-2.094
acular-1.972
enegger-1.949
orious-1.914
 gears-1.856
Tokenayer
Token ID2794
Feature activation-5.95e-01

Pos logit contributions
 derog+2.252
 curs+2.178
beit+2.034
 perpet+2.011
��+1.912
Neg logit contributions
orio-2.468
acular-2.302
enegger-2.280
orious-2.219
 gears-2.140
Token.
Token ID13
Feature activation+3.99e-02

Pos logit contributions
 derog+2.404
 curs+2.320
beit+2.156
 perpet+2.155
��+2.017
Neg logit contributions
orio-2.774
acular-2.590
enegger-2.570
orious-2.491
 gears-2.409
Token
Token ID198
Feature activation+4.99e-01

Pos logit contributions
orio+0.187
acular+0.177
enegger+0.174
orious+0.171
 gears+0.163
Neg logit contributions
 derog-0.162
 curs-0.155
beit-0.143
 perpet-0.141
��-0.138
Token few
Token ID1178
Feature activation+2.25e-01

Pos logit contributions
orio+3.870
acular+3.682
orious+3.544
enegger+3.503
 gears+3.374
Neg logit contributions
 derog-3.241
 curs-3.038
beit-2.960
 perpet-2.847
��-2.771
Token hours
Token ID2250
Feature activation+9.09e-01

Pos logit contributions
orio+1.134
acular+1.085
orious+1.048
enegger+1.048
 gears+1.025
Neg logit contributions
 derog-0.805
 curs-0.761
beit-0.729
 perpet-0.702
��-0.676
Token ago
Token ID2084
Feature activation+9.04e-01

Pos logit contributions
orio+4.154
acular+3.944
enegger+3.860
orious+3.838
 gears+3.718
Neg logit contributions
 derog-3.497
 curs-3.366
beit-3.204
 perpet-3.103
��-3.095
Token,
Token ID11
Feature activation+3.94e-01

Pos logit contributions
orio+3.969
acular+3.774
enegger+3.667
orious+3.619
 gears+3.503
Neg logit contributions
 derog-3.710
 curs-3.608
beit-3.401
��-3.267
 perpet-3.258
Token on
Token ID319
Feature activation+8.79e-01

Pos logit contributions
orio+1.839
acular+1.729
enegger+1.701
orious+1.671
 gears+1.625
Neg logit contributions
 derog-1.557
 curs-1.506
beit-1.416
 perpet-1.373
��-1.340
Token Billy
Token ID15890
Feature activation-2.68e+00

Pos logit contributions
orio+4.094
acular+3.850
orious+3.771
enegger+3.713
 gears+3.661
Neg logit contributions
 derog-3.358
 curs-3.201
beit-3.128
��-2.953
 perpet-2.921
Token Turner
Token ID15406
Feature activation-1.63e-01

Pos logit contributions
 derog+8.543
 curs+8.182
 perpet+7.712
beit+7.441
+7.125
Neg logit contributions
orio-12.856
enegger-12.590
acular-12.416
OPLE-11.745
rontal-11.736
Token,
Token ID11
Feature activation+1.43e-01

Pos logit contributions
 derog+0.623
 curs+0.603
beit+0.561
 perpet+0.548
��+0.529
Neg logit contributions
orio-0.789
acular-0.743
enegger-0.735
orious-0.717
 gears-0.697
Token the
Token ID262
Feature activation+4.51e-01

Pos logit contributions
orio+0.695
acular+0.652
enegger+0.643
orious+0.633
 gears+0.611
Neg logit contributions
 derog-0.549
 curs-0.530
beit-0.497
 perpet-0.483
��-0.469
Token Miko
Token ID49071
Feature activation-1.90e+00

Pos logit contributions
orio+2.099
acular+1.958
enegger+1.922
orious+1.919
 gears+1.863
Neg logit contributions
 derog-1.766
 curs-1.705
beit-1.624
 perpet-1.558
��-1.537
Token Grimes
Token ID49462
Feature activation+5.04e-01

Pos logit contributions
 derog+7.350
 curs+7.182
 perpet+6.593
beit+6.451
+6.314
Neg logit contributions
orio-8.801
enegger-8.219
acular-8.050
orious-7.840
ierrez-7.623
Token disagreement
Token ID25800
Feature activation+1.51e-01

Pos logit contributions
 derog+1.483
 curs+1.437
beit+1.353
 perpet+1.330
��+1.280
Neg logit contributions
orio-1.609
acular-1.501
enegger-1.481
orious-1.444
 gears-1.396
Token with
Token ID351
Feature activation-7.75e-01

Pos logit contributions
orio+0.757
acular+0.724
enegger+0.697
orious+0.691
 gears+0.675
Neg logit contributions
 derog-0.535
 curs-0.520
beit-0.482
 perpet-0.466
��-0.464
Token
Token ID564
Feature activation-1.05e-01

Pos logit contributions
 derog+2.706
 curs+2.598
beit+2.394
 perpet+2.362
��+2.209
Neg logit contributions
orio-4.033
acular-3.792
enegger-3.775
orious-3.676
 gears-3.564
Token
Token ID250
Feature activation-4.23e-01

Pos logit contributions
 derog+0.412
 curs+0.399
 perpet+0.368
beit+0.367
+0.332
Neg logit contributions
orio-0.507
acular-0.470
enegger-0.467
orious-0.463
 gears-0.442
TokenThis
Token ID1212
Feature activation-1.85e-01

Pos logit contributions
 derog+1.826
 curs+1.770
beit+1.669
 perpet+1.642
��+1.561
Neg logit contributions
orio-1.847
acular-1.718
enegger-1.711
orious-1.650
 gears-1.599
Token version
Token ID2196
Feature activation-2.66e+00

Pos logit contributions
 derog+0.708
 curs+0.682
beit+0.634
 perpet+0.625
��+0.594
Neg logit contributions
orio-0.903
acular-0.848
enegger-0.838
orious-0.820
 gears-0.793
Token had
Token ID550
Feature activation-3.57e-01

Pos logit contributions
 derog+8.880
 curs+8.417
 perpet+7.992
beit+7.622
+7.449
Neg logit contributions
orio-12.842
enegger-12.248
acular-11.806
orious-11.491
OPLE-11.332
Token the
Token ID262
Feature activation-2.19e-01

Pos logit contributions
 derog+1.364
 curs+1.315
beit+1.224
 perpet+1.207
��+1.144
Neg logit contributions
orio-1.745
acular-1.637
enegger-1.620
orious-1.581
 gears-1.533
Token most
Token ID749
Feature activation-2.42e-01

Pos logit contributions
 derog+0.870
 curs+0.840
beit+0.785
 perpet+0.773
��+0.736
Neg logit contributions
orio-1.033
acular-0.967
enegger-0.957
orious-0.933
 gears-0.903
Token motion
Token ID6268
Feature activation+6.00e-01

Pos logit contributions
 derog+1.055
 curs+1.021
beit+0.963
 perpet+0.949
��+0.908
Neg logit contributions
orio-1.046
acular-0.974
enegger-0.961
orious-0.936
 gears-0.903
Token
Token ID447
Feature activation-6.15e-02

Pos logit contributions
orio+2.865
acular+2.766
enegger+2.659
orious+2.624
 gears+2.566
Neg logit contributions
 derog-2.274
 curs-2.194
beit-2.072
 perpet-1.999
��-1.948
Token Baylor
Token ID28245
Feature activation+5.67e-01

Pos logit contributions
orio+0.948
acular+0.902
orious+0.878
enegger+0.873
 gears+0.852
Neg logit contributions
 derog-0.645
 curs-0.620
beit-0.583
 perpet-0.554
��-0.544
Token produced
Token ID4635
Feature activation+8.44e-01

Pos logit contributions
orio+2.730
acular+2.587
enegger+2.513
orious+2.510
 gears+2.449
Neg logit contributions
 derog-2.112
 curs-2.034
beit-1.945
 perpet-1.845
��-1.809
Token --
Token ID1377
Feature activation+5.57e-01

Pos logit contributions
orio+3.850
acular+3.670
orious+3.612
enegger+3.547
 gears+3.520
Neg logit contributions
 derog-3.237
 curs-3.125
beit-2.995
��-2.910
 perpet-2.808
Token but
Token ID475
Feature activation-2.50e-01

Pos logit contributions
orio+2.802
acular+2.678
enegger+2.602
orious+2.578
 gears+2.523
Neg logit contributions
 derog-1.960
 curs-1.892
beit-1.765
 perpet-1.674
��-1.665
Token was
Token ID373
Feature activation-3.64e-01

Pos logit contributions
 derog+0.944
 curs+0.909
beit+0.844
 perpet+0.832
��+0.788
Neg logit contributions
orio-1.233
acular-1.157
enegger-1.146
orious-1.118
 gears-1.083
Token fo
Token ID11511
Feature activation-2.65e+00

Pos logit contributions
 derog+1.467
 curs+1.420
beit+1.316
 perpet+1.311
��+1.228
Neg logit contributions
orio-1.706
acular-1.592
enegger-1.585
orious-1.534
 gears-1.481
Tokeniled
Token ID3902
Feature activation-1.41e+00

Pos logit contributions
 derog+9.930
 curs+9.905
beit+9.338
 perpet+9.309
+8.897
Neg logit contributions
orio-10.936
acular-10.434
enegger-10.381
 gears-9.804
orious-9.586
Token by
Token ID416
Feature activation-4.64e-01

Pos logit contributions
 derog+4.526
 curs+4.329
 perpet+4.025
beit+3.821
+3.471
Neg logit contributions
orio-7.699
enegger-7.258
acular-7.126
orious-6.884
OPLE-6.772
Token a
Token ID257
Feature activation+2.13e-01

Pos logit contributions
 derog+1.799
 curs+1.734
beit+1.614
 perpet+1.593
��+1.509
Neg logit contributions
orio-2.239
acular-2.097
enegger-2.079
orious-2.025
 gears-1.961
Token combination
Token ID6087
Feature activation-1.49e-01

Pos logit contributions
orio+0.982
acular+0.919
enegger+0.899
orious+0.886
 gears+0.860
Neg logit contributions
 derog-0.865
 curs-0.829
beit-0.789
 perpet-0.769
��-0.744
Token of
Token ID286
Feature activation+1.65e-01

Pos logit contributions
 derog+0.326
 curs+0.308
 perpet+0.266
beit+0.263
+0.222
Neg logit contributions
orio-0.977
enegger-0.930
acular-0.926
orious-0.903
reetings-0.880
Token plays
Token ID5341
Feature activation-1.70e-01

Pos logit contributions
 derog+2.071
 curs+1.989
 perpet+1.864
beit+1.839
+1.697
Neg logit contributions
orio-2.417
acular-2.246
enegger-2.229
orious-2.160
reetings-2.079
Token the
Token ID262
Feature activation-1.85e-01

Pos logit contributions
 derog+0.654
 curs+0.630
beit+0.591
 perpet+0.579
��+0.555
Neg logit contributions
orio-0.826
acular-0.774
enegger-0.768
orious-0.746
 gears-0.727
Token harmon
Token ID25625
Feature activation-2.40e-01

Pos logit contributions
 derog+0.709
 curs+0.683
beit+0.636
 perpet+0.627
��+0.594
Neg logit contributions
orio-0.898
acular-0.842
enegger-0.835
orious-0.813
 gears-0.788
Tokenica
Token ID3970
Feature activation-7.74e-01

Pos logit contributions
 derog+1.229
 curs+1.192
beit+1.125
 perpet+1.110
��+1.084
Neg logit contributions
orio-0.886
acular-0.810
enegger-0.788
orious-0.772
 gears-0.728
Token during
Token ID1141
Feature activation-6.28e-01

Pos logit contributions
 derog+2.797
 curs+2.682
 perpet+2.466
beit+2.452
��+2.262
Neg logit contributions
orio-3.934
acular-3.696
enegger-3.662
orious-3.572
 gears-3.445
Token Gon
Token ID35371
Feature activation-2.61e+00

Pos logit contributions
 derog+2.383
 curs+2.298
beit+2.132
 perpet+2.106
��+1.989
Neg logit contributions
orio-3.084
acular-2.891
enegger-2.867
orious-2.794
 gears-2.705
Tokenzo
Token ID10872
Feature activation-1.37e+00

Pos logit contributions
 derog+8.811
 curs+8.544
beit+8.036
 perpet+7.829
+7.608
Neg logit contributions
orio-11.803
enegger-11.256
acular-11.081
OPLE-10.921
ierrez-10.720
Token's
Token ID338
Feature activation-2.59e-01

Pos logit contributions
 derog+5.347
 curs+5.127
 perpet+4.801
beit+4.777
+4.467
Neg logit contributions
orio-6.424
acular-5.961
enegger-5.919
orious-5.781
 gears-5.561
Token song
Token ID3496
Feature activation-3.60e-01

Pos logit contributions
 derog+1.030
 curs+0.995
beit+0.934
 perpet+0.915
��+0.875
Neg logit contributions
orio-1.223
acular-1.143
enegger-1.132
orious-1.102
 gears-1.070
Token "
Token ID366
Feature activation+3.06e-01

Pos logit contributions
 derog+1.224
 curs+1.177
beit+1.083
 perpet+1.063
��+1.000
Neg logit contributions
orio-1.911
acular-1.803
enegger-1.782
orious-1.743
 gears-1.693
TokenI
Token ID40
Feature activation-1.13e-01

Pos logit contributions
orio+1.391
acular+1.301
enegger+1.270
orious+1.258
reetings+1.193
Neg logit contributions
 derog-1.289
 curs-1.234
beit-1.143
 perpet-1.138
��-1.076
Token that
Token ID326
Feature activation-8.69e-01

Pos logit contributions
 derog+0.463
 curs+0.443
beit+0.418
 perpet+0.406
��+0.399
Neg logit contributions
orio-0.550
acular-0.520
enegger-0.509
orious-0.506
 gears-0.492
Token the
Token ID262
Feature activation-7.58e-02

Pos logit contributions
 derog+3.426
 curs+3.312
beit+3.073
 perpet+3.064
��+2.823
Neg logit contributions
orio-4.142
acular-3.863
enegger-3.860
orious-3.713
 gears-3.578
Token NFL
Token ID5134
Feature activation+4.37e-01

Pos logit contributions
 derog+0.290
 curs+0.279
beit+0.262
 perpet+0.255
��+0.245
Neg logit contributions
orio-0.368
acular-0.346
enegger-0.340
orious-0.335
 gears-0.325
Token would
Token ID561
Feature activation-3.64e-01

Pos logit contributions
orio+2.228
acular+2.102
enegger+2.059
orious+2.034
 gears+1.984
Neg logit contributions
 derog-1.534
 curs-1.476
beit-1.378
 perpet-1.315
��-1.299
Token provide
Token ID2148
Feature activation+7.29e-02

Pos logit contributions
 derog+1.278
 curs+1.227
beit+1.128
 perpet+1.119
��+1.041
Neg logit contributions
orio-1.895
acular-1.780
enegger-1.769
orious-1.724
 gears-1.670
Token san
Token ID5336
Feature activation-2.58e+00

Pos logit contributions
orio+0.344
acular+0.322
enegger+0.315
orious+0.312
 gears+0.307
Neg logit contributions
 derog-0.283
 curs-0.270
beit-0.258
 perpet-0.249
��-0.248
Tokenitized
Token ID36951
Feature activation-1.59e+00

Pos logit contributions
 derog+8.013
 curs+7.648
 perpet+7.012
beit+6.912
itized+6.321
Neg logit contributions
orio-13.171
enegger-12.750
acular-12.558
orious-11.977
OPLE-11.890
Token limited
Token ID3614
Feature activation-1.34e+00

Pos logit contributions
 derog+5.742
 curs+5.599
 perpet+5.057
beit+4.798
 ¶+4.519
Neg logit contributions
orio-7.952
enegger-7.578
acular-7.549
orious-7.155
ierrez-6.958
Token evidence
Token ID2370
Feature activation-2.70e-01

Pos logit contributions
 derog+4.890
 curs+4.730
 perpet+4.291
beit+4.183
+3.822
Neg logit contributions
orio-6.766
enegger-6.399
acular-6.395
orious-6.095
ierrez-5.906
Token in
Token ID287
Feature activation-4.19e-01

Pos logit contributions
 derog+0.958
 curs+0.922
beit+0.860
 perpet+0.838
��+0.806
Neg logit contributions
orio-1.382
acular-1.304
enegger-1.286
orious-1.263
 gears-1.229
Token an
Token ID281
Feature activation-6.36e-01

Pos logit contributions
 derog+1.729
 curs+1.670
beit+1.571
 perpet+1.534
��+1.482
Neg logit contributions
orio-1.913
acular-1.786
enegger-1.763
orious-1.725
 gears-1.669
Token functions
Token ID5499
Feature activation+1.67e-01

Pos logit contributions
 derog+1.860
 curs+1.786
beit+1.659
 perpet+1.631
��+1.543
Neg logit contributions
orio-2.662
acular-2.502
enegger-2.478
orious-2.424
 gears-2.357
Token that
Token ID326
Feature activation+2.65e-01

Pos logit contributions
orio+0.811
acular+0.758
enegger+0.747
orious+0.736
 gears+0.717
Neg logit contributions
 derog-0.638
 curs-0.612
beit-0.579
 perpet-0.561
��-0.549
Token will
Token ID481
Feature activation-6.86e-02

Pos logit contributions
orio+1.278
acular+1.196
enegger+1.176
orious+1.161
 gears+1.132
Neg logit contributions
 derog-1.020
 curs-0.980
beit-0.923
 perpet-0.896
��-0.871
Token run
Token ID1057
Feature activation-1.36e-01

Pos logit contributions
 derog+0.253
 curs+0.244
beit+0.226
 perpet+0.223
��+0.210
Neg logit contributions
orio-0.344
acular-0.323
enegger-0.320
orious-0.312
 gears-0.303
Token in
Token ID287
Feature activation-6.01e-01

Pos logit contributions
 derog+0.512
 curs+0.492
beit+0.458
 perpet+0.450
��+0.428
Neg logit contributions
orio-0.674
acular-0.632
enegger-0.626
orious-0.611
 gears-0.594
Token parallel
Token ID10730
Feature activation-2.57e+00

Pos logit contributions
 derog+2.043
 curs+1.960
beit+1.804
 perpet+1.776
��+1.667
Neg logit contributions
orio-3.191
acular-3.007
enegger-2.984
orious-2.914
 gears-2.830
Token.
Token ID13
Feature activation-3.77e-01

Pos logit contributions
 derog+7.624
 curs+7.444
 perpet+6.829
 ¶+6.265
beit+6.259
Neg logit contributions
orio-13.204
enegger-12.873
acular-12.389
orious-12.023
reetings-11.706
Token All
Token ID1439
Feature activation+3.45e-01

Pos logit contributions
 derog+1.320
 curs+1.275
beit+1.169
 perpet+1.158
��+1.080
Neg logit contributions
orio-1.961
acular-1.842
enegger-1.837
orious-1.780
 gears-1.725
Token these
Token ID777
Feature activation-1.39e-01

Pos logit contributions
orio+1.675
acular+1.572
enegger+1.548
orious+1.536
 gears+1.496
Neg logit contributions
 derog-1.307
 curs-1.238
beit-1.169
 perpet-1.142
��-1.101
Token lambda
Token ID37456
Feature activation-7.20e-01

Pos logit contributions
 derog+0.474
 curs+0.452
beit+0.423
 perpet+0.412
��+0.393
Neg logit contributions
orio-0.734
acular-0.692
enegger-0.682
orious-0.672
 gears-0.658
Token function
Token ID2163
Feature activation+2.37e-01

Pos logit contributions
 derog+2.599
 curs+2.490
beit+2.335
 perpet+2.288
��+2.176
Neg logit contributions
orio-3.673
acular-3.457
enegger-3.409
orious-3.348
 gears-3.273
Token of
Token ID286
Feature activation+2.32e-01

Pos logit contributions
orio+2.616
acular+2.462
orious+2.428
 gears+2.409
enegger+2.385
Neg logit contributions
 derog-2.011
 curs-1.896
beit-1.882
��-1.807
 perpet-1.746
Token whose
Token ID3025
Feature activation+2.66e-01

Pos logit contributions
orio+0.975
acular+0.905
orious+0.879
enegger+0.876
 gears+0.858
Neg logit contributions
 derog-1.027
 curs-0.989
beit-0.943
��-0.909
 perpet-0.906
Token members
Token ID1866
Feature activation-1.76e-01

Pos logit contributions
orio+1.156
acular+1.071
enegger+1.056
orious+1.044
 gears+1.021
Neg logit contributions
 derog-1.142
 curs-1.097
beit-1.044
 perpet-1.013
��-0.998
Token have
Token ID423
Feature activation-1.16e-01

Pos logit contributions
 derog+0.596
 curs+0.573
beit+0.525
 perpet+0.512
��+0.498
Neg logit contributions
orio-0.928
acular-0.877
enegger-0.867
orious-0.851
 gears-0.829
Token been
Token ID587
Feature activation-2.78e-01

Pos logit contributions
 derog+0.422
 curs+0.404
beit+0.378
 perpet+0.365
��+0.358
Neg logit contributions
orio-0.582
acular-0.548
enegger-0.543
orious-0.532
 gears-0.520
Token accused
Token ID5371
Feature activation-2.57e+00

Pos logit contributions
 derog+0.993
 curs+0.955
beit+0.879
 perpet+0.873
��+0.811
Neg logit contributions
orio-1.430
acular-1.345
enegger-1.334
orious-1.299
 gears-1.259
Token of
Token ID286
Feature activation-6.45e-01

Pos logit contributions
 derog+5.863
 curs+5.396
 perpet+4.902
beit+4.510
+4.013
Neg logit contributions
orio-15.992
enegger-15.191
acular-14.943
orious-14.476
reetings-14.363
Token mass
Token ID2347
Feature activation-1.62e+00

Pos logit contributions
 derog+2.462
 curs+2.374
beit+2.198
 perpet+2.185
��+2.049
Neg logit contributions
orio-3.154
acular-2.954
enegger-2.937
orious-2.853
 gears-2.759
Token rape
Token ID7262
Feature activation-1.83e+00

Pos logit contributions
 derog+4.549
 curs+4.313
 perpet+3.954
beit+3.777
+3.420
Neg logit contributions
orio-9.384
enegger-8.900
acular-8.869
orious-8.546
 gears-8.320
Token,
Token ID11
Feature activation-3.68e-01

Pos logit contributions
 derog+5.635
 curs+5.292
 perpet+5.041
beit+4.645
+4.387
Neg logit contributions
orio-10.095
enegger-9.540
acular-9.417
orious-9.054
reetings-8.878
Token was
Token ID373
Feature activation-4.84e-01

Pos logit contributions
 derog+1.366
 curs+1.317
beit+1.217
 perpet+1.207
��+1.127
Neg logit contributions
orio-1.842
acular-1.730
enegger-1.717
orious-1.671
 gears-1.615
Tokeni
Token ID72
Feature activation-5.16e-01

Pos logit contributions
orio+0.058
acular+0.054
enegger+0.052
orious+0.051
 gears+0.048
Neg logit contributions
 derog-0.066
 curs-0.064
beit-0.059
 perpet-0.059
��-0.058
Token M
Token ID337
Feature activation-1.80e-01

Pos logit contributions
 derog+1.971
 curs+1.900
beit+1.766
 perpet+1.742
��+1.649
Neg logit contributions
orio-2.523
acular-2.365
enegger-2.342
orious-2.284
 gears-2.212
Tokenok
Token ID482
Feature activation+2.15e-01

Pos logit contributions
 derog+0.752
 curs+0.726
beit+0.678
 perpet+0.670
��+0.637
Neg logit contributions
orio-0.818
acular-0.762
enegger-0.751
orious-0.733
 gears-0.705
Tokenup
Token ID929
Feature activation-2.61e-01

Pos logit contributions
orio+0.942
acular+0.882
enegger+0.853
orious+0.840
 gears+0.800
Neg logit contributions
 derog-0.941
 curs-0.906
beit-0.843
 perpet-0.841
��-0.804
Tokenuni
Token ID35657
Feature activation-1.95e+00

Pos logit contributions
 derog+1.161
 curs+1.125
beit+1.055
 perpet+1.045
��+0.996
Neg logit contributions
orio-1.117
acular-1.037
enegger-1.025
orious-0.995
 gears-0.957
Token ma
Token ID17266
Feature activation-2.53e+00

Pos logit contributions
 derog+6.295
 curs+6.092
 perpet+5.605
beit+5.456
+5.242
Neg logit contributions
orio-10.018
enegger-9.615
acular-9.329
orious-9.217
ierrez-8.851
Token
Token ID220
Feature activation-2.55e-01

Pos logit contributions
 derog+8.164
 curs+7.949
 perpet+7.355
beit+7.160
+7.119
Neg logit contributions
orio-12.256
enegger-11.834
acular-11.443
orious-11.351
rontal-10.872
Token
Token ID134
Feature activation-1.74e-01

Pos logit contributions
 derog+1.039
 curs+0.999
beit+0.928
 perpet+0.916
��+0.866
Neg logit contributions
orio-1.210
acular-1.127
enegger-1.102
orious-1.086
 gears-1.038
Token
Token ID119
Feature activation+2.23e-02

Pos logit contributions
 derog+0.643
 curs+0.618
beit+0.572
 perpet+0.565
��+0.530
Neg logit contributions
orio-0.876
acular-0.822
enegger-0.814
orious-0.796
 gears-0.770
TokenOk
Token ID18690
Feature activation+5.69e-01

Pos logit contributions
orio+0.100
acular+0.092
enegger+0.091
orious+0.089
 gears+0.085
Neg logit contributions
 derog-0.096
 curs-0.093
beit-0.086
 perpet-0.086
��-0.082
Tokenak
Token ID461
Feature activation+3.63e-01

Pos logit contributions
orio+2.343
acular+2.224
enegger+2.088
orious+2.080
ilus+1.975
Neg logit contributions
 derog-2.645
 curs-2.524
 perpet-2.381
beit-2.368
��-2.266
Token,
Token ID11
Feature activation-2.64e-01

Pos logit contributions
orio+1.299
acular+1.230
enegger+1.206
orious+1.184
 gears+1.148
Neg logit contributions
 derog-1.115
 curs-1.081
beit-1.021
��-0.984
 perpet-0.982
Token telecommunications
Token ID27473
Feature activation-7.70e-02

Pos logit contributions
 derog+1.015
 curs+0.978
beit+0.913
 perpet+0.896
��+0.860
Neg logit contributions
orio-1.280
acular-1.202
enegger-1.190
orious-1.163
 gears-1.124
Token companies
Token ID2706
Feature activation-5.10e-01

Pos logit contributions
 derog+0.317
 curs+0.308
beit+0.293
 perpet+0.282
��+0.278
Neg logit contributions
orio-0.345
acular-0.324
enegger-0.317
orious-0.315
 gears-0.308
Token were
Token ID547
Feature activation-5.67e-01

Pos logit contributions
 derog+1.853
 curs+1.784
beit+1.653
 perpet+1.625
��+1.541
Neg logit contributions
orio-2.585
acular-2.430
enegger-2.408
orious-2.352
 gears-2.281
Token granted
Token ID7520
Feature activation-1.96e+00

Pos logit contributions
 derog+2.114
 curs+2.044
 perpet+1.874
beit+1.866
��+1.734
Neg logit contributions
orio-2.826
acular-2.645
enegger-2.636
orious-2.543
 gears-2.470
Token retro
Token ID12175
Feature activation-2.53e+00

Pos logit contributions
 derog+7.292
 curs+7.029
 perpet+6.434
beit+6.117
 ¶+5.754
Neg logit contributions
orio-9.579
enegger-9.081
acular-8.883
orious-8.483
reetings-8.241
Tokenactive
Token ID5275
Feature activation-1.66e+00

Pos logit contributions
 derog+8.922
 curs+8.591
 perpet+7.902
beit+7.639
+7.302
Neg logit contributions
orio-12.267
acular-11.635
enegger-11.412
orious-10.843
OPLE-10.643
Token immunity
Token ID16989
Feature activation-1.51e+00

Pos logit contributions
 derog+4.004
 curs+3.717
 perpet+3.207
beit+2.999
+2.714
Neg logit contributions
orio-10.442
acular-9.930
enegger-9.912
orious-9.609
reetings-9.296
Token for
Token ID329
Feature activation-1.02e+00

Pos logit contributions
 derog+4.908
 curs+4.568
 perpet+4.299
beit+4.006
+3.850
Neg logit contributions
orio-8.234
enegger-7.692
acular-7.670
orious-7.391
reetings-7.203
Token violating
Token ID18134
Feature activation-3.70e-01

Pos logit contributions
 derog+3.773
 curs+3.638
 perpet+3.370
beit+3.291
��+3.035
Neg logit contributions
orio-5.143
enegger-4.857
acular-4.785
orious-4.619
 gears-4.484
Token the
Token ID262
Feature activation-8.78e-02

Pos logit contributions
 derog+1.360
 curs+1.307
beit+1.216
 perpet+1.196
��+1.132
Neg logit contributions
orio-1.855
acular-1.743
enegger-1.725
orious-1.690
 gears-1.636
Token and
Token ID290
Feature activation+2.02e-01

Pos logit contributions
orio+1.565
acular+1.484
enegger+1.449
orious+1.429
 gears+1.404
Neg logit contributions
 derog-1.208
 curs-1.166
beit-1.095
 perpet-1.051
��-1.047
Token slap
Token ID23905
Feature activation-1.09e+00

Pos logit contributions
orio+0.922
acular+0.872
enegger+0.846
orious+0.834
 gears+0.829
Neg logit contributions
 derog-0.810
 curs-0.771
beit-0.736
 perpet-0.719
��-0.708
Tokenstick
Token ID13915
Feature activation-8.86e-01

Pos logit contributions
 derog+4.147
 curs+4.047
beit+3.709
 perpet+3.706
��+3.437
Neg logit contributions
orio-5.270
acular-4.889
enegger-4.871
orious-4.742
 gears-4.522
Token moments
Token ID7188
Feature activation-3.74e-01

Pos logit contributions
 derog+3.672
 curs+3.575
 perpet+3.298
beit+3.282
��+3.037
Neg logit contributions
orio-4.067
acular-3.749
enegger-3.733
orious-3.625
reetings-3.459
Token whenever
Token ID8797
Feature activation-1.26e-01

Pos logit contributions
 derog+1.449
 curs+1.398
beit+1.301
 perpet+1.282
��+1.218
Neg logit contributions
orio-1.804
acular-1.692
enegger-1.676
orious-1.633
 gears-1.582
Token Gon
Token ID35371
Feature activation-2.52e+00

Pos logit contributions
 derog+0.503
 curs+0.485
beit+0.454
 perpet+0.445
��+0.428
Neg logit contributions
orio-0.595
acular-0.557
enegger-0.550
orious-0.536
 gears-0.522
Token gets
Token ID3011
Feature activation+2.89e-02

Pos logit contributions
 derog+8.805
 curs+8.537
 perpet+8.004
beit+7.886
+7.600
Neg logit contributions
orio-11.131
enegger-10.779
acular-10.600
orious-10.274
OPLE-10.146
Token into
Token ID656
Feature activation+3.22e-01

Pos logit contributions
orio+0.134
acular+0.125
enegger+0.123
orious+0.120
 gears+0.117
Neg logit contributions
 derog-0.117
 curs-0.113
beit-0.106
 perpet-0.104
��-0.100
Token a
Token ID257
Feature activation+5.64e-01

Pos logit contributions
orio+1.394
acular+1.309
enegger+1.261
orious+1.239
 gears+1.225
Neg logit contributions
 derog-1.376
 curs-1.329
beit-1.277
 perpet-1.229
��-1.209
Token fight
Token ID1907
Feature activation+8.06e-01

Pos logit contributions
orio+2.444
acular+2.300
enegger+2.230
orious+2.210
 gears+2.152
Neg logit contributions
 derog-2.386
 curs-2.284
beit-2.200
 perpet-2.120
��-2.082
Token.
Token ID13
Feature activation+9.96e-03

Pos logit contributions
orio+3.829
acular+3.693
enegger+3.576
orious+3.521
 gears+3.437
Neg logit contributions
 derog-3.031
 curs-2.924
beit-2.725
��-2.643
 perpet-2.602
Token category
Token ID6536
Feature activation-5.92e-01

Pos logit contributions
orio+3.418
acular+3.212
enegger+3.093
orious+3.071
 gears+3.049
Neg logit contributions
 derog-3.222
 curs-3.087
beit-3.028
��-2.859
 perpet-2.822
Token of
Token ID286
Feature activation+3.48e-01

Pos logit contributions
 derog+2.456
 curs+2.373
beit+2.215
 perpet+2.195
��+2.080
Neg logit contributions
orio-2.697
acular-2.513
enegger-2.495
orious-2.422
 gears-2.337
Token planets
Token ID14705
Feature activation-3.09e-01

Pos logit contributions
orio+1.585
acular+1.486
enegger+1.459
orious+1.423
 gears+1.414
Neg logit contributions
 derog-1.409
 curs-1.361
beit-1.292
 perpet-1.247
��-1.216
Token known
Token ID1900
Feature activation-4.49e-01

Pos logit contributions
 derog+1.232
 curs+1.190
beit+1.108
 perpet+1.096
��+1.036
Neg logit contributions
orio-1.459
acular-1.363
enegger-1.353
orious-1.315
 gears-1.271
Token as
Token ID355
Feature activation-6.75e-02

Pos logit contributions
 derog+1.511
 curs+1.467
beit+1.356
 perpet+1.317
��+1.276
Neg logit contributions
orio-2.358
acular-2.257
enegger-2.222
orious-2.178
 gears-2.113
Token mini
Token ID9927
Feature activation-2.52e+00

Pos logit contributions
 derog+0.259
 curs+0.249
beit+0.235
 perpet+0.229
��+0.220
Neg logit contributions
orio-0.326
acular-0.306
enegger-0.301
orious-0.294
 gears-0.288
Token-
Token ID12
Feature activation-2.14e-01

Pos logit contributions
 curs+8.817
 derog+8.807
 perpet+8.006
beit+7.725
+7.621
Neg logit contributions
orio-11.528
enegger-11.109
acular-10.790
orious-10.560
ierrez-10.471
TokenNe
Token ID8199
Feature activation+4.29e-01

Pos logit contributions
 derog+0.982
 curs+0.947
beit+0.891
 perpet+0.883
��+0.843
Neg logit contributions
orio-0.898
acular-0.831
enegger-0.809
orious-0.790
 gears-0.760
Tokenpt
Token ID457
Feature activation+4.91e-01

Pos logit contributions
orio+1.777
acular+1.646
orious+1.545
enegger+1.537
reetings+1.475
Neg logit contributions
 derog-2.033
 curs-1.936
beit-1.809
 perpet-1.778
��-1.715
Tokenunes
Token ID4015
Feature activation-3.39e-01

Pos logit contributions
orio+1.536
acular+1.471
orious+1.359
enegger+1.357
ilus+1.242
Neg logit contributions
 derog-2.777
 curs-2.668
beit-2.553
 perpet-2.504
��-2.479
Token.
Token ID13
Feature activation-2.09e-02

Pos logit contributions
 derog+1.286
 curs+1.240
beit+1.151
 perpet+1.137
��+1.073
Neg logit contributions
orio-1.667
acular-1.563
enegger-1.550
orious-1.511
 gears-1.463
Token turned
Token ID2900
Feature activation+2.86e-01

Pos logit contributions
 derog+1.776
 curs+1.705
beit+1.586
 perpet+1.578
��+1.464
Neg logit contributions
orio-2.191
acular-2.051
enegger-2.032
orious-1.976
 gears-1.911
Token criticism
Token ID7734
Feature activation-7.15e-01

Pos logit contributions
orio+1.347
acular+1.260
enegger+1.237
orious+1.222
 gears+1.211
Neg logit contributions
 derog-1.115
 curs-1.074
beit-1.015
 perpet-0.992
��-0.977
Token of
Token ID286
Feature activation-4.03e-01

Pos logit contributions
 derog+1.960
 curs+1.860
beit+1.685
 perpet+1.638
��+1.530
Neg logit contributions
orio-4.260
acular-4.063
enegger-4.006
orious-3.952
 gears-3.845
Token its
Token ID663
Feature activation-5.65e-01

Pos logit contributions
 derog+1.453
 curs+1.398
beit+1.299
 perpet+1.272
��+1.218
Neg logit contributions
orio-2.052
acular-1.925
enegger-1.909
orious-1.868
 gears-1.816
Token brutal
Token ID12399
Feature activation-4.54e-01

Pos logit contributions
 derog+2.128
 curs+2.050
beit+1.907
 perpet+1.877
��+1.780
Neg logit contributions
orio-2.786
acular-2.612
enegger-2.590
orious-2.528
 gears-2.449
Token version
Token ID2196
Feature activation-2.52e+00

Pos logit contributions
 derog+1.642
 curs+1.580
beit+1.467
 perpet+1.437
��+1.366
Neg logit contributions
orio-2.310
acular-2.167
enegger-2.151
orious-2.104
 gears-2.040
Token of
Token ID286
Feature activation-6.51e-01

Pos logit contributions
 derog+5.910
 curs+5.517
 perpet+4.937
beit+4.745
+4.481
Neg logit contributions
orio-15.056
enegger-14.334
acular-14.201
orious-13.750
reetings-13.659
Token Islam
Token ID3449
Feature activation-5.44e-01

Pos logit contributions
 derog+2.376
 curs+2.289
beit+2.116
 perpet+2.090
��+1.965
Neg logit contributions
orio-3.290
acular-3.091
enegger-3.067
orious-2.989
 gears-2.896
Token into
Token ID656
Feature activation-2.87e-01

Pos logit contributions
 derog+2.181
 curs+2.103
beit+1.960
 perpet+1.943
��+1.829
Neg logit contributions
orio-2.553
acular-2.378
enegger-2.371
orious-2.293
 gears-2.222
Token an
Token ID281
Feature activation-8.80e-02

Pos logit contributions
 derog+1.097
 curs+1.058
beit+0.992
 perpet+0.968
��+0.928
Neg logit contributions
orio-1.394
acular-1.312
enegger-1.296
orious-1.266
 gears-1.231
Token attack
Token ID1368
Feature activation+2.72e-01

Pos logit contributions
 derog+0.319
 curs+0.308
beit+0.286
 perpet+0.279
��+0.270
Neg logit contributions
orio-0.444
acular-0.422
enegger-0.412
orious-0.406
 gears-0.393
Tokeneed
Token ID2308
Feature activation+6.01e-01

Pos logit contributions
orio+3.274
acular+3.116
enegger+3.006
orious+2.967
 gears+2.808
Neg logit contributions
 derog-3.495
 curs-3.337
 perpet-3.061
beit-3.014
��-2.944
Token has
Token ID468
Feature activation-2.05e-01

Pos logit contributions
orio+2.870
enegger+2.699
acular+2.690
orious+2.588
 gears+2.566
Neg logit contributions
 derog-2.281
 curs-2.206
beit-2.045
 perpet-1.965
��-1.945
Token been
Token ID587
Feature activation-1.17e-01

Pos logit contributions
 derog+0.779
 curs+0.751
beit+0.698
 perpet+0.687
��+0.652
Neg logit contributions
orio-1.009
acular-0.946
enegger-0.939
orious-0.914
 gears-0.887
Token making
Token ID1642
Feature activation+2.25e-01

Pos logit contributions
 derog+0.469
 curs+0.454
beit+0.425
 perpet+0.415
��+0.402
Neg logit contributions
orio-0.546
acular-0.512
enegger-0.507
orious-0.496
 gears-0.479
Token a
Token ID257
Feature activation+5.80e-02

Pos logit contributions
orio+1.021
acular+0.968
enegger+0.944
orious+0.933
 gears+0.919
Neg logit contributions
 derog-0.907
 curs-0.868
beit-0.833
 perpet-0.802
��-0.788
Token version
Token ID2196
Feature activation-2.49e+00

Pos logit contributions
orio+0.268
acular+0.251
enegger+0.247
orious+0.243
 gears+0.235
Neg logit contributions
 derog-0.235
 curs-0.225
beit-0.213
 perpet-0.208
��-0.199
Token of
Token ID286
Feature activation-4.46e-01

Pos logit contributions
 derog+6.508
 curs+6.118
 perpet+5.589
beit+5.230
+4.919
Neg logit contributions
orio-14.504
enegger-13.733
acular-13.496
orious-13.211
 gears-12.904
Token this
Token ID428
Feature activation-8.35e-01

Pos logit contributions
 derog+1.759
 curs+1.701
beit+1.578
 perpet+1.566
��+1.476
Neg logit contributions
orio-2.120
acular-1.983
enegger-1.970
orious-1.912
 gears-1.847
Token argument
Token ID4578
Feature activation+7.42e-02

Pos logit contributions
 derog+3.069
 curs+2.962
 perpet+2.728
beit+2.719
��+2.511
Neg logit contributions
orio-4.213
acular-3.925
enegger-3.913
orious-3.792
 gears-3.663
Token for
Token ID329
Feature activation-1.03e+00

Pos logit contributions
orio+0.368
acular+0.351
enegger+0.345
orious+0.339
 gears+0.330
Neg logit contributions
 derog-0.271
 curs-0.262
beit-0.244
 perpet-0.235
��-0.231
Token many
Token ID867
Feature activation-8.95e-02

Pos logit contributions
 derog+3.807
 curs+3.674
 perpet+3.411
beit+3.325
 ¶+3.078
Neg logit contributions
orio-5.163
acular-4.787
enegger-4.783
orious-4.602
reetings-4.466
Tokenop
Token ID404
Feature activation+2.26e-01

Pos logit contributions
orio+0.762
acular+0.705
enegger+0.691
orious+0.676
 gears+0.638
Neg logit contributions
 derog-0.814
 curs-0.789
beit-0.731
 perpet-0.730
��-0.700
Tokenā
Token ID10235
Feature activation-7.75e-01

Pos logit contributions
orio+0.987
acular+0.916
enegger+0.892
orious+0.875
 gears+0.830
Neg logit contributions
 derog-1.000
 curs-0.966
beit-0.902
 perpet-0.892
��-0.860
Tokenp
Token ID79
Feature activation-5.94e-01

Pos logit contributions
 derog+3.258
 curs+3.162
beit+2.966
 perpet+2.935
+2.763
Neg logit contributions
orio-3.445
enegger-3.216
acular-3.213
orious-3.107
 gears-2.997
Tokenā
Token ID10235
Feature activation-7.45e-01

Pos logit contributions
 derog+2.445
 curs+2.367
beit+2.211
 perpet+2.192
��+2.069
Neg logit contributions
orio-2.705
acular-2.521
enegger-2.512
orious-2.434
 gears-2.360
Token.
Token ID13
Feature activation-5.66e-01

Pos logit contributions
 derog+3.109
 curs+3.017
beit+2.827
 perpet+2.798
��+2.633
Neg logit contributions
orio-3.336
acular-3.114
enegger-3.113
orious-3.011
 gears-2.903
Token Pa
Token ID11243
Feature activation-2.49e+00

Pos logit contributions
 derog+1.918
 curs+1.842
beit+1.692
 perpet+1.668
��+1.564
Neg logit contributions
orio-3.015
acular-2.842
enegger-2.817
orious-2.753
 gears-2.672
Token
Token ID134
Feature activation-1.25e+00

Pos logit contributions
 derog+9.658
 curs+9.435
 perpet+8.837
beit+8.773
+8.625
Neg logit contributions
orio-10.183
enegger-9.885
acular-9.427
orious-9.292
 gears-9.025
Token
Token ID119
Feature activation-6.62e-01

Pos logit contributions
 derog+3.901
 curs+3.779
beit+3.440
 perpet+3.421
��+3.408
Neg logit contributions
orio-6.663
enegger-6.414
acular-6.338
orious-6.121
 gears-6.031
Tokenē
Token ID27092
Feature activation-6.72e-02

Pos logit contributions
 derog+2.878
 curs+2.796
beit+2.651
 perpet+2.603
+2.484
Neg logit contributions
orio-2.799
enegger-2.606
acular-2.603
orious-2.513
 gears-2.452
Token ak
Token ID47594
Feature activation-1.45e+00

Pos logit contributions
 derog+0.258
 curs+0.248
beit+0.230
 perpet+0.228
��+0.217
Neg logit contributions
orio-0.328
acular-0.308
enegger-0.302
orious-0.295
 gears-0.287
Tokenula
Token ID4712
Feature activation-1.78e+00

Pos logit contributions
 derog+6.131
 curs+6.036
beit+5.744
 perpet+5.614
+5.448
Neg logit contributions
orio-5.941
enegger-5.636
acular-5.479
orious-5.336
 gears-5.233
Token Temple
Token ID10857
Feature activation-2.13e-01

Pos logit contributions
 derog+3.423
 curs+3.295
beit+3.048
 perpet+3.009
��+2.833
Neg logit contributions
orio-4.750
acular-4.460
enegger-4.427
orious-4.316
 gears-4.183
Token
Token ID198
Feature activation+5.63e-01

Pos logit contributions
 derog+0.872
 curs+0.840
beit+0.777
 perpet+0.768
��+0.734
Neg logit contributions
orio-1.006
acular-0.959
enegger-0.913
orious-0.906
 gears-0.872
Token
Token ID198
Feature activation-1.79e-01

Pos logit contributions
orio+2.768
acular+2.605
enegger+2.559
orious+2.514
 gears+2.425
Neg logit contributions
 derog-2.138
 curs-2.050
beit-1.900
 perpet-1.868
��-1.801
TokenAddress
Token ID20231
Feature activation-1.17e-01

Pos logit contributions
 derog+0.849
 curs+0.839
beit+0.804
 perpet+0.791
+0.771
Neg logit contributions
orio-0.681
enegger-0.638
acular-0.623
orious-0.599
 gears-0.592
Token:
Token ID25
Feature activation-7.92e-01

Pos logit contributions
 derog+0.386
 curs+0.374
beit+0.348
 perpet+0.345
+0.322
Neg logit contributions
orio-0.625
enegger-0.592
acular-0.584
orious-0.568
 gears-0.557
Token Da
Token ID9637
Feature activation-2.47e+00

Pos logit contributions
 derog+2.670
 curs+2.583
beit+2.371
 perpet+2.338
+2.163
Neg logit contributions
orio-4.189
acular-3.932
enegger-3.920
orious-3.815
 gears-3.709
Tokenar
Token ID283
Feature activation+1.11e-01

Pos logit contributions
 curs+9.897
 derog+9.845
beit+9.665
+9.476
 perpet+9.091
Neg logit contributions
orio-9.215
enegger-8.410
acular-8.352
 gears-8.277
orious-8.273
Tokenuk
Token ID2724
Feature activation-1.39e-01

Pos logit contributions
orio+0.512
acular+0.484
enegger+0.472
orious+0.463
 gears+0.443
Neg logit contributions
 derog-0.453
 curs-0.434
 perpet-0.405
beit-0.400
��-0.384
Tokenavan
Token ID12421
Feature activation-8.38e-01

Pos logit contributions
 derog+0.580
 curs+0.559
beit+0.521
 perpet+0.519
��+0.493
Neg logit contributions
orio-0.630
acular-0.592
enegger-0.580
orious-0.567
 gears-0.544
Tokenam
Token ID321
Feature activation-9.00e-01

Pos logit contributions
 derog+3.217
 curs+3.112
beit+2.901
 perpet+2.846
��+2.690
Neg logit contributions
orio-4.043
acular-3.766
enegger-3.765
orious-3.650
 gears-3.544
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
 derog+3.358
 curs+3.239
beit+3.006
 perpet+2.958
��+2.780
Neg logit contributions
orio-4.425
acular-4.130
enegger-4.126
orious-4.003
 gears-3.896
Token
Token ID134
Feature activation-5.78e-01

Pos logit contributions
 derog+3.620
 curs+3.487
beit+3.226
 perpet+3.188
��+3.000
Neg logit contributions
orio-4.939
acular-4.635
enegger-4.602
orious-4.486
 gears-4.345
Token
Token ID119
Feature activation-2.56e-01

Pos logit contributions
 derog+1.652
 curs+1.621
beit+1.530
 perpet+1.484
��+1.473
Neg logit contributions
orio-3.242
enegger-3.146
acular-3.061
orious-2.957
 gears-2.952
Tokeni
Token ID72
Feature activation-5.11e-01

Pos logit contributions
 derog+1.113
 curs+1.078
beit+1.007
 perpet+0.998
��+0.954
Neg logit contributions
orio-1.121
acular-1.040
enegger-1.027
orious-1.000
 gears-0.959
Token pa
Token ID14187
Feature activation-2.06e+00

Pos logit contributions
 derog+1.633
 curs+1.562
beit+1.430
 perpet+1.405
��+1.316
Neg logit contributions
orio-2.822
acular-2.665
enegger-2.642
orious-2.585
 gears-2.513
Tokenia
Token ID544
Feature activation-1.07e+00

Pos logit contributions
 derog+7.443
 curs+7.225
 perpet+6.734
beit+6.663
+6.398
Neg logit contributions
orio-9.629
enegger-9.167
acular-8.988
orious-8.827
 gears-8.595
Token ma
Token ID17266
Feature activation-2.46e+00

Pos logit contributions
 derog+3.368
 curs+3.218
beit+2.926
 perpet+2.919
+2.668
Neg logit contributions
orio-5.914
enegger-5.593
acular-5.585
orious-5.438
 gears-5.279
Token Mei
Token ID42244
Feature activation-1.30e+00

Pos logit contributions
 derog+7.940
 curs+7.712
 perpet+7.166
beit+6.996
+6.899
Neg logit contributions
orio-12.043
enegger-11.576
acular-11.225
orious-11.089
 gears-10.712
Token 25
Token ID1679
Feature activation-4.63e-01

Pos logit contributions
 derog+4.364
 curs+4.216
beit+3.858
 perpet+3.839
+3.620
Neg logit contributions
orio-6.720
enegger-6.350
acular-6.317
orious-6.159
 gears-5.987
Token,
Token ID11
Feature activation-1.22e+00

Pos logit contributions
 derog+1.744
 curs+1.677
beit+1.557
 perpet+1.525
��+1.458
Neg logit contributions
orio-2.304
acular-2.166
enegger-2.124
orious-2.084
 gears-2.023
Token 2018
Token ID2864
Feature activation-1.81e-01

Pos logit contributions
 derog+4.280
 curs+4.110
 perpet+3.799
beit+3.773
+3.497
Neg logit contributions
orio-6.185
enegger-5.844
acular-5.813
orious-5.637
 gears-5.456
Token ma
Token ID17266
Feature activation-1.99e+00

Pos logit contributions
 derog+0.596
 curs+0.571
beit+0.525
 perpet+0.511
��+0.491
Neg logit contributions
orio-0.983
acular-0.927
enegger-0.915
orious-0.897
 gears-0.874
Token is
Token ID318
Feature activation+5.13e-01

Pos logit contributions
orio+4.106
acular+3.851
 gears+3.728
orious+3.724
enegger+3.682
Neg logit contributions
 derog-3.398
 curs-3.276
beit-3.077
��-3.031
 perpet-2.973
Token Lean
Token ID45661
Feature activation+9.73e-01

Pos logit contributions
orio+2.245
acular+2.094
enegger+2.054
orious+2.044
 gears+2.007
Neg logit contributions
 derog-2.114
 curs-2.023
beit-1.937
��-1.882
 perpet-1.866
Token Six
Token ID9699
Feature activation-3.29e-01

Pos logit contributions
orio+4.244
acular+3.901
orious+3.828
enegger+3.815
 gears+3.803
Neg logit contributions
 derog-3.879
 curs-3.682
��-3.542
beit-3.503
 perpet-3.428
Token Sigma
Token ID31669
Feature activation+9.46e-02

Pos logit contributions
 derog+0.776
 curs+0.733
beit+0.652
 perpet+0.650
+0.569
Neg logit contributions
orio-2.090
enegger-1.987
acular-1.985
orious-1.934
 gears-1.880
Token?
Token ID30
Feature activation+1.40e+00

Pos logit contributions
orio+0.475
acular+0.451
enegger+0.442
orious+0.435
 gears+0.426
Neg logit contributions
 derog-0.341
 curs-0.331
beit-0.305
 perpet-0.299
��-0.290
Token
Token ID198
Feature activation+1.61e+00

Pos logit contributions
orio+5.742
acular+5.412
orious+5.330
enegger+5.147
 gears+5.065
Neg logit contributions
 derog-5.727
 curs-5.537
beit-5.262
��-5.141
 perpet-5.110
Token
Token ID198
Feature activation+8.88e-01

Pos logit contributions
orio+6.477
acular+6.248
orious+5.936
enegger+5.716
rain+5.636
Neg logit contributions
 derog-7.203
 curs-6.804
��-6.617
beit-6.350
 perpet-6.079
TokenDef
Token ID7469
Feature activation+1.65e+00

Pos logit contributions
orio+3.688
acular+3.445
orious+3.414
enegger+3.272
rain+3.256
Neg logit contributions
 derog-3.941
 curs-3.782
 perpet-3.479
beit-3.450
��-3.378
Tokenining
Token ID3191
Feature activation+1.18e+00

Pos logit contributions
orio+5.763
acular+5.208
orious+5.137
enegger+5.047
rain+4.963
Neg logit contributions
 derog-8.170
 curs-7.788
��-7.239
 perpet-7.229
beit-7.219
Token Lean
Token ID45661
Feature activation+1.07e+00

Pos logit contributions
orio+4.832
acular+4.425
orious+4.372
 gears+4.346
enegger+4.345
Neg logit contributions
 derog-4.896
 curs-4.724
beit-4.596
��-4.472
 perpet-4.376
Token Six
Token ID9699
Feature activation-2.34e-01

Pos logit contributions
orio+4.525
acular+4.158
orious+4.072
 gears+4.066
enegger+4.020
Neg logit contributions
 derog-4.364
 curs-4.082
��-3.956
beit-3.936
 perpet-3.813
Token have
Token ID423
Feature activation+2.13e-01

Pos logit contributions
orio+3.900
acular+3.790
orious+3.653
enegger+3.652
 gears+3.573
Neg logit contributions
 derog-3.474
 curs-3.415
beit-3.241
��-3.236
 perpet-3.046
Token that
Token ID326
Feature activation-2.27e-01

Pos logit contributions
orio+1.014
acular+0.954
enegger+0.940
orious+0.923
 gears+0.907
Neg logit contributions
 derog-0.827
 curs-0.796
beit-0.753
 perpet-0.725
��-0.719
Token many
Token ID867
Feature activation+7.81e-02

Pos logit contributions
 derog+0.839
 curs+0.809
beit+0.747
 perpet+0.741
��+0.691
Neg logit contributions
orio-1.139
acular-1.067
enegger-1.061
orious-1.033
 gears-0.998
Token good
Token ID922
Feature activation-3.51e-01

Pos logit contributions
orio+0.363
acular+0.340
enegger+0.334
orious+0.327
 gears+0.321
Neg logit contributions
 derog-0.315
 curs-0.302
beit-0.286
 perpet-0.279
��-0.271
Token years
Token ID812
Feature activation+3.16e-01

Pos logit contributions
 derog+1.443
 curs+1.398
beit+1.301
 perpet+1.291
��+1.215
Neg logit contributions
orio-1.610
acular-1.505
enegger-1.493
orious-1.449
 gears-1.392
Token left
Token ID1364
Feature activation+1.80e+00

Pos logit contributions
orio+1.463
acular+1.372
enegger+1.353
orious+1.324
 gears+1.288
Neg logit contributions
 derog-1.276
 curs-1.235
beit-1.155
 perpet-1.121
��-1.109
Token in
Token ID287
Feature activation+7.25e-01

Pos logit contributions
orio+7.546
acular+7.176
orious+7.039
enegger+6.820
 gears+6.733
Neg logit contributions
 derog-6.966
 curs-6.858
��-6.547
beit-6.481
 perpet-5.936
Token me
Token ID502
Feature activation-5.36e-02

Pos logit contributions
orio+2.825
acular+2.623
enegger+2.537
orious+2.503
 gears+2.466
Neg logit contributions
 derog-3.386
 curs-3.284
beit-3.124
��-3.041
 perpet-2.961
Token,
Token ID11
Feature activation+2.89e-01

Pos logit contributions
 derog+0.208
 curs+0.201
beit+0.187
 perpet+0.182
��+0.177
Neg logit contributions
orio-0.258
acular-0.243
enegger-0.239
orious-0.235
 gears-0.227
Token and
Token ID290
Feature activation+4.24e-01

Pos logit contributions
orio+1.437
acular+1.353
enegger+1.330
orious+1.315
 gears+1.279
Neg logit contributions
 derog-1.069
 curs-1.029
beit-0.955
 perpet-0.925
��-0.910
Token I
Token ID314
Feature activation-3.15e-01

Pos logit contributions
orio+1.992
acular+1.873
enegger+1.836
orious+1.816
 gears+1.769
Neg logit contributions
 derog-1.675
 curs-1.615
beit-1.510
 perpet-1.464
��-1.449
Token also
Token ID635
Feature activation+3.74e-01

Pos logit contributions
orio+1.829
acular+1.717
enegger+1.710
orious+1.664
 gears+1.659
Neg logit contributions
 derog-1.325
 curs-1.295
beit-1.212
��-1.167
 perpet-1.148
Token wrote
Token ID2630
Feature activation+3.19e-01

Pos logit contributions
orio+1.722
acular+1.614
enegger+1.608
orious+1.563
 gears+1.548
Neg logit contributions
 derog-1.484
 curs-1.443
beit-1.364
��-1.309
 perpet-1.304
Token that
Token ID326
Feature activation-5.49e-01

Pos logit contributions
orio+1.427
acular+1.349
enegger+1.317
orious+1.278
 gears+1.266
Neg logit contributions
 derog-1.287
 curs-1.246
beit-1.212
��-1.169
 perpet-1.154
Token
Token ID564
Feature activation+6.02e-01

Pos logit contributions
 derog+2.025
 curs+1.953
beit+1.804
 perpet+1.786
��+1.674
Neg logit contributions
orio-2.760
acular-2.588
enegger-2.570
orious-2.503
 gears-2.422
Token
Token ID250
Feature activation-4.11e-01

Pos logit contributions
orio+2.954
acular+2.766
enegger+2.743
orious+2.677
 gears+2.590
Neg logit contributions
 derog-2.284
 curs-2.201
beit-2.042
 perpet-2.018
��-1.902
Tokensign
Token ID12683
Feature activation+1.76e+00

Pos logit contributions
 derog+1.760
 curs+1.710
beit+1.606
 perpet+1.588
��+1.500
Neg logit contributions
orio-1.810
acular-1.682
enegger-1.672
orious-1.617
 gears-1.564
Tokenificantly
Token ID42491
Feature activation-9.40e-03

Pos logit contributions
orio+6.231
acular+6.072
orious+5.599
reetings+5.220
 gears+5.145
Neg logit contributions
 derog-8.032
 curs-7.884
beit-7.577
��-7.480
 perpet-7.148
Token scaling
Token ID20796
Feature activation-1.01e+00

Pos logit contributions
 derog+0.037
 curs+0.036
beit+0.034
 perpet+0.033
��+0.033
Neg logit contributions
orio-0.044
acular-0.041
enegger-0.040
orious-0.040
 gears-0.039
Token back
Token ID736
Feature activation-4.17e-01

Pos logit contributions
 derog+3.381
 curs+3.247
beit+2.961
 perpet+2.941
��+2.703
Neg logit contributions
orio-5.430
acular-5.116
enegger-5.083
orious-4.956
 gears-4.770
Token the
Token ID262
Feature activation-2.04e-01

Pos logit contributions
 derog+1.658
 curs+1.599
beit+1.494
 perpet+1.470
��+1.401
Neg logit contributions
orio-1.972
acular-1.846
enegger-1.826
orious-1.782
 gears-1.725
Token Clinton
Token ID2605
Feature activation+5.34e-01

Pos logit contributions
 derog+0.951
 curs+0.921
beit+0.872
 perpet+0.858
��+0.828
Neg logit contributions
orio-0.826
acular-0.764
enegger-0.755
orious-0.734
 gears-0.707
Token doesn
Token ID1595
Feature activation+3.30e-01

Pos logit contributions
orio+1.226
acular+1.154
enegger+1.135
orious+1.116
 gears+1.093
Neg logit contributions
 derog-0.949
 curs-0.924
beit-0.860
 perpet-0.827
��-0.817
Token
Token ID447
Feature activation-3.85e-01

Pos logit contributions
orio+1.912
acular+1.812
enegger+1.795
orious+1.760
 gears+1.709
Neg logit contributions
 derog-0.962
 curs-0.916
beit-0.827
 perpet-0.811
��-0.760
Token
Token ID247
Feature activation-8.77e-02

Pos logit contributions
 derog+0.969
 curs+0.943
beit+0.844
 perpet+0.825
��+0.783
Neg logit contributions
orio-2.348
enegger-2.270
acular-2.236
orious-2.158
 gears-2.114
Tokent
Token ID83
Feature activation+9.37e-01

Pos logit contributions
 derog+0.476
 curs+0.464
beit+0.440
 perpet+0.436
��+0.423
Neg logit contributions
orio-0.288
acular-0.262
enegger-0.257
orious-0.248
 gears-0.236
Token support
Token ID1104
Feature activation+2.59e-01

Pos logit contributions
orio+4.136
acular+4.045
orious+3.938
enegger+3.906
 gears+3.820
Neg logit contributions
 derog-3.550
 curs-3.474
beit-3.341
��-3.337
 perpet-3.058
Token Clinton
Token ID2605
Feature activation+1.61e+00

Pos logit contributions
orio+1.162
acular+1.077
enegger+1.053
orious+1.045
 gears+1.008
Neg logit contributions
 derog-1.081
 curs-1.039
beit-0.988
 perpet-0.947
��-0.935
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
orio+6.748
acular+6.469
enegger+6.457
orious+6.279
 gears+6.115
Neg logit contributions
 derog-6.185
 curs-6.017
��-5.795
beit-5.669
 perpet-5.263
Token
Token ID198
Feature activation-2.00e-01

Pos logit contributions
 derog+0.051
 curs+0.049
beit+0.045
 perpet+0.044
��+0.042
Neg logit contributions
orio-0.070
acular-0.066
enegger-0.065
orious-0.064
 gears-0.061
Token
Token ID198
Feature activation-3.59e-01

Pos logit contributions
 derog+0.627
 curs+0.617
 perpet+0.573
beit+0.569
+0.540
Neg logit contributions
orio-1.091
enegger-1.044
acular-1.017
orious-0.991
 gears-0.979
TokenBack
Token ID7282
Feature activation+3.39e-01

Pos logit contributions
 derog+1.382
 curs+1.350
beit+1.262
 perpet+1.248
+1.179
Neg logit contributions
orio-1.715
enegger-1.607
acular-1.604
orious-1.544
 gears-1.512
Token during
Token ID1141
Feature activation-3.22e-01

Pos logit contributions
orio+1.627
acular+1.540
enegger+1.522
orious+1.504
 gears+1.455
Neg logit contributions
 derog-1.306
 curs-1.257
beit-1.171
 perpet-1.136
��-1.111
Token is
Token ID318
Feature activation+9.10e-01

Pos logit contributions
orio+2.725
acular+2.550
enegger+2.539
orious+2.467
 gears+2.430
Neg logit contributions
 derog-2.286
 curs-2.212
beit-2.071
 perpet-2.001
��-1.986
Token retiring
Token ID29040
Feature activation+1.17e+00

Pos logit contributions
orio+4.084
enegger+3.832
acular+3.779
orious+3.751
 gears+3.682
Neg logit contributions
 derog-3.618
 curs-3.496
beit-3.314
��-3.245
 perpet-3.124
Token when
Token ID618
Feature activation+5.06e-01

Pos logit contributions
orio+5.355
acular+4.967
enegger+4.956
orious+4.865
 gears+4.807
Neg logit contributions
 derog-4.530
 curs-4.351
beit-4.121
��-4.062
 perpet-3.954
Token her
Token ID607
Feature activation-5.63e-02

Pos logit contributions
orio+2.436
acular+2.292
enegger+2.257
orious+2.226
 gears+2.160
Neg logit contributions
 derog-1.937
 curs-1.848
beit-1.709
��-1.649
 perpet-1.644
Token term
Token ID3381
Feature activation+3.47e-01

Pos logit contributions
 derog+0.214
 curs+0.205
beit+0.192
 perpet+0.188
��+0.181
Neg logit contributions
orio-0.277
acular-0.259
enegger-0.257
orious-0.252
 gears-0.244
Token ends
Token ID5645
Feature activation+1.61e+00

Pos logit contributions
orio+1.712
acular+1.608
enegger+1.594
orious+1.554
 gears+1.531
Neg logit contributions
 derog-1.294
 curs-1.238
beit-1.158
 perpet-1.117
��-1.105
Token this
Token ID428
Feature activation-2.07e-01

Pos logit contributions
orio+6.615
acular+6.105
orious+6.017
enegger+6.004
 gears+5.953
Neg logit contributions
 derog-6.596
 curs-6.376
��-6.213
beit-6.083
 perpet-5.688
Token year
Token ID614
Feature activation+1.05e+00

Pos logit contributions
 derog+0.748
 curs+0.720
beit+0.665
 perpet+0.658
��+0.617
Neg logit contributions
orio-1.051
acular-0.987
enegger-0.980
orious-0.954
 gears-0.925
Token.
Token ID13
Feature activation+1.89e-01

Pos logit contributions
orio+4.373
acular+4.061
enegger+4.006
orious+3.897
 gears+3.837
Neg logit contributions
 derog-4.581
 curs-4.457
��-4.148
beit-4.078
 perpet-4.014
Token
Token ID564
Feature activation+5.75e-02

Pos logit contributions
orio+0.918
acular+0.866
enegger+0.856
orious+0.834
 gears+0.801
Neg logit contributions
 derog-0.729
 curs-0.701
beit-0.647
 perpet-0.638
��-0.619
Token
Token ID250
Feature activation-1.16e-01

Pos logit contributions
orio+0.266
acular+0.248
enegger+0.245
orious+0.242
 gears+0.234
Neg logit contributions
 derog-0.234
 curs-0.227
beit-0.209
 perpet-0.209
-0.191
Token to
Token ID284
Feature activation-2.50e-01

Pos logit contributions
 derog+2.523
 curs+2.424
beit+2.233
 perpet+2.214
��+2.061
Neg logit contributions
orio-3.765
acular-3.535
enegger-3.519
orious-3.424
 gears-3.320
Token the
Token ID262
Feature activation+3.32e-01

Pos logit contributions
 derog+0.948
 curs+0.907
beit+0.840
 perpet+0.824
��+0.783
Neg logit contributions
orio-1.229
acular-1.159
enegger-1.146
orious-1.120
 gears-1.086
Token footwear
Token ID43463
Feature activation+4.63e-01

Pos logit contributions
orio+1.600
acular+1.502
enegger+1.496
orious+1.455
 gears+1.416
Neg logit contributions
 derog-1.275
 curs-1.222
beit-1.140
 perpet-1.107
��-1.068
Token pur
Token ID1308
Feature activation+4.93e-02

Pos logit contributions
orio+2.062
acular+1.944
enegger+1.919
orious+1.903
 gears+1.835
Neg logit contributions
 derog-1.915
 curs-1.853
beit-1.758
 perpet-1.667
��-1.631
Tokenvey
Token ID3304
Feature activation-2.86e-01

Pos logit contributions
orio+0.203
acular+0.189
enegger+0.183
orious+0.180
 gears+0.172
Neg logit contributions
 derog-0.230
 curs-0.222
beit-0.209
 perpet-0.205
��-0.200
Tokenor
Token ID273
Feature activation-8.99e-02

Pos logit contributions
 derog+1.787
 curs+1.747
beit+1.673
 perpet+1.665
��+1.606
Neg logit contributions
orio-0.694
acular-0.608
enegger-0.598
orious-0.560
 gears-0.525
Token;
Token ID26
Feature activation+3.68e-01

Pos logit contributions
 derog+0.320
 curs+0.305
beit+0.284
 perpet+0.276
��+0.265
Neg logit contributions
orio-0.462
acular-0.437
enegger-0.428
orious-0.425
 gears-0.411
Token 40
Token ID2319
Feature activation-1.97e-01

Pos logit contributions
orio+1.830
acular+1.728
enegger+1.706
orious+1.671
 gears+1.635
Neg logit contributions
 derog-1.364
 curs-1.282
beit-1.193
 perpet-1.158
��-1.128
Token Wall
Token ID5007
Feature activation+2.95e-01

Pos logit contributions
 derog+0.731
 curs+0.693
beit+0.648
 perpet+0.631
��+0.599
Neg logit contributions
orio-0.998
acular-0.938
enegger-0.924
orious-0.913
 gears-0.885
Token Street
Token ID3530
Feature activation-3.67e-01

Pos logit contributions
orio+1.126
acular+1.062
enegger+1.001
orious+0.997
 gears+0.944
Neg logit contributions
 derog-1.441
 curs-1.384
beit-1.322
 perpet-1.290
��-1.251
Token,
Token ID11
Feature activation-7.29e-01

Pos logit contributions
 derog+1.440
 curs+1.392
beit+1.299
 perpet+1.269
��+1.219
Neg logit contributions
orio-1.756
acular-1.651
enegger-1.627
orious-1.587
 gears-1.543
TokenThe
Token ID464
Feature activation+6.50e-01

Pos logit contributions
 derog+2.677
 curs+2.595
beit+2.429
 perpet+2.399
��+2.277
Neg logit contributions
orio-2.957
acular-2.757
enegger-2.738
orious-2.654
 gears-2.572
Token messages
Token ID6218
Feature activation+1.84e-01

Pos logit contributions
orio+3.106
acular+2.891
enegger+2.839
orious+2.828
 gears+2.774
Neg logit contributions
 derog-2.478
 curs-2.355
beit-2.269
 perpet-2.155
��-2.129
Token are
Token ID389
Feature activation-7.27e-02

Pos logit contributions
orio+0.915
acular+0.861
enegger+0.848
orious+0.835
 gears+0.814
Neg logit contributions
 derog-0.679
 curs-0.651
beit-0.612
 perpet-0.587
��-0.582
Token written
Token ID3194
Feature activation-1.72e-01

Pos logit contributions
 derog+0.299
 curs+0.287
beit+0.271
 perpet+0.264
��+0.257
Neg logit contributions
orio-0.331
acular-0.311
enegger-0.307
orious-0.301
 gears-0.292
Token,
Token ID11
Feature activation-7.45e-01

Pos logit contributions
 derog+0.613
 curs+0.588
beit+0.550
 perpet+0.537
��+0.522
Neg logit contributions
orio-0.872
acular-0.827
enegger-0.813
orious-0.799
 gears-0.778
Token we
Token ID356
Feature activation+6.11e-02

Pos logit contributions
 derog+2.724
 curs+2.644
beit+2.428
 perpet+2.424
��+2.221
Neg logit contributions
orio-3.745
acular-3.502
enegger-3.490
orious-3.392
 gears-3.270
Token hope
Token ID2911
Feature activation-5.64e-01

Pos logit contributions
orio+0.317
acular+0.299
enegger+0.295
orious+0.290
 gears+0.281
Neg logit contributions
 derog-0.214
 curs-0.205
beit-0.190
 perpet-0.185
��-0.178
Token,
Token ID11
Feature activation-1.47e-01

Pos logit contributions
 derog+2.235
 curs+2.157
beit+2.009
 perpet+1.985
��+1.881
Neg logit contributions
orio-2.677
acular-2.504
enegger-2.482
orious-2.417
 gears-2.337
Token with
Token ID351
Feature activation-2.31e-01

Pos logit contributions
 derog+0.499
 curs+0.478
beit+0.443
 perpet+0.432
��+0.414
Neg logit contributions
orio-0.776
acular-0.736
enegger-0.726
orious-0.714
 gears-0.693
Token some
Token ID617
Feature activation+8.62e-02

Pos logit contributions
 derog+0.946
 curs+0.912
beit+0.855
 perpet+0.843
��+0.805
Neg logit contributions
orio-1.065
acular-0.995
enegger-0.984
orious-0.960
 gears-0.929
Token sense
Token ID2565
Feature activation-1.36e-01

Pos logit contributions
orio+0.390
acular+0.367
enegger+0.358
orious+0.353
 gears+0.346
Neg logit contributions
 derog-0.353
 curs-0.337
beit-0.327
 perpet-0.315
��-0.309
Token up
Token ID510
Feature activation-9.03e-01

Pos logit contributions
 derog+1.727
 curs+1.670
beit+1.559
 perpet+1.534
��+1.481
Neg logit contributions
orio-1.914
acular-1.794
enegger-1.769
orious-1.733
 gears-1.677
Token until
Token ID1566
Feature activation-6.73e-01

Pos logit contributions
 derog+3.223
 curs+3.085
beit+2.866
 perpet+2.852
��+2.618
Neg logit contributions
orio-4.631
acular-4.336
enegger-4.310
orious-4.184
 gears-4.063
Token after
Token ID706
Feature activation-4.79e-01

Pos logit contributions
 derog+2.256
 curs+2.165
beit+1.986
 perpet+1.956
��+1.838
Neg logit contributions
orio-3.606
acular-3.401
enegger-3.374
orious-3.299
 gears-3.203
Token the
Token ID262
Feature activation-1.34e-01

Pos logit contributions
 derog+1.702
 curs+1.639
beit+1.506
 perpet+1.480
��+1.411
Neg logit contributions
orio-2.466
acular-2.326
enegger-2.309
orious-2.259
 gears-2.187
Token election
Token ID3071
Feature activation+1.78e+00

Pos logit contributions
 derog+0.462
 curs+0.442
beit+0.412
 perpet+0.399
��+0.385
Neg logit contributions
orio-0.698
acular-0.657
enegger-0.652
orious-0.641
 gears-0.625
Token,
Token ID11
Feature activation-1.02e-01

Pos logit contributions
orio+7.457
acular+7.172
orious+6.944
enegger+6.921
 gears+6.733
Neg logit contributions
 derog-6.776
 curs-6.612
beit-6.206
��-6.174
 perpet-5.845
Token and
Token ID290
Feature activation+1.69e-01

Pos logit contributions
 derog+0.381
 curs+0.367
beit+0.340
 perpet+0.334
��+0.321
Neg logit contributions
orio-0.501
acular-0.471
enegger-0.467
orious-0.456
 gears-0.442
Token the
Token ID262
Feature activation+1.26e-01

Pos logit contributions
orio+0.870
acular+0.819
enegger+0.815
orious+0.796
 gears+0.776
Neg logit contributions
 derog-0.590
 curs-0.569
beit-0.524
 perpet-0.510
��-0.500
Token Iranians
Token ID34608
Feature activation-2.12e-01

Pos logit contributions
orio+0.612
acular+0.575
enegger+0.570
orious+0.558
 gears+0.545
Neg logit contributions
 derog-0.478
 curs-0.460
beit-0.432
 perpet-0.420
��-0.407
Token had
Token ID550
Feature activation-4.53e-01

Pos logit contributions
 derog+0.757
 curs+0.731
beit+0.676
 perpet+0.661
��+0.633
Neg logit contributions
orio-1.084
acular-1.019
enegger-1.013
orious-0.989
 gears-0.961
Token a
Token ID257
Feature activation-9.76e-03

Pos logit contributions
 derog+1.673
 curs+1.612
beit+1.491
 perpet+1.474
��+1.387
Neg logit contributions
orio-2.273
acular-2.133
enegger-2.116
orious-2.063
 gears-1.998
TokenHe
Token ID1544
Feature activation-3.22e-02

Pos logit contributions
 derog+0.935
 curs+0.901
beit+0.837
 perpet+0.827
��+0.782
Neg logit contributions
orio-1.182
acular-1.108
enegger-1.097
orious-1.070
 gears-1.035
Token has
Token ID468
Feature activation-3.08e-01

Pos logit contributions
 derog+0.122
 curs+0.118
beit+0.109
 perpet+0.108
��+0.102
Neg logit contributions
orio-0.159
acular-0.149
enegger-0.147
orious-0.144
 gears-0.139
Token an
Token ID281
Feature activation+3.24e-01

Pos logit contributions
 derog+1.136
 curs+1.099
beit+1.010
 perpet+1.007
��+0.929
Neg logit contributions
orio-1.547
acular-1.449
enegger-1.437
orious-1.404
 gears-1.352
Token 8
Token ID807
Feature activation+7.43e-01

Pos logit contributions
orio+1.509
acular+1.420
enegger+1.385
orious+1.357
 gears+1.305
Neg logit contributions
 derog-1.313
 curs-1.257
beit-1.195
 perpet-1.160
��-1.148
Token-
Token ID12
Feature activation+7.62e-01

Pos logit contributions
orio+3.631
acular+3.425
orious+3.312
enegger+3.294
 gears+3.253
Neg logit contributions
 derog-2.755
 curs-2.561
beit-2.437
 perpet-2.348
��-2.293
Tokenby
Token ID1525
Feature activation+1.16e-01

Pos logit contributions
orio+3.211
enegger+2.930
acular+2.919
orious+2.804
 gears+2.734
Neg logit contributions
 derog-3.399
 curs-3.246
 perpet-3.010
beit-3.009
��-2.894
Token-
Token ID12
Feature activation+3.17e-01

Pos logit contributions
orio+0.645
acular+0.609
enegger+0.603
orious+0.592
 gears+0.571
Neg logit contributions
 derog-0.368
 curs-0.351
beit-0.320
 perpet-0.314
��-0.301
Token12
Token ID1065
Feature activation+4.12e-01

Pos logit contributions
orio+1.677
acular+1.573
enegger+1.546
orious+1.533
rain+1.463
Neg logit contributions
 derog-1.101
 curs-1.046
beit-0.950
 perpet-0.944
��-0.915
Token copy
Token ID4866
Feature activation-1.51e+00

Pos logit contributions
orio+2.156
acular+2.038
enegger+2.014
orious+1.976
 gears+1.923
Neg logit contributions
 derog-1.415
 curs-1.308
beit-1.255
 perpet-1.208
��-1.164
Token of
Token ID286
Feature activation+1.26e-01

Pos logit contributions
 derog+3.739
 curs+3.564
beit+3.119
 perpet+3.105
��+2.747
Neg logit contributions
orio-9.348
acular-8.885
enegger-8.846
orious-8.651
 gears-8.438
Token that
Token ID326
Feature activation-1.93e-01

Pos logit contributions
orio+0.605
acular+0.561
enegger+0.555
orious+0.547
 gears+0.531
Neg logit contributions
 derog-0.494
 curs-0.467
beit-0.443
 perpet-0.432
��-0.417
Token third
Token ID2368
Feature activation-1.87e-01

Pos logit contributions
orio+1.674
acular+1.566
enegger+1.527
orious+1.523
 gears+1.482
Neg logit contributions
 derog-1.358
 curs-1.282
beit-1.233
 perpet-1.188
��-1.160
Token of
Token ID286
Feature activation+5.14e-01

Pos logit contributions
 derog+0.519
 curs+0.484
beit+0.445
 perpet+0.422
��+0.418
Neg logit contributions
orio-1.105
acular-1.055
enegger-1.037
orious-1.024
 gears-1.012
Token the
Token ID262
Feature activation+5.66e-01

Pos logit contributions
orio+2.265
acular+2.114
enegger+2.069
orious+2.034
 gears+2.012
Neg logit contributions
 derog-2.170
 curs-2.058
beit-1.955
 perpet-1.885
��-1.867
Token cap
Token ID1451
Feature activation-4.88e-03

Pos logit contributions
orio+2.534
acular+2.364
enegger+2.324
orious+2.277
 gears+2.257
Neg logit contributions
 derog-2.338
 curs-2.244
beit-2.137
 perpet-2.057
��-2.039
Tokenes
Token ID274
Feature activation+3.46e-01

Pos logit contributions
 derog+0.021
 curs+0.019
beit+0.018
 perpet+0.018
��+0.017
Neg logit contributions
orio-0.022
acular-0.021
orious-0.020
enegger-0.020
 gears-0.019
Token that
Token ID326
Feature activation+2.80e-02

Pos logit contributions
orio+1.695
acular+1.604
enegger+1.575
orious+1.554
 gears+1.503
Neg logit contributions
 derog-1.295
 curs-1.242
beit-1.160
 perpet-1.120
��-1.098
Token arrived
Token ID5284
Feature activation+9.83e-01

Pos logit contributions
orio+0.143
acular+0.135
enegger+0.133
orious+0.130
 gears+0.126
Neg logit contributions
 derog-0.101
 curs-0.097
beit-0.089
 perpet-0.088
��-0.084
Token to
Token ID284
Feature activation+3.48e-01

Pos logit contributions
orio+4.332
acular+4.142
orious+4.014
enegger+3.954
 gears+3.939
Neg logit contributions
 derog-3.863
 curs-3.739
beit-3.635
��-3.609
 perpet-3.366
Token fight
Token ID1907
Feature activation+5.40e-01

Pos logit contributions
orio+1.631
acular+1.542
enegger+1.502
orious+1.492
 gears+1.446
Neg logit contributions
 derog-1.360
 curs-1.314
beit-1.235
 perpet-1.190
��-1.168
Token him
Token ID683
Feature activation-4.21e-01

Pos logit contributions
orio+2.592
acular+2.430
enegger+2.368
orious+2.343
 gears+2.293
Neg logit contributions
 derog-2.082
 curs-1.978
beit-1.844
 perpet-1.798
��-1.760
Token.
Token ID13
Feature activation-8.85e-02

Pos logit contributions
 derog+1.669
 curs+1.612
beit+1.500
 perpet+1.486
��+1.400
Neg logit contributions
orio-1.994
acular-1.864
enegger-1.850
orious-1.799
 gears-1.738
TokenC
Token ID34
Feature activation+5.29e-01

Pos logit contributions
 derog+0.009
 curs+0.009
beit+0.008
 perpet+0.008
��+0.008
Neg logit contributions
orio-0.010
acular-0.009
enegger-0.009
orious-0.009
 gears-0.009
Tokenomet
Token ID908
Feature activation+8.60e-01

Pos logit contributions
orio+2.338
acular+2.198
enegger+2.120
orious+2.115
reetings+2.011
Neg logit contributions
 derog-2.262
 curs-2.176
beit-2.013
 perpet-2.011
��-1.930
Token Song
Token ID10940
Feature activation+2.16e-01

Pos logit contributions
orio+3.866
acular+3.672
orious+3.548
enegger+3.524
 gears+3.389
Neg logit contributions
 derog-3.433
 curs-3.352
beit-3.085
 perpet-3.026
��-2.951
Token)
Token ID8
Feature activation+3.51e-01

Pos logit contributions
orio+1.008
acular+0.953
enegger+0.916
orious+0.906
 gears+0.873
Neg logit contributions
 derog-0.868
 curs-0.848
beit-0.769
 perpet-0.763
��-0.742
Token for
Token ID329
Feature activation-7.00e-01

Pos logit contributions
orio+1.823
acular+1.727
enegger+1.692
orious+1.676
 gears+1.618
Neg logit contributions
 derog-1.194
 curs-1.165
beit-1.068
 perpet-1.027
��-1.008
Token the
Token ID262
Feature activation-2.08e-01

Pos logit contributions
 derog+2.581
 curs+2.484
beit+2.300
 perpet+2.276
��+2.141
Neg logit contributions
orio-3.514
acular-3.298
enegger-3.273
orious-3.189
 gears-3.089
Token film
Token ID2646
Feature activation-8.47e-01

Pos logit contributions
 derog+0.773
 curs+0.744
beit+0.691
 perpet+0.678
��+0.644
Neg logit contributions
orio-1.034
acular-0.972
enegger-0.962
orious-0.940
 gears-0.913
Token M
Token ID337
Feature activation-1.50e-02

Pos logit contributions
 derog+2.983
 curs+2.870
beit+2.658
 perpet+2.625
��+2.459
Neg logit contributions
orio-4.374
acular-4.105
enegger-4.079
orious-3.972
 gears-3.846
Tokenoom
Token ID4207
Feature activation+2.79e-01

Pos logit contributions
 derog+0.058
 curs+0.057
beit+0.052
 perpet+0.052
��+0.049
Neg logit contributions
orio-0.073
acular-0.068
enegger-0.067
orious-0.066
 gears-0.063
Tokenins
Token ID1040
Feature activation+8.62e-02

Pos logit contributions
orio+0.785
acular+0.704
enegger+0.688
orious+0.671
rain+0.609
Neg logit contributions
 derog-1.655
 curs-1.630
 perpet-1.538
beit-1.522
��-1.477
Token and
Token ID290
Feature activation-2.69e-01

Pos logit contributions
orio+0.425
acular+0.402
enegger+0.393
orious+0.389
 gears+0.375
Neg logit contributions
 derog-0.322
 curs-0.311
beit-0.286
 perpet-0.281
��-0.269
Token
Token ID198
Feature activation-4.55e-01

Pos logit contributions
 derog+0.405
 curs+0.397
 perpet+0.367
beit+0.366
+0.342
Neg logit contributions
orio-0.664
enegger-0.629
acular-0.619
orious-0.602
 gears-0.591
TokenIn
Token ID818
Feature activation-1.53e-01

Pos logit contributions
 derog+1.746
 curs+1.694
beit+1.598
 perpet+1.569
+1.485
Neg logit contributions
orio-2.187
enegger-2.048
acular-2.047
orious-1.968
 gears-1.927
Token the
Token ID262
Feature activation-6.37e-01

Pos logit contributions
 derog+0.558
 curs+0.537
beit+0.499
 perpet+0.488
��+0.467
Neg logit contributions
orio-0.777
acular-0.727
enegger-0.719
orious-0.705
 gears-0.685
Token end
Token ID886
Feature activation+1.24e-01

Pos logit contributions
 derog+2.262
 curs+2.174
 perpet+1.997
beit+1.976
��+1.816
Neg logit contributions
orio-3.291
acular-3.089
enegger-3.075
orious-2.980
reetings-2.864
Token this
Token ID428
Feature activation-8.74e-01

Pos logit contributions
orio+0.596
acular+0.559
enegger+0.552
orious+0.543
 gears+0.534
Neg logit contributions
 derog-0.473
 curs-0.457
beit-0.423
 perpet-0.414
��-0.408
Token would
Token ID561
Feature activation-1.21e+00

Pos logit contributions
 derog+3.421
 curs+3.298
 perpet+3.059
beit+3.026
+2.793
Neg logit contributions
orio-4.218
enegger-3.926
acular-3.913
orious-3.771
reetings-3.645
Token be
Token ID307
Feature activation-6.93e-01

Pos logit contributions
 derog+4.292
 curs+4.079
 perpet+3.841
beit+3.689
+3.388
Neg logit contributions
orio-6.294
enegger-5.829
acular-5.740
orious-5.633
reetings-5.427
Token the
Token ID262
Feature activation+4.50e-03

Pos logit contributions
 derog+2.668
 curs+2.576
beit+2.380
 perpet+2.376
��+2.213
Neg logit contributions
orio-3.368
acular-3.145
enegger-3.138
orious-3.036
 gears-2.934
Token start
Token ID923
Feature activation-2.17e-01

Pos logit contributions
orio+0.021
acular+0.019
enegger+0.019
orious+0.019
 gears+0.018
Neg logit contributions
 derog-0.018
 curs-0.018
beit-0.017
 perpet-0.016
��-0.016
Token of
Token ID286
Feature activation+1.53e-01

Pos logit contributions
 derog+0.615
 curs+0.582
beit+0.522
 perpet+0.500
��+0.479
Neg logit contributions
orio-1.283
acular-1.218
enegger-1.190
orious-1.184
 gears-1.176
Token a
Token ID257
Feature activation+2.74e-01

Pos logit contributions
orio+0.714
acular+0.669
enegger+0.650
orious+0.645
 gears+0.635
Neg logit contributions
 derog-0.615
 curs-0.597
beit-0.562
 perpet-0.536
��-0.524
Token10
Token ID940
Feature activation-5.88e-01

Pos logit contributions
 derog+1.181
 curs+1.152
beit+1.088
 perpet+1.080
+1.027
Neg logit contributions
orio-2.210
enegger-2.136
acular-2.079
orious-2.017
 gears-2.011
Token:
Token ID25
Feature activation+5.50e-02

Pos logit contributions
 derog+1.716
 curs+1.696
 perpet+1.601
beit+1.568
+1.491
Neg logit contributions
orio-3.296
enegger-3.156
acular-3.066
orious-3.002
ierrez-2.977
Token47
Token ID2857
Feature activation+4.94e-01

Pos logit contributions
orio+0.246
acular+0.227
enegger+0.226
orious+0.219
 gears+0.213
Neg logit contributions
 derog-0.233
 curs-0.226
beit-0.212
 perpet-0.210
��-0.198
Token]
Token ID60
Feature activation-2.85e-01

Pos logit contributions
orio+2.290
acular+2.144
enegger+2.117
orious+2.066
 gears+1.989
Neg logit contributions
 derog-2.015
 curs-1.944
beit-1.809
 perpet-1.785
��-1.714
Token <
Token ID1279
Feature activation-2.91e-01

Pos logit contributions
 derog+1.254
 curs+1.216
beit+1.148
 perpet+1.130
��+1.090
Neg logit contributions
orio-1.229
acular-1.149
enegger-1.143
orious-1.092
 gears-1.068
Tokenmet
Token ID4164
Feature activation-3.14e-01

Pos logit contributions
 derog+1.299
 curs+1.259
beit+1.182
 perpet+1.170
��+1.116
Neg logit contributions
orio-1.232
acular-1.143
enegger-1.132
orious-1.098
 gears-1.056
Tokenros
Token ID4951
Feature activation-3.27e-01

Pos logit contributions
 derog+1.497
 curs+1.445
 perpet+1.352
beit+1.350
��+1.298
Neg logit contributions
orio-1.288
acular-1.187
enegger-1.154
orious-1.142
 gears-1.073
Tokenxual
Token ID5541
Feature activation+4.87e-03

Pos logit contributions
 derog+1.351
 curs+1.348
beit+1.306
 perpet+1.265
+1.232
Neg logit contributions
orio-1.403
enegger-1.300
acular-1.274
 gears-1.244
OPLE-1.228
Tokenth
Token ID400
Feature activation+7.65e-01

Pos logit contributions
orio+0.024
enegger+0.022
acular+0.022
orious+0.021
 gears+0.021
Neg logit contributions
 derog-0.019
 curs-0.018
beit-0.017
 perpet-0.017
-0.016
Tokenug
Token ID1018
Feature activation+9.79e-01

Pos logit contributions
orio+3.538
acular+3.305
enegger+3.244
orious+3.194
 gears+3.053
Neg logit contributions
 derog-3.131
 curs-3.031
beit-2.811
 perpet-2.788
��-2.659
Token>
Token ID29
Feature activation+6.11e-01

Pos logit contributions
orio+4.317
acular+4.059
enegger+3.946
orious+3.898
 gears+3.691
Neg logit contributions
 derog-4.223
 curs-4.041
beit-3.731
 perpet-3.678
��-3.628
Token of
Token ID286
Feature activation+1.25e-01

Pos logit contributions
orio+0.860
acular+0.827
enegger+0.806
orious+0.804
 gears+0.795
Neg logit contributions
 derog-0.502
 curs-0.482
beit-0.450
��-0.411
 perpet-0.408
Token truly
Token ID4988
Feature activation-1.38e-01

Pos logit contributions
orio+0.578
acular+0.540
enegger+0.530
orious+0.523
 gears+0.511
Neg logit contributions
 derog-0.504
 curs-0.484
beit-0.455
 perpet-0.441
��-0.434
Token believing
Token ID14773
Feature activation+8.20e-03

Pos logit contributions
 derog+0.584
 curs+0.565
beit+0.529
 perpet+0.521
��+0.499
Neg logit contributions
orio-0.612
acular-0.571
enegger-0.563
orious-0.550
 gears-0.532
Token in
Token ID287
Feature activation-3.96e-01

Pos logit contributions
orio+0.038
acular+0.036
enegger+0.035
orious+0.035
 gears+0.033
Neg logit contributions
 derog-0.033
 curs-0.032
beit-0.030
 perpet-0.029
��-0.028
Token your
Token ID534
Feature activation-8.13e-01

Pos logit contributions
 derog+1.714
 curs+1.664
beit+1.558
 perpet+1.548
��+1.463
Neg logit contributions
orio-1.728
acular-1.604
enegger-1.596
orious-1.542
 gears-1.480
Token own
Token ID898
Feature activation-6.02e-01

Pos logit contributions
 derog+3.301
 curs+3.200
 perpet+2.981
beit+2.972
��+2.757
Neg logit contributions
orio-3.763
acular-3.495
enegger-3.489
orious-3.364
reetings-3.232
Token ability
Token ID2694
Feature activation+7.13e-02

Pos logit contributions
 derog+2.495
 curs+2.418
beit+2.255
 perpet+2.247
��+2.101
Neg logit contributions
orio-2.741
acular-2.549
enegger-2.543
orious-2.460
 gears-2.349
Token is
Token ID318
Feature activation+4.75e-01

Pos logit contributions
orio+0.352
acular+0.332
enegger+0.327
orious+0.320
 gears+0.312
Neg logit contributions
 derog-0.267
 curs-0.257
beit-0.239
 perpet-0.233
��-0.224
Token substantial
Token ID8904
Feature activation+3.04e-02

Pos logit contributions
orio+2.069
acular+1.953
enegger+1.897
orious+1.884
 gears+1.828
Neg logit contributions
 derog-2.018
 curs-1.927
beit-1.857
 perpet-1.750
��-1.734
Token,
Token ID11
Feature activation-6.30e-02

Pos logit contributions
orio+0.143
acular+0.135
enegger+0.133
orious+0.129
 gears+0.127
Neg logit contributions
 derog-0.121
 curs-0.117
beit-0.110
 perpet-0.106
��-0.103
Token and
Token ID290
Feature activation+3.41e-01

Pos logit contributions
 derog+0.220
 curs+0.210
beit+0.194
 perpet+0.190
��+0.180
Neg logit contributions
orio-0.328
acular-0.310
enegger-0.306
orious-0.300
 gears-0.291
Token to
Token ID284
Feature activation+5.49e-01

Pos logit contributions
 derog+1.584
 curs+1.509
beit+1.375
 perpet+1.341
��+1.268
Neg logit contributions
orio-3.112
acular-2.952
enegger-2.926
orious-2.867
 gears-2.796
Token haul
Token ID25647
Feature activation+1.16e+00

Pos logit contributions
orio+2.648
acular+2.533
enegger+2.450
orious+2.435
 gears+2.386
Neg logit contributions
 derog-2.010
 curs-1.929
beit-1.822
��-1.769
 perpet-1.740
Token up
Token ID510
Feature activation+1.11e-01

Pos logit contributions
orio+4.904
acular+4.696
 gears+4.675
enegger+4.524
orious+4.491
Neg logit contributions
 derog-4.686
 curs-4.395
��-4.213
beit-4.203
 perpet-4.108
Token any
Token ID597
Feature activation+4.73e-01

Pos logit contributions
orio+0.544
acular+0.514
enegger+0.505
orious+0.494
 gears+0.486
Neg logit contributions
 derog-0.419
 curs-0.400
beit-0.373
 perpet-0.367
��-0.354
Token spe
Token ID693
Feature activation-6.43e-01

Pos logit contributions
orio+2.190
acular+2.066
enegger+2.016
orious+1.988
 gears+1.972
Neg logit contributions
 derog-1.849
 curs-1.751
beit-1.684
 perpet-1.633
��-1.612
Tokenared
Token ID1144
Feature activation-2.82e-01

Pos logit contributions
 derog+3.042
 curs+2.950
beit+2.774
 perpet+2.753
��+2.639
Neg logit contributions
orio-2.571
acular-2.380
enegger-2.341
orious-2.276
 gears-2.174
Token m
Token ID285
Feature activation-4.41e-01

Pos logit contributions
 derog+1.168
 curs+1.127
beit+1.058
 perpet+1.043
��+0.997
Neg logit contributions
orio-1.283
acular-1.198
enegger-1.184
orious-1.154
 gears-1.119
Tokenogg
Token ID10332
Feature activation+1.48e+00

Pos logit contributions
 derog+2.017
 curs+1.951
beit+1.828
 perpet+1.817
��+1.740
Neg logit contributions
orio-1.832
acular-1.703
enegger-1.672
orious-1.632
 gears-1.559
Tokenies
Token ID444
Feature activation+2.90e-01

Pos logit contributions
orio+6.109
acular+5.929
enegger+5.702
orious+5.662
 gears+5.595
Neg logit contributions
 derog-6.144
 curs-5.740
beit-5.466
��-5.369
 perpet-5.257
Token.
Token ID13
Feature activation+6.55e-02

Pos logit contributions
orio+1.405
acular+1.329
enegger+1.303
orious+1.285
 gears+1.252
Neg logit contributions
 derog-1.095
 curs-1.049
beit-0.980
 perpet-0.952
��-0.946
Token Did
Token ID7731
Feature activation-2.53e-01

Pos logit contributions
orio+0.337
acular+0.317
enegger+0.314
orious+0.307
 gears+0.297
Neg logit contributions
 derog-0.235
 curs-0.224
beit-0.206
 perpet-0.204
��-0.194
Token-
Token ID12
Feature activation+6.42e-01

Pos logit contributions
orio+0.443
acular+0.417
enegger+0.417
orious+0.407
 gears+0.396
Neg logit contributions
 derog-0.273
 curs-0.267
beit-0.246
 perpet-0.235
��-0.233
TokenK
Token ID42
Feature activation-1.69e-01

Pos logit contributions
orio+3.139
enegger+2.968
acular+2.917
orious+2.862
 gears+2.718
Neg logit contributions
 derog-2.408
 curs-2.357
 perpet-2.125
beit-2.101
��-2.098
Tokenahn
Token ID15386
Feature activation+3.52e-01

Pos logit contributions
 derog+0.849
 curs+0.825
beit+0.803
 perpet+0.782
+0.764
Neg logit contributions
orio-0.598
acular-0.544
enegger-0.536
orious-0.516
 gears-0.512
Token.
Token ID13
Feature activation-6.28e-02

Pos logit contributions
orio+1.619
enegger+1.519
acular+1.508
orious+1.464
 gears+1.428
Neg logit contributions
 derog-1.414
 curs-1.376
beit-1.291
 perpet-1.256
��-1.234
Token<|endoftext|>
Token ID50256
Feature activation-7.54e-01

Pos logit contributions
 derog+0.265
 curs+0.253
 perpet+0.234
beit+0.233
��+0.226
Neg logit contributions
orio-0.287
enegger-0.269
acular-0.268
orious-0.258
 gears-0.247
TokenSAN
Token ID36753
Feature activation-2.33e+00

Pos logit contributions
 derog+3.090
 curs+3.005
beit+2.822
 perpet+2.781
��+2.637
Neg logit contributions
orio-3.432
acular-3.198
enegger-3.185
orious-3.075
 gears-2.996
Token FR
Token ID8782
Feature activation-1.40e+00

Pos logit contributions
 derog+6.747
 curs+6.576
 perpet+5.979
beit+5.828
+5.637
Neg logit contributions
orio-12.490
acular-11.901
enegger-11.732
orious-11.523
ierrez-11.102
TokenANC
Token ID20940
Feature activation-2.49e-01

Pos logit contributions
+2.131
 derog+2.087
 curs+2.004
 perpet+1.894
 ¶+1.783
Neg logit contributions
orio-9.214
enegger-9.100
acular-9.012
ierrez-8.816
rontal-8.784
TokenIS
Token ID1797
Feature activation-3.18e-01

Pos logit contributions
 derog+0.813
 curs+0.793
beit+0.732
 perpet+0.726
+0.682
Neg logit contributions
orio-1.339
acular-1.268
enegger-1.259
orious-1.226
 gears-1.196
TokenCO
Token ID8220
Feature activation-4.16e-01

Pos logit contributions
 derog+1.001
 curs+0.981
 perpet+0.904
beit+0.893
+0.841
Neg logit contributions
orio-1.752
acular-1.637
enegger-1.636
orious-1.606
 gears-1.579
Token -
Token ID532
Feature activation-6.10e-01

Pos logit contributions
 derog+1.528
 curs+1.469
beit+1.362
 perpet+1.338
��+1.270
Neg logit contributions
orio-2.101
acular-1.973
enegger-1.959
orious-1.912
 gears-1.854
Tokenanners
Token ID15672
Feature activation+4.99e-01

Pos logit contributions
orio+1.294
acular+1.229
enegger+1.186
orious+1.158
 gears+1.112
Neg logit contributions
 derog-1.453
 curs-1.392
beit-1.300
 perpet-1.293
��-1.249
Token -
Token ID532
Feature activation-1.43e+00

Pos logit contributions
orio+2.289
acular+2.179
enegger+2.145
orious+2.085
reetings+1.982
Neg logit contributions
 derog-2.018
 curs-1.920
beit-1.811
 perpet-1.778
��-1.715
Token favorite
Token ID4004
Feature activation-1.64e+00

Pos logit contributions
 curs+4.865
 derog+4.847
 perpet+4.538
beit+4.196
+3.960
Neg logit contributions
orio-7.224
enegger-7.050
OPLE-6.697
ierrez-6.533
acular-6.505
Token favorite
Token ID4004
Feature activation-1.75e+00

Pos logit contributions
 derog+5.308
 curs+5.292
 perpet+5.117
beit+4.569
 mi+4.396
Neg logit contributions
orio-8.265
enegger-8.123
OPLE-7.730
acular-7.600
ierrez-7.460
Token favorite
Token ID4004
Feature activation-2.04e+00

Pos logit contributions
 derog+5.585
 curs+5.581
 perpet+5.402
beit+4.799
 mi+4.640
Neg logit contributions
orio-8.813
enegger-8.704
OPLE-8.269
acular-8.130
rontal-7.993
Token favorite
Token ID4004
Feature activation-2.03e+00

Pos logit contributions
 curs+6.324
 derog+6.321
 perpet+6.115
beit+5.411
 mi+5.298
Neg logit contributions
orio-10.177
enegger-10.105
OPLE-9.618
acular-9.461
rontal-9.323
Token favorite
Token ID4004
Feature activation-1.90e+00

Pos logit contributions
 derog+7.609
 curs+7.448
 perpet+6.988
beit+6.790
��+6.468
Neg logit contributions
orio-9.374
enegger-8.874
acular-8.722
orious-8.474
OPLE-8.177
Token -
Token ID532
Feature activation-9.94e-01

Pos logit contributions
 derog+6.219
 curs+6.032
 perpet+5.574
beit+5.507
��+5.154
Neg logit contributions
orio-9.696
enegger-9.213
acular-9.136
orious-8.868
 gears-8.575
Token December
Token ID3426
Feature activation+3.91e-01

Pos logit contributions
 derog+2.908
 curs+2.894
 perpet+2.645
beit+2.540
+2.359
Neg logit contributions
orio-5.612
enegger-5.365
acular-5.273
orious-5.083
ierrez-5.022
Token 5
Token ID642
Feature activation-6.10e-01

Pos logit contributions
orio+2.167
acular+2.048
enegger+2.040
orious+1.982
 gears+1.930
Neg logit contributions
 derog-1.233
 curs-1.185
beit-1.082
 perpet-1.070
��-0.978
Token,
Token ID11
Feature activation-1.07e+00

Pos logit contributions
 derog+1.746
 curs+1.744
 perpet+1.643
beit+1.620
+1.528
Neg logit contributions
orio-3.414
enegger-3.277
acular-3.182
ierrez-3.134
yip-3.114
Token
Token ID134
Feature activation-4.50e-01

Pos logit contributions
 derog+5.374
 curs+5.185
beit+4.788
 perpet+4.750
+4.469
Neg logit contributions
orio-7.303
acular-6.849
enegger-6.820
orious-6.643
 gears-6.406
Token
Token ID119
Feature activation+2.99e-02

Pos logit contributions
 derog+1.367
 curs+1.334
beit+1.246
 perpet+1.225
��+1.192
Neg logit contributions
orio-2.473
enegger-2.382
acular-2.341
orious-2.255
 gears-2.245
Tokeni
Token ID72
Feature activation-5.61e-01

Pos logit contributions
orio+0.124
acular+0.115
enegger+0.113
orious+0.110
 gears+0.104
Neg logit contributions
 derog-0.138
 curs-0.134
beit-0.124
 perpet-0.124
��-0.119
Token n
Token ID299
Feature activation-7.46e-01

Pos logit contributions
 derog+1.894
 curs+1.816
beit+1.670
 perpet+1.645
��+1.543
Neg logit contributions
orio-2.991
acular-2.820
enegger-2.794
orious-2.730
 gears-2.651
Tokenō
Token ID13090
Feature activation-4.88e-01

Pos logit contributions
 derog+3.106
 curs+3.006
beit+2.837
 perpet+2.791
+2.647
Neg logit contributions
orio-3.310
enegger-3.096
acular-3.087
orious-2.983
 gears-2.900
Token ka
Token ID38387
Feature activation-1.81e+00

Pos logit contributions
 derog+1.915
 curs+1.849
beit+1.721
 perpet+1.700
��+1.609
Neg logit contributions
orio-2.331
acular-2.182
enegger-2.164
orious-2.106
 gears-2.037
Token p
Token ID279
Feature activation-7.60e-01

Pos logit contributions
 derog+6.093
 curs+5.914
 perpet+5.385
beit+5.304
+5.165
Neg logit contributions
orio-9.123
enegger-8.738
acular-8.553
orious-8.435
 gears-8.051
Tokenā
Token ID10235
Feature activation-7.32e-01

Pos logit contributions
 derog+3.246
 curs+3.145
beit+2.968
 perpet+2.932
+2.795
Neg logit contributions
orio-3.275
enegger-3.054
acular-3.045
orious-2.928
 gears-2.868
Tokenh
Token ID71
Feature activation-8.82e-01

Pos logit contributions
 derog+2.967
 curs+2.876
beit+2.691
 perpet+2.654
��+2.506
Neg logit contributions
orio-3.368
acular-3.150
enegger-3.143
orious-3.044
 gears-2.940
Tokenana
Token ID2271
Feature activation-1.79e+00

Pos logit contributions
 derog+3.361
 curs+3.261
beit+3.040
 perpet+3.006
+2.823
Neg logit contributions
orio-4.221
acular-3.956
enegger-3.950
orious-3.841
 gears-3.736
Token i
Token ID1312
Feature activation-1.63e+00

Pos logit contributions
 derog+5.724
 curs+5.515
 perpet+5.065
beit+4.948
+4.738
Neg logit contributions
orio-9.411
enegger-9.022
acular-8.858
orious-8.659
 gears-8.327
Token University
Token ID2059
Feature activation-2.13e-01

Pos logit contributions
 derog+0.425
 curs+0.408
beit+0.378
 perpet+0.374
��+0.357
Neg logit contributions
orio-0.540
acular-0.507
enegger-0.503
orious-0.488
 gears-0.474
Token of
Token ID286
Feature activation-1.09e-01

Pos logit contributions
 derog+0.775
 curs+0.736
beit+0.685
 perpet+0.674
��+0.632
Neg logit contributions
orio-1.089
acular-1.048
enegger-0.997
orious-0.991
 gears-0.960
Token Pennsylvania
Token ID9589
Feature activation+2.10e-01

Pos logit contributions
 derog+0.404
 curs+0.384
beit+0.358
 perpet+0.350
��+0.338
Neg logit contributions
orio-0.552
acular-0.517
enegger-0.511
orious-0.500
 gears-0.484
Token,
Token ID11
Feature activation-7.75e-02

Pos logit contributions
orio+1.001
acular+0.942
enegger+0.929
orious+0.901
 gears+0.880
Neg logit contributions
 derog-0.820
 curs-0.785
beit-0.736
 perpet-0.716
��-0.700
Token and
Token ID290
Feature activation+5.63e-01

Pos logit contributions
 derog+0.297
 curs+0.287
beit+0.267
 perpet+0.262
��+0.250
Neg logit contributions
orio-0.376
acular-0.352
enegger-0.349
orious-0.340
 gears-0.331
Token Milan
Token ID21574
Feature activation-1.90e+00

Pos logit contributions
orio+2.789
acular+2.617
enegger+2.559
orious+2.526
 gears+2.492
Neg logit contributions
 derog-2.058
 curs-1.928
beit-1.849
 perpet-1.773
��-1.768
Token Va
Token ID17668
Feature activation-3.77e-01

Pos logit contributions
 derog+6.234
 curs+6.159
beit+5.772
 perpet+5.570
+5.532
Neg logit contributions
orio-9.208
acular-8.783
enegger-8.742
orious-8.452
 gears-8.295
Tokenish
Token ID680
Feature activation-1.65e-01

Pos logit contributions
 derog+1.612
 curs+1.560
beit+1.459
 perpet+1.444
��+1.377
Neg logit contributions
orio-1.674
acular-1.559
enegger-1.543
orious-1.500
 gears-1.444
Tokennav
Token ID28341
Feature activation+1.58e-02

Pos logit contributions
 derog+0.759
 curs+0.731
beit+0.684
 perpet+0.682
��+0.661
Neg logit contributions
orio-0.684
acular-0.632
enegger-0.617
orious-0.607
 gears-0.577
Token,
Token ID11
Feature activation-5.60e-01

Pos logit contributions
orio+0.075
acular+0.070
enegger+0.069
orious+0.068
 gears+0.066
Neg logit contributions
 derog-0.063
 curs-0.060
beit-0.056
 perpet-0.056
��-0.053
Token a
Token ID257
Feature activation+5.58e-01

Pos logit contributions
 derog+2.183
 curs+2.107
beit+1.959
 perpet+1.936
��+1.831
Neg logit contributions
orio-2.690
acular-2.518
enegger-2.497
orious-2.431
 gears-2.352
Token
Token ID447
Feature activation+6.79e-01

Pos logit contributions
orio+3.065
acular+2.898
enegger+2.882
orious+2.818
 gears+2.783
Neg logit contributions
 derog-2.624
 curs-2.534
beit-2.371
��-2.299
 perpet-2.271
Token
Token ID247
Feature activation+3.38e-01

Pos logit contributions
orio+3.256
acular+3.029
enegger+2.995
orious+2.951
 gears+2.866
Neg logit contributions
 derog-2.628
 curs-2.535
beit-2.336
 perpet-2.314
-2.130
Tokens
Token ID82
Feature activation+1.88e-01

Pos logit contributions
orio+1.137
acular+1.039
enegger+1.027
orious+0.989
 gears+0.947
Neg logit contributions
 derog-1.796
 curs-1.746
beit-1.655
 perpet-1.633
��-1.590
Token ra
Token ID2179
Feature activation-7.24e-03

Pos logit contributions
orio+0.863
acular+0.804
enegger+0.798
orious+0.781
 gears+0.757
Neg logit contributions
 derog-0.774
 curs-0.740
beit-0.700
 perpet-0.683
��-0.660
Tokenison
Token ID1653
Feature activation-3.15e-01

Pos logit contributions
 derog+0.036
 curs+0.035
beit+0.033
 perpet+0.033
��+0.032
Neg logit contributions
orio-0.027
acular-0.025
enegger-0.024
orious-0.024
 gears-0.023
Token d
Token ID288
Feature activation-2.16e+00

Pos logit contributions
 derog+0.874
 curs+0.840
beit+0.760
 perpet+0.734
��+0.705
Neg logit contributions
orio-1.863
acular-1.773
enegger-1.739
orious-1.710
 gears-1.672
Token
Token ID447
Feature activation-5.62e-01

Pos logit contributions
 derog+4.340
 curs+4.125
+3.812
 perpet+3.792
beit+3.714
Neg logit contributions
orio-13.166
enegger-13.049
acular-12.628
yip-12.439
OPLE-12.241
Token
Token ID247
Feature activation-4.48e-01

Pos logit contributions
 derog+2.048
 curs+1.971
beit+1.826
 perpet+1.800
��+1.725
Neg logit contributions
orio-2.823
acular-2.656
enegger-2.654
orious-2.565
 gears-2.499
Tokenet
Token ID316
Feature activation+6.40e-01

Pos logit contributions
 derog+2.069
 curs+2.008
beit+1.891
 perpet+1.872
��+1.786
Neg logit contributions
orio-1.831
acular-1.693
enegger-1.678
orious-1.624
 gears-1.562
Tokenre
Token ID260
Feature activation-3.11e-01

Pos logit contributions
orio+3.537
acular+3.364
orious+3.244
enegger+3.235
rain+3.125
Neg logit contributions
 derog-2.013
 curs-1.932
beit-1.780
 perpet-1.722
��-1.698
Token is
Token ID318
Feature activation+2.31e-01

Pos logit contributions
 derog+1.156
 curs+1.114
beit+1.032
 perpet+1.019
��+0.962
Neg logit contributions
orio-1.550
acular-1.455
enegger-1.443
orious-1.406
 gears-1.362