TOP ACTIVATIONS
MAX = 5.706

Irvine , California . Hide Caption 10 of 15 Photos :
Women in politics . Hide Caption 7 of 15 Photos :
Irvine , California . Hide Caption 9 of 15 Photos :
Hills , California . Hide Caption 14 of 15 Photos :
, New Hampshire . Hide Caption 6 of 15 Photos :
in , Iowa . Hide Caption 5 of 15 Photos :
Pasadena , California . Hide Caption 12 of 15 Photos :
Pasadena , California . Hide Caption 11 of 15 Photos :
aga , California . Hide Caption 13 of 15 Photos :
Grove , California . Hide Caption 15 of 15
View all New York Times newsletters . For its
20 , 2015 . Hide Caption 8 of 15 Photos :
and stem . View Full Caption Adam Glenn C
community . ( Photo by REUTERS / John S omm ers
her . ( Photo by REUTERS / Car lo Alleg ri
by John Moore / Getty Images ) Jeff Sessions Sen .
View all New York Times newsletters .
issues . ( Photo by REUTERS / Gary Cameron / File
View all New York Times newsletters . The White
/ T NS via Getty Images ) Indiana Gov . Mike

MIN ACTIVATIONS
MIN = -5.553

ow support from former Ku Klux Klan leader David Duke .
Feed books , try Project Gutenberg ( www . g utenberg
comments . High lights of this new release ,
subway gr ates or on sto ops or in encamp ments
o Hal ep ā nih o m ai , n
announced an alliance with B ibli othe ca to directly sell
Hillary Clinton and were silenced . 1 : You have
called by Chief Minister Ar vind Kejriwal . "
invent ories , two product catalog s , and two payment
track of two sets of invent ories , two product catalog
Greenland s ice sheet to start losing more ice
ice from the central ice sheet ; but even in a
refused one . From Ed Koch on down , every mayor
the new search deal with Google aren 't yet clear ,
a loophole that could guarantee fossil fuel production past 20 45
on , then open the catalog like you would any ebook
In all , the ice sheet contains enough water to raise
and evolve to fill ecological nic hes left vacant after the
partnerships with search engines like Google , Yahoo , Duck D
don 't know who the Koch brothers are ."

INTERVAL 2.891 - 5.706
CONTAINS 0.182%

Ford , America 's truck leader , today introduced the
s punches had blown Brook s eye up
and stem . View Full Caption Adam Glenn C
the doctor of Catholic truth ought not only to teach the
income for his spouse , according to his disclosure statement .

INTERVAL 0.076 - 2.891
CONTAINS 44.587%

, though : Would Os we iler , as unprepared as
The Company of the Ring are nine in number : Fro
regulating the use of the agricultural lands . Such changes could
Turner , but it has inexpl icably been censored by the
of debris it takes to kill a turtle .

INTERVAL -2.738 - 0.076
CONTAINS 54.887%

to ethics commissioner , would be affected . Par
. <|endoftext|> C ort ic otrop in - re leasing factor
record with 18 , 355 career yards . C
're not ready to show you what we 've been working
Jade Helm 15 operation across the southwest continue to suggest that

INTERVAL -5.553 - -2.738
CONTAINS 0.344%

first it blew me away ", Ms Al br itton said
was as if at this moment they shared a single awareness
Title VI of the Civil Rights Act of 1964 . It
available . B ast ian said he found it
he fell down on his knees . For give
Token Irvine
Token ID37277
Feature activation+7.11e-01

Pos logit contributions
ipal+0.229
init+0.226
shift+0.216
actory+0.216
ounge+0.211
Neg logit contributions
 Dent-0.151
 Nadu-0.143
 Devi-0.139
 Equity-0.126
 Benefit-0.125
Token,
Token ID11
Feature activation-1.39e-01

Pos logit contributions
ipal+0.492
init+0.482
shift+0.453
actory+0.452
ounge+0.439
Neg logit contributions
 Dent-0.575
 Nadu-0.553
 Devi-0.541
 Equity-0.505
iaz-0.503
Token California
Token ID3442
Feature activation-7.21e-01

Pos logit contributions
 Dent+0.085
 Nadu+0.080
 Devi+0.078
 Equity+0.072
 Benefit+0.071
Neg logit contributions
ipal-0.124
init-0.122
shift-0.117
actory-0.117
ounge-0.114
Token.
Token ID13
Feature activation+4.53e-01

Pos logit contributions
 Dent+0.548
 Nadu+0.520
 Devi+0.511
 Benefit+0.476
 Equity+0.475
Neg logit contributions
ipal-0.530
init-0.523
shift-0.502
actory-0.500
ounge-0.486
Token Hide
Token ID10415
Feature activation+1.51e+00

Pos logit contributions
ipal+0.331
init+0.328
shift+0.309
actory+0.307
ounge+0.297
Neg logit contributions
 Dent-0.342
 Nadu-0.332
 Devi-0.321
iaz-0.302
 Equity-0.299
Token Caption
Token ID11260
Feature activation+5.65e+00

Pos logit contributions
ipal+0.563
init+0.560
shift+0.498
actory+0.472
photo+0.460
Neg logit contributions
 Dent-1.670
 Nadu-1.636
 Devi-1.612
iaz-1.543
merce-1.539
Token 10
Token ID838
Feature activation+1.44e+00

Pos logit contributions
init+2.171
ipal+2.093
shift+1.856
actory+1.778
photo+1.752
Neg logit contributions
 Dent-6.045
 Nadu-5.967
 Devi-5.770
iaz-5.752
merce-5.713
Token of
Token ID286
Feature activation+2.11e-01

Pos logit contributions
init+0.853
ipal+0.834
shift+0.795
actory+0.770
photo+0.750
Neg logit contributions
 Dent-1.315
 Nadu-1.287
 Devi-1.252
merce-1.184
 Equity-1.170
Token 15
Token ID1315
Feature activation+1.01e+00

Pos logit contributions
init+0.101
ipal+0.098
shift+0.091
actory+0.090
photo+0.084
Neg logit contributions
 Dent-0.215
 Nadu-0.211
 Devi-0.208
iaz-0.199
ouri-0.195
Token Photos
Token ID9434
Feature activation+4.36e+00

Pos logit contributions
init+0.478
ipal+0.469
shift+0.428
actory+0.424
photo+0.420
Neg logit contributions
 Dent-1.009
 Nadu-0.995
 Devi-0.969
merce-0.935
iaz-0.930
Token:
Token ID25
Feature activation+1.63e+00

Pos logit contributions
init+1.717
ipal+1.574
shift+1.550
actory+1.420
photo+1.419
Neg logit contributions
 Dent-4.730
 Nadu-4.695
 eleph-4.650
 Devi-4.605
merce-4.582
Token Women
Token ID6926
Feature activation-4.71e-01

Pos logit contributions
ipal+0.476
init+0.469
shift+0.451
actory+0.450
ounge+0.441
Neg logit contributions
 Dent-0.180
 Nadu-0.173
 Devi-0.159
iaz-0.140
 Equity-0.137
Token in
Token ID287
Feature activation-6.76e-03

Pos logit contributions
 Dent+0.375
 Nadu+0.362
 Devi+0.353
iaz+0.329
 Equity+0.327
Neg logit contributions
ipal-0.329
init-0.324
shift-0.306
actory-0.304
ounge-0.293
Token politics
Token ID4819
Feature activation+9.03e-01

Pos logit contributions
 Dent+0.005
 Nadu+0.005
 Devi+0.004
iaz+0.004
 Benefit+0.004
Neg logit contributions
ipal-0.005
init-0.005
shift-0.005
actory-0.005
ounge-0.005
Token.
Token ID13
Feature activation+4.34e-01

Pos logit contributions
ipal+0.600
init+0.596
shift+0.560
actory+0.552
ounge+0.533
Neg logit contributions
 Dent-0.741
 Nadu-0.719
 Devi-0.704
iaz-0.656
 Equity-0.653
Token Hide
Token ID10415
Feature activation+1.77e+00

Pos logit contributions
ipal+0.307
init+0.305
shift+0.287
actory+0.284
ounge+0.275
Neg logit contributions
 Dent-0.337
 Nadu-0.329
 Devi-0.318
iaz-0.299
 Equity-0.295
Token Caption
Token ID11260
Feature activation+5.63e+00

Pos logit contributions
ipal+0.651
init+0.646
shift+0.576
actory+0.551
photo+0.535
Neg logit contributions
 Dent-1.962
 Nadu-1.919
 Devi-1.894
iaz-1.806
merce-1.795
Token 7
Token ID767
Feature activation+6.46e-01

Pos logit contributions
ipal+1.852
init+1.837
actory+1.638
shift+1.622
photo+1.554
Neg logit contributions
 Dent-6.403
 Nadu-6.384
 Devi-6.103
merce-5.946
ouri-5.913
Token of
Token ID286
Feature activation+9.21e-02

Pos logit contributions
init+0.388
ipal+0.384
shift+0.363
actory+0.352
photo+0.343
Neg logit contributions
 Dent-0.581
 Nadu-0.570
 Devi-0.554
 Equity-0.517
merce-0.514
Token 15
Token ID1315
Feature activation+9.51e-01

Pos logit contributions
init+0.044
ipal+0.043
shift+0.040
actory+0.039
photo+0.036
Neg logit contributions
 Dent-0.093
 Nadu-0.092
 Devi-0.090
iaz-0.086
ouri-0.085
Token Photos
Token ID9434
Feature activation+4.51e+00

Pos logit contributions
init+0.453
ipal+0.445
shift+0.405
actory+0.403
photo+0.397
Neg logit contributions
 Dent-0.954
 Nadu-0.939
 Devi-0.915
merce-0.878
iaz-0.876
Token:
Token ID25
Feature activation+1.74e+00

Pos logit contributions
init+1.769
ipal+1.625
shift+1.603
photo+1.472
actory+1.462
Neg logit contributions
 Dent-4.887
 Nadu-4.852
 eleph-4.790
 Devi-4.756
merce-4.730
Token Irvine
Token ID37277
Feature activation+5.36e-01

Pos logit contributions
ipal+0.094
init+0.093
shift+0.089
actory+0.089
ounge+0.086
Neg logit contributions
 Dent-0.069
 Nadu-0.066
 Devi-0.064
iaz-0.058
 Equity-0.058
Token,
Token ID11
Feature activation-7.19e-02

Pos logit contributions
ipal+0.384
init+0.377
shift+0.358
actory+0.357
ounge+0.346
Neg logit contributions
 Dent-0.421
 Nadu-0.403
 Devi-0.394
 Equity-0.368
 Benefit-0.367
Token California
Token ID3442
Feature activation-7.75e-01

Pos logit contributions
 Dent+0.048
 Nadu+0.045
 Devi+0.044
iaz+0.041
 Equity+0.040
Neg logit contributions
ipal-0.060
init-0.060
shift-0.057
actory-0.056
itual-0.055
Token.
Token ID13
Feature activation+3.82e-01

Pos logit contributions
 Dent+0.584
 Nadu+0.554
 Devi+0.543
 Equity+0.507
 Benefit+0.507
Neg logit contributions
ipal-0.573
init-0.565
shift-0.544
actory-0.541
ounge-0.525
Token Hide
Token ID10415
Feature activation+1.52e+00

Pos logit contributions
ipal+0.278
init+0.276
shift+0.261
actory+0.259
ounge+0.250
Neg logit contributions
 Dent-0.290
 Nadu-0.281
 Devi-0.273
iaz-0.255
 Equity-0.252
Token Caption
Token ID11260
Feature activation+5.60e+00

Pos logit contributions
ipal+0.561
init+0.559
shift+0.496
actory+0.473
photo+0.460
Neg logit contributions
 Dent-1.680
 Nadu-1.644
 Devi-1.623
iaz-1.548
merce-1.544
Token 9
Token ID860
Feature activation+4.60e-01

Pos logit contributions
ipal+1.443
init+1.391
shift+1.210
actory+1.183
photo+1.047
Neg logit contributions
 Dent-6.754
 Nadu-6.740
 Devi-6.514
merce-6.317
iaz-6.282
Token of
Token ID286
Feature activation+2.25e-01

Pos logit contributions
init+0.278
ipal+0.272
shift+0.258
actory+0.251
photo+0.242
Neg logit contributions
 Dent-0.414
 Nadu-0.406
 Devi-0.394
merce-0.369
 Equity-0.368
Token 15
Token ID1315
Feature activation+1.08e+00

Pos logit contributions
init+0.108
ipal+0.104
shift+0.097
actory+0.096
photo+0.089
Neg logit contributions
 Dent-0.229
 Nadu-0.224
 Devi-0.221
iaz-0.211
ouri-0.208
Token Photos
Token ID9434
Feature activation+4.41e+00

Pos logit contributions
init+0.513
ipal+0.503
shift+0.459
actory+0.456
photo+0.451
Neg logit contributions
 Dent-1.085
 Nadu-1.069
 Devi-1.041
merce-1.004
iaz-0.999
Token:
Token ID25
Feature activation+1.63e+00

Pos logit contributions
init+1.736
ipal+1.591
shift+1.568
photo+1.440
actory+1.433
Neg logit contributions
 Dent-4.785
 Nadu-4.750
 eleph-4.700
 Devi-4.658
merce-4.631
Token Hills
Token ID14379
Feature activation+8.75e-01

Pos logit contributions
 Dent+1.449
 Nadu+1.378
 Devi+1.347
 Equity+1.259
 Benefit+1.254
Neg logit contributions
ipal-1.383
init-1.357
shift-1.292
actory-1.290
ounge-1.251
Token,
Token ID11
Feature activation-3.94e-01

Pos logit contributions
ipal+0.618
init+0.607
shift+0.574
actory+0.572
ounge+0.555
Neg logit contributions
 Dent-0.694
 Nadu-0.666
 Devi-0.651
 Equity-0.608
 Benefit-0.606
Token California
Token ID3442
Feature activation-1.11e+00

Pos logit contributions
 Dent+0.248
 Nadu+0.235
 Devi+0.229
 Equity+0.209
 Benefit+0.208
Neg logit contributions
ipal-0.343
init-0.338
shift-0.323
actory-0.322
ounge-0.314
Token.
Token ID13
Feature activation+3.95e-01

Pos logit contributions
 Dent+0.829
 Nadu+0.792
 Devi+0.769
 Benefit+0.721
 Equity+0.720
Neg logit contributions
ipal-0.829
init-0.818
shift-0.786
actory-0.785
itual-0.761
Token Hide
Token ID10415
Feature activation+1.39e+00

Pos logit contributions
ipal+0.276
init+0.273
shift+0.257
actory+0.255
ounge+0.246
Neg logit contributions
 Dent-0.313
 Nadu-0.303
 Devi-0.295
iaz-0.276
 Equity-0.274
Token Caption
Token ID11260
Feature activation+5.50e+00

Pos logit contributions
ipal+0.514
init+0.513
shift+0.451
actory+0.431
photo+0.421
Neg logit contributions
 Dent-1.534
 Nadu-1.507
 Devi-1.483
iaz-1.422
merce-1.417
Token 14
Token ID1478
Feature activation+1.11e+00

Pos logit contributions
init+1.678
ipal+1.547
shift+1.507
actory+1.328
photo+1.321
Neg logit contributions
 Dent-6.413
 Nadu-6.263
 Devi-6.183
merce-6.063
iaz-5.983
Token of
Token ID286
Feature activation+1.09e-01

Pos logit contributions
init+0.660
ipal+0.644
shift+0.614
actory+0.594
photo+0.578
Neg logit contributions
 Dent-1.004
 Nadu-0.986
 Devi-0.957
merce-0.902
 Equity-0.895
Token 15
Token ID1315
Feature activation+7.74e-01

Pos logit contributions
init+0.052
ipal+0.050
shift+0.047
actory+0.046
photo+0.043
Neg logit contributions
 Dent-0.110
 Nadu-0.108
 Devi-0.106
iaz-0.102
ouri-0.100
Token Photos
Token ID9434
Feature activation+4.23e+00

Pos logit contributions
init+0.367
ipal+0.361
shift+0.328
actory+0.326
photo+0.325
Neg logit contributions
 Dent-0.776
 Nadu-0.765
 Devi-0.744
merce-0.718
iaz-0.715
Token:
Token ID25
Feature activation+1.46e+00

Pos logit contributions
init+1.673
ipal+1.539
shift+1.511
photo+1.386
actory+1.384
Neg logit contributions
 Dent-4.575
 Nadu-4.552
 eleph-4.501
 Devi-4.457
merce-4.442
Token,
Token ID11
Feature activation-1.67e-01

Pos logit contributions
 Dent+1.137
 Nadu+1.083
 Devi+1.062
 Equity+0.990
 Benefit+0.989
Neg logit contributions
ipal-1.083
init-1.064
shift-1.014
actory-1.012
itual-0.980
Token New
Token ID968
Feature activation-3.01e-01

Pos logit contributions
 Dent+0.103
 Nadu+0.099
 Devi+0.095
iaz+0.088
 Equity+0.087
Neg logit contributions
init-0.145
ipal-0.145
shift-0.137
actory-0.136
ounge-0.133
Token Hampshire
Token ID13910
Feature activation-3.04e-01

Pos logit contributions
 Dent+0.199
 Nadu+0.191
 Devi+0.184
 Equity+0.168
iaz+0.168
Neg logit contributions
init-0.252
ipal-0.252
shift-0.239
actory-0.238
ounge-0.228
Token.
Token ID13
Feature activation+7.10e-01

Pos logit contributions
 Dent+0.233
 Nadu+0.221
 Devi+0.217
 Benefit+0.203
 Equity+0.203
Neg logit contributions
ipal-0.224
init-0.219
shift-0.211
actory-0.209
ounge-0.204
Token Hide
Token ID10415
Feature activation+1.80e+00

Pos logit contributions
ipal+0.494
init+0.490
shift+0.461
actory+0.455
ounge+0.439
Neg logit contributions
 Dent-0.562
 Nadu-0.546
 Devi-0.531
iaz-0.499
 Equity-0.494
Token Caption
Token ID11260
Feature activation+5.47e+00

Pos logit contributions
ipal+0.660
init+0.658
shift+0.582
actory+0.556
photo+0.544
Neg logit contributions
 Dent-2.001
 Nadu-1.950
 Devi-1.932
iaz-1.840
merce-1.835
Token 6
Token ID718
Feature activation+6.00e-01

Pos logit contributions
init+2.460
ipal+2.411
shift+2.215
actory+2.116
photo+2.103
Neg logit contributions
 Dent-5.594
 Nadu-5.459
 Devi-5.286
merce-5.134
iaz-5.095
Token of
Token ID286
Feature activation+2.18e-01

Pos logit contributions
init+0.361
ipal+0.355
shift+0.337
actory+0.327
photo+0.318
Neg logit contributions
 Dent-0.542
 Nadu-0.531
 Devi-0.517
 Equity-0.482
merce-0.481
Token 15
Token ID1315
Feature activation+1.04e+00

Pos logit contributions
init+0.104
ipal+0.101
shift+0.094
actory+0.093
photo+0.087
Neg logit contributions
 Dent-0.221
 Nadu-0.217
 Devi-0.214
iaz-0.204
ouri-0.201
Token Photos
Token ID9434
Feature activation+4.42e+00

Pos logit contributions
init+0.495
ipal+0.488
shift+0.442
actory+0.441
photo+0.433
Neg logit contributions
 Dent-1.041
 Nadu-1.023
 Devi-0.997
iaz-0.953
merce-0.952
Token:
Token ID25
Feature activation+1.89e+00

Pos logit contributions
init+1.740
ipal+1.596
shift+1.573
photo+1.444
actory+1.442
Neg logit contributions
 Dent-4.795
 Nadu-4.755
 eleph-4.691
 Devi-4.663
merce-4.635
Tokenin
Token ID259
Feature activation-5.70e-01

Pos logit contributions
ipal+1.392
init+1.388
shift+1.285
actory+1.273
ounge+1.258
Neg logit contributions
 Dent-1.594
 Nadu-1.518
 Devi-1.498
 Benefit-1.391
 Equity-1.391
Token,
Token ID11
Feature activation-2.48e-01

Pos logit contributions
 Dent+0.445
 Nadu+0.426
 Devi+0.416
 Equity+0.388
 Benefit+0.388
Neg logit contributions
ipal-0.411
init-0.404
shift-0.383
actory-0.383
ounge-0.371
Token Iowa
Token ID9406
Feature activation+5.25e-01

Pos logit contributions
 Dent+0.157
 Nadu+0.148
 Devi+0.144
 Equity+0.132
 Benefit+0.132
Neg logit contributions
ipal-0.216
init-0.213
shift-0.203
actory-0.203
ounge-0.197
Token.
Token ID13
Feature activation+5.42e-01

Pos logit contributions
ipal+0.375
init+0.369
shift+0.350
actory+0.350
ounge+0.339
Neg logit contributions
 Dent-0.414
 Nadu-0.395
 Devi-0.387
 Equity-0.362
 Benefit-0.361
Token Hide
Token ID10415
Feature activation+1.65e+00

Pos logit contributions
ipal+0.379
init+0.375
shift+0.353
actory+0.350
ounge+0.338
Neg logit contributions
 Dent-0.429
 Nadu-0.416
 Devi-0.404
iaz-0.379
 Equity-0.377
Token Caption
Token ID11260
Feature activation+5.47e+00

Pos logit contributions
ipal+0.616
init+0.612
shift+0.537
actory+0.516
photo+0.510
Neg logit contributions
 Dent-1.831
 Nadu-1.781
 Devi-1.764
iaz-1.677
merce-1.671
Token 5
Token ID642
Feature activation+6.99e-01

Pos logit contributions
ipal+2.765
init+2.733
actory+2.534
shift+2.522
photo+2.479
Neg logit contributions
 Nadu-5.224
 Dent-5.163
 Devi-4.950
merce-4.854
ouri-4.780
Token of
Token ID286
Feature activation+1.89e-01

Pos logit contributions
init+0.423
ipal+0.416
shift+0.394
actory+0.385
photo+0.374
Neg logit contributions
 Dent-0.627
 Nadu-0.615
 Devi-0.598
 Equity-0.557
merce-0.556
Token 15
Token ID1315
Feature activation+1.07e+00

Pos logit contributions
init+0.090
ipal+0.089
shift+0.082
actory+0.081
ounge+0.076
Neg logit contributions
 Dent-0.191
 Nadu-0.187
 Devi-0.184
iaz-0.175
ouri-0.173
Token Photos
Token ID9434
Feature activation+4.45e+00

Pos logit contributions
init+0.510
ipal+0.504
actory+0.454
shift+0.453
photo+0.447
Neg logit contributions
 Dent-1.070
 Nadu-1.050
 Devi-1.025
iaz-0.980
merce-0.973
Token:
Token ID25
Feature activation+1.82e+00

Pos logit contributions
init+1.763
ipal+1.636
shift+1.611
photo+1.513
actory+1.481
Neg logit contributions
 Dent-4.813
 Nadu-4.763
 Devi-4.673
 eleph-4.650
merce-4.635
Token Pasadena
Token ID41010
Feature activation+5.04e-02

Pos logit contributions
ipal+0.070
init+0.069
shift+0.066
actory+0.066
ounge+0.064
Neg logit contributions
 Dent-0.068
 Nadu-0.066
 Devi-0.064
iaz-0.059
 Equity-0.059
Token,
Token ID11
Feature activation-1.93e-01

Pos logit contributions
ipal+0.038
init+0.037
actory+0.036
shift+0.035
itual+0.034
Neg logit contributions
 Dent-0.038
 Nadu-0.036
 Devi-0.035
 Benefit-0.033
 Equity-0.033
Token California
Token ID3442
Feature activation-1.21e+00

Pos logit contributions
 Dent+0.114
 Nadu+0.106
 Devi+0.103
 Equity+0.095
 Benefit+0.094
Neg logit contributions
ipal-0.175
init-0.174
actory-0.166
shift-0.166
ounge-0.163
Token.
Token ID13
Feature activation+4.13e-01

Pos logit contributions
 Dent+0.905
 Nadu+0.858
 Devi+0.842
 Benefit+0.791
 Equity+0.788
Neg logit contributions
ipal-0.893
init-0.884
actory-0.846
shift-0.845
ounge-0.820
Token Hide
Token ID10415
Feature activation+1.26e+00

Pos logit contributions
ipal+0.288
init+0.285
shift+0.268
actory+0.266
ounge+0.257
Neg logit contributions
 Dent-0.328
 Nadu-0.318
 Devi-0.309
iaz-0.289
 Equity-0.288
Token Caption
Token ID11260
Feature activation+5.46e+00

Pos logit contributions
ipal+0.469
init+0.466
shift+0.413
actory+0.393
photo+0.382
Neg logit contributions
 Dent-1.392
 Nadu-1.364
 Devi-1.346
iaz-1.288
merce-1.282
Token 12
Token ID1105
Feature activation+1.04e+00

Pos logit contributions
init+2.108
ipal+1.942
shift+1.828
actory+1.741
photo+1.712
Neg logit contributions
 Dent-5.871
 Nadu-5.812
merce-5.741
 Devi-5.640
iaz-5.518
Token of
Token ID286
Feature activation+2.63e-01

Pos logit contributions
init+0.623
ipal+0.610
shift+0.583
actory+0.564
photo+0.546
Neg logit contributions
 Dent-0.947
 Nadu-0.927
 Devi-0.903
merce-0.847
 Equity-0.843
Token 15
Token ID1315
Feature activation+8.24e-01

Pos logit contributions
init+0.125
ipal+0.121
shift+0.113
actory+0.112
photo+0.104
Neg logit contributions
 Dent-0.268
 Nadu-0.261
 Devi-0.258
iaz-0.247
ouri-0.243
Token Photos
Token ID9434
Feature activation+4.19e+00

Pos logit contributions
init+0.394
ipal+0.387
shift+0.352
actory+0.351
photo+0.347
Neg logit contributions
 Dent-0.825
 Nadu-0.812
 Devi-0.792
merce-0.760
iaz-0.759
Token:
Token ID25
Feature activation+1.50e+00

Pos logit contributions
init+1.660
ipal+1.527
shift+1.500
actory+1.376
photo+1.371
Neg logit contributions
 Dent-4.528
 Nadu-4.499
 eleph-4.441
 Devi-4.409
merce-4.382
Token Pasadena
Token ID41010
Feature activation-1.36e-01

Pos logit contributions
ipal+0.105
init+0.104
shift+0.099
actory+0.099
ounge+0.096
Neg logit contributions
 Dent-0.092
 Nadu-0.088
 Devi-0.086
iaz-0.079
 Equity-0.079
Token,
Token ID11
Feature activation-4.31e-01

Pos logit contributions
 Dent+0.103
 Nadu+0.098
 Devi+0.096
 Equity+0.090
 Benefit+0.090
Neg logit contributions
ipal-0.101
init-0.101
actory-0.096
shift-0.095
ounge-0.092
Token California
Token ID3442
Feature activation-1.27e+00

Pos logit contributions
 Dent+0.263
 Nadu+0.248
 Devi+0.240
 Equity+0.220
 Benefit+0.219
Neg logit contributions
ipal-0.384
init-0.379
shift-0.363
actory-0.362
ounge-0.354
Token.
Token ID13
Feature activation+2.83e-01

Pos logit contributions
 Dent+0.951
 Nadu+0.902
 Devi+0.879
 Benefit+0.826
 Equity+0.823
Neg logit contributions
ipal-0.942
init-0.931
shift-0.895
actory-0.892
itual-0.867
Token Hide
Token ID10415
Feature activation+1.23e+00

Pos logit contributions
ipal+0.203
init+0.200
shift+0.189
actory+0.187
ounge+0.181
Neg logit contributions
 Dent-0.221
 Nadu-0.213
 Devi-0.207
iaz-0.194
 Equity-0.193
Token Caption
Token ID11260
Feature activation+5.46e+00

Pos logit contributions
ipal+0.460
init+0.456
shift+0.405
actory+0.386
photo+0.373
Neg logit contributions
 Dent-1.356
 Nadu-1.327
 Devi-1.309
iaz-1.250
merce-1.244
Token 11
Token ID1367
Feature activation+1.07e+00

Pos logit contributions
init+2.069
ipal+1.918
shift+1.821
actory+1.756
photo+1.670
Neg logit contributions
 Nadu-5.817
 Dent-5.805
 Devi-5.717
merce-5.601
iaz-5.516
Token of
Token ID286
Feature activation+1.34e-01

Pos logit contributions
init+0.639
ipal+0.625
shift+0.597
actory+0.579
photo+0.560
Neg logit contributions
 Dent-0.973
 Nadu-0.956
 Devi-0.929
merce-0.871
 Equity-0.866
Token 15
Token ID1315
Feature activation+6.94e-01

Pos logit contributions
init+0.064
ipal+0.062
shift+0.058
actory+0.057
photo+0.053
Neg logit contributions
 Dent-0.136
 Nadu-0.133
 Devi-0.131
iaz-0.126
ouri-0.124
Token Photos
Token ID9434
Feature activation+4.11e+00

Pos logit contributions
init+0.332
ipal+0.327
shift+0.298
actory+0.297
photo+0.292
Neg logit contributions
 Dent-0.694
 Nadu-0.682
 Devi-0.666
merce-0.638
iaz-0.637
Token:
Token ID25
Feature activation+1.43e+00

Pos logit contributions
init+1.638
ipal+1.510
shift+1.483
actory+1.361
photo+1.358
Neg logit contributions
 Dent-4.448
 Nadu-4.417
 eleph-4.338
 Devi-4.330
merce-4.293
Tokenaga
Token ID8126
Feature activation-8.71e-01

Pos logit contributions
ipal+0.584
init+0.572
shift+0.535
actory+0.533
ounge+0.514
Neg logit contributions
 Dent-0.849
 Nadu-0.818
 Devi-0.803
 Equity-0.755
 Benefit-0.754
Token,
Token ID11
Feature activation-4.79e-01

Pos logit contributions
 Dent+0.673
 Nadu+0.643
 Devi+0.629
 Equity+0.586
 Benefit+0.584
Neg logit contributions
ipal-0.636
init-0.625
shift-0.593
actory-0.591
ounge-0.573
Token California
Token ID3442
Feature activation-1.35e+00

Pos logit contributions
 Dent+0.302
 Nadu+0.286
 Devi+0.280
iaz+0.256
 Equity+0.256
Neg logit contributions
ipal-0.414
init-0.409
shift-0.391
actory-0.389
ounge-0.378
Token.
Token ID13
Feature activation+3.46e-01

Pos logit contributions
 Dent+1.006
 Nadu+0.959
 Devi+0.934
 Benefit+0.876
 Equity+0.874
Neg logit contributions
ipal-1.002
init-0.992
shift-0.955
actory-0.953
ounge-0.927
Token Hide
Token ID10415
Feature activation+1.30e+00

Pos logit contributions
ipal+0.241
init+0.238
shift+0.225
actory+0.222
ounge+0.216
Neg logit contributions
 Dent-0.276
 Nadu-0.266
 Devi-0.259
iaz-0.243
 Equity-0.241
Token Caption
Token ID11260
Feature activation+5.35e+00

Pos logit contributions
ipal+0.490
init+0.487
shift+0.429
actory+0.411
photo+0.398
Neg logit contributions
 Dent-1.438
 Nadu-1.409
 Devi-1.390
iaz-1.327
merce-1.323
Token 13
Token ID1511
Feature activation+1.26e+00

Pos logit contributions
init+1.752
ipal+1.730
shift+1.641
actory+1.597
photo+1.470
Neg logit contributions
 Nadu-6.035
 Dent-5.973
 Devi-5.781
merce-5.651
iaz-5.561
Token of
Token ID286
Feature activation+4.19e-02

Pos logit contributions
init+0.748
ipal+0.730
shift+0.696
actory+0.678
photo+0.656
Neg logit contributions
 Dent-1.144
 Nadu-1.122
 Devi-1.093
merce-1.030
 Equity-1.021
Token 15
Token ID1315
Feature activation+7.85e-01

Pos logit contributions
init+0.020
ipal+0.019
shift+0.018
actory+0.018
photo+0.017
Neg logit contributions
 Dent-0.043
 Nadu-0.042
 Devi-0.041
iaz-0.039
ouri-0.039
Token Photos
Token ID9434
Feature activation+4.16e+00

Pos logit contributions
init+0.374
ipal+0.368
shift+0.335
actory+0.332
photo+0.330
Neg logit contributions
 Dent-0.786
 Nadu-0.775
 Devi-0.754
merce-0.727
iaz-0.724
Token:
Token ID25
Feature activation+1.45e+00

Pos logit contributions
init+1.652
ipal+1.522
shift+1.492
actory+1.369
photo+1.368
Neg logit contributions
 Dent-4.501
 Nadu-4.473
 eleph-4.414
 Devi-4.385
merce-4.361
Token Grove
Token ID24144
Feature activation+1.03e+00

Pos logit contributions
ipal+0.740
init+0.730
shift+0.697
actory+0.695
ounge+0.676
Neg logit contributions
 Dent-0.605
 Nadu-0.576
 Devi-0.561
 Equity-0.515
 Benefit-0.512
Token,
Token ID11
Feature activation-2.35e-01

Pos logit contributions
ipal+0.727
init+0.714
shift+0.675
actory+0.674
ounge+0.653
Neg logit contributions
 Dent-0.812
 Nadu-0.779
 Devi-0.761
 Equity-0.711
 Benefit-0.708
Token California
Token ID3442
Feature activation-1.05e+00

Pos logit contributions
 Dent+0.149
 Nadu+0.141
 Devi+0.137
 Equity+0.126
iaz+0.125
Neg logit contributions
ipal-0.202
init-0.200
shift-0.191
actory-0.191
ounge-0.186
Token.
Token ID13
Feature activation+3.34e-01

Pos logit contributions
 Dent+0.780
 Nadu+0.744
 Devi+0.726
 Benefit+0.680
 Equity+0.678
Neg logit contributions
ipal-0.777
init-0.766
shift-0.736
actory-0.730
itual-0.713
Token Hide
Token ID10415
Feature activation+1.31e+00

Pos logit contributions
ipal+0.236
init+0.234
shift+0.220
actory+0.218
ounge+0.211
Neg logit contributions
 Dent-0.262
 Nadu-0.254
 Devi-0.246
iaz-0.231
 Equity-0.229
Token Caption
Token ID11260
Feature activation+5.28e+00

Pos logit contributions
ipal+0.487
init+0.486
shift+0.429
actory+0.410
photo+0.398
Neg logit contributions
 Dent-1.443
 Nadu-1.417
 Devi-1.394
iaz-1.337
merce-1.331
Token 15
Token ID1315
Feature activation+8.84e-01

Pos logit contributions
init+2.123
ipal+2.011
shift+1.940
actory+1.875
photo+1.826
Neg logit contributions
 Nadu-5.556
 Dent-5.516
 Devi-5.388
merce-5.303
iaz-5.267
Token of
Token ID286
Feature activation+1.02e-01

Pos logit contributions
init+0.533
ipal+0.519
shift+0.494
photo+0.480
actory+0.479
Neg logit contributions
 Dent-0.786
 Nadu-0.776
 Devi-0.747
iaz-0.707
merce-0.699
Token 15
Token ID1315
Feature activation+8.58e-01

Pos logit contributions
init+0.048
ipal+0.047
shift+0.044
actory+0.043
photo+0.041
Neg logit contributions
 Dent-0.103
 Nadu-0.101
 Devi-0.100
iaz-0.095
ouri-0.094
Token
Token ID198
Feature activation+5.41e-01

Pos logit contributions
init+0.545
ipal+0.545
shift+0.506
actory+0.495
photo+0.491
Neg logit contributions
 Dent-0.728
 Nadu-0.713
 Devi-0.696
iaz-0.652
ouri-0.643
Token
Token ID198
Feature activation+4.72e-01

Pos logit contributions
init+0.345
ipal+0.335
shift+0.321
actory+0.310
photo+0.302
Neg logit contributions
 Dent-0.471
 Nadu-0.457
 Devi-0.446
iaz-0.419
 Equity-0.416
Token View
Token ID3582
Feature activation+1.36e+00

Pos logit contributions
ipal+0.152
init+0.146
shift+0.135
actory+0.133
photo+0.128
Neg logit contributions
 Dent-0.263
 Nadu-0.259
 Devi-0.251
iaz-0.239
ouri-0.239
Token all
Token ID477
Feature activation-3.33e-01

Pos logit contributions
init+0.998
ipal+0.994
actory+0.953
shift+0.945
 selector+0.909
Neg logit contributions
 Dent-1.039
 Nadu-0.990
 Devi-0.966
 Equity-0.893
 Benefit-0.891
Token New
Token ID968
Feature activation+6.91e-01

Pos logit contributions
 Dent+0.211
 Nadu+0.206
 Devi+0.198
iaz+0.186
 Equity+0.181
Neg logit contributions
ipal-0.281
init-0.279
shift-0.266
actory-0.263
ounge-0.256
Token York
Token ID1971
Feature activation+1.31e+00

Pos logit contributions
init+0.415
ipal+0.407
shift+0.391
actory+0.382
photo+0.361
Neg logit contributions
 Dent-0.606
 Nadu-0.590
 Devi-0.585
iaz-0.545
ouri-0.538
Token Times
Token ID3782
Feature activation+2.99e+00

Pos logit contributions
init+1.164
ipal+1.161
shift+1.100
actory+1.097
 selector+1.066
Neg logit contributions
 Dent-0.757
 Nadu-0.729
 Devi-0.718
iaz-0.661
merce-0.659
Token newsletters
Token ID16983
Feature activation+5.27e+00

Pos logit contributions
init+1.302
ipal+1.252
shift+1.154
actory+1.150
photo+1.137
Neg logit contributions
 Dent-3.087
 Nadu-3.002
 Devi-2.966
iaz-2.866
 Benefit-2.812
Token.
Token ID13
Feature activation+9.32e-01

Pos logit contributions
init+2.904
ipal+2.699
shift+2.644
actory+2.563
photo+2.525
Neg logit contributions
 Dent-4.918
 eleph-4.826
 Nadu-4.792
 Devi-4.715
merce-4.644
Token
Token ID198
Feature activation+8.44e-01

Pos logit contributions
init+0.593
ipal+0.578
shift+0.553
actory+0.536
photo+0.518
Neg logit contributions
 Dent-0.804
 Nadu-0.783
 Devi-0.767
iaz-0.724
merce-0.716
Token
Token ID198
Feature activation+6.90e-01

Pos logit contributions
init+0.529
ipal+0.513
shift+0.494
actory+0.479
photo+0.464
Neg logit contributions
 Dent-0.736
 Nadu-0.719
 Devi-0.703
iaz-0.659
 Equity-0.653
TokenFor
Token ID1890
Feature activation-4.23e-01

Pos logit contributions
ipal+0.455
init+0.453
shift+0.427
actory+0.420
ounge+0.407
Neg logit contributions
 Dent-0.580
 Nadu-0.556
 Devi-0.545
 Equity-0.509
 Benefit-0.509
Token its
Token ID663
Feature activation-7.23e-02

Pos logit contributions
 Dent+0.322
 Nadu+0.309
 Devi+0.300
 Equity+0.280
iaz+0.279
Neg logit contributions
ipal-0.312
init-0.307
shift-0.291
actory-0.290
ounge-0.281
Token 20
Token ID1160
Feature activation+3.25e-01

Pos logit contributions
ipal+0.045
init+0.045
shift+0.041
actory+0.041
ounge+0.039
Neg logit contributions
 Dent-0.082
 Nadu-0.081
 Devi-0.079
iaz-0.075
 Equity-0.074
Token,
Token ID11
Feature activation-2.46e-01

Pos logit contributions
init+0.206
ipal+0.206
shift+0.192
actory+0.190
photo+0.179
Neg logit contributions
 Dent-0.279
 Nadu-0.270
 Devi-0.263
iaz-0.249
 Equity-0.247
Token 2015
Token ID1853
Feature activation-5.65e-01

Pos logit contributions
 Dent+0.174
 Nadu+0.166
 Devi+0.161
 Equity+0.149
 Benefit+0.148
Neg logit contributions
ipal-0.196
init-0.193
shift-0.183
actory-0.183
ounge-0.178
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
 Dent+0.432
 Nadu+0.408
 Devi+0.402
 Benefit+0.377
 Equity+0.376
Neg logit contributions
ipal-0.419
init-0.408
shift-0.390
actory-0.390
ounge-0.381
Token Hide
Token ID10415
Feature activation+1.21e+00

Pos logit contributions
 Dent+0.130
 Nadu+0.125
 Devi+0.122
iaz+0.114
 Equity+0.114
Neg logit contributions
ipal-0.115
init-0.114
shift-0.107
actory-0.106
ounge-0.103
Token Caption
Token ID11260
Feature activation+5.21e+00

Pos logit contributions
ipal+0.456
init+0.451
shift+0.404
actory+0.387
photo+0.373
Neg logit contributions
 Dent-1.338
 Nadu-1.305
 Devi-1.289
iaz-1.227
merce-1.218
Token 8
Token ID807
Feature activation+1.81e-01

Pos logit contributions
init+2.283
ipal+2.234
shift+2.001
actory+1.926
photo+1.913
Neg logit contributions
 Dent-5.411
 Nadu-5.299
 Devi-5.156
merce-5.116
iaz-4.985
Token of
Token ID286
Feature activation-1.19e-01

Pos logit contributions
init+0.111
ipal+0.110
shift+0.104
actory+0.101
photo+0.098
Neg logit contributions
 Dent-0.161
 Nadu-0.157
 Devi-0.153
 Equity-0.143
iaz-0.142
Token 15
Token ID1315
Feature activation+5.56e-01

Pos logit contributions
 Dent+0.120
 Nadu+0.118
 Devi+0.116
iaz+0.111
ouri+0.109
Neg logit contributions
init-0.058
ipal-0.056
shift-0.052
actory-0.052
itual-0.048
Token Photos
Token ID9434
Feature activation+3.93e+00

Pos logit contributions
init+0.270
ipal+0.266
shift+0.243
actory+0.241
photo+0.236
Neg logit contributions
 Dent-0.554
 Nadu-0.545
 Devi-0.531
iaz-0.508
merce-0.506
Token:
Token ID25
Feature activation+1.22e+00

Pos logit contributions
init+1.585
ipal+1.471
shift+1.442
actory+1.327
photo+1.319
Neg logit contributions
 Dent-4.233
 Nadu-4.194
 Devi-4.113
 eleph-4.077
merce-4.055
Token and
Token ID290
Feature activation+8.25e-02

Pos logit contributions
ipal+0.177
init+0.173
shift+0.164
actory+0.163
ounge+0.158
Neg logit contributions
 Dent-0.206
 Nadu-0.198
 Devi-0.193
 Equity-0.181
 Benefit-0.180
Token stem
Token ID10717
Feature activation-5.30e-01

Pos logit contributions
ipal+0.057
init+0.055
shift+0.053
actory+0.052
ounge+0.051
Neg logit contributions
 Dent-0.066
 Nadu-0.064
 Devi-0.063
 Equity-0.059
iaz-0.058
Token.
Token ID13
Feature activation+4.25e-01

Pos logit contributions
 Dent+0.430
 Nadu+0.411
 Devi+0.403
 Equity+0.377
 Benefit+0.376
Neg logit contributions
ipal-0.367
init-0.360
actory-0.340
shift-0.340
ounge-0.329
Token View
Token ID3582
Feature activation+5.34e-01

Pos logit contributions
ipal+0.344
init+0.339
shift+0.325
actory+0.321
ounge+0.313
Neg logit contributions
 Dent-0.290
 Nadu-0.279
 Devi-0.270
iaz-0.251
 Equity-0.249
Token Full
Token ID6462
Feature activation-1.24e-01

Pos logit contributions
ipal+0.378
init+0.373
actory+0.355
shift+0.355
ounge+0.341
Neg logit contributions
 Dent-0.421
 Nadu-0.404
 Devi-0.394
 Equity-0.367
iaz-0.366
Token Caption
Token ID11260
Feature activation+5.20e+00

Pos logit contributions
 Dent+0.084
 Nadu+0.081
 Devi+0.078
 Equity+0.072
 Benefit+0.072
Neg logit contributions
ipal-0.101
init-0.100
shift-0.095
actory-0.095
ounge-0.092
Token Adam
Token ID7244
Feature activation+1.08e+00

Pos logit contributions
ipal+3.148
init+3.072
shift+2.897
actory+2.872
photo+2.751
Neg logit contributions
 Dent-4.453
 Nadu-4.413
 Devi-4.256
iaz-4.126
merce-4.033
Token Glenn
Token ID17551
Feature activation+1.23e+00

Pos logit contributions
ipal+0.882
init+0.871
shift+0.827
actory+0.827
ounge+0.801
Neg logit contributions
 Dent-0.737
 Nadu-0.708
 Devi-0.687
 Equity-0.636
 Benefit-0.631
Token
Token ID198
Feature activation+3.05e-01

Pos logit contributions
ipal+0.905
init+0.897
shift+0.844
actory+0.842
ounge+0.817
Neg logit contributions
 Dent-0.935
 Nadu-0.898
 Devi-0.875
 Equity-0.816
 Benefit-0.813
Token
Token ID198
Feature activation+1.56e-01

Pos logit contributions
init+0.199
ipal+0.195
shift+0.187
actory+0.182
photo+0.176
Neg logit contributions
 Dent-0.260
 Nadu-0.252
 Devi-0.246
iaz-0.230
 Equity-0.229
TokenC
Token ID34
Feature activation+5.04e-01

Pos logit contributions
ipal+0.094
init+0.092
actory+0.086
shift+0.086
ounge+0.083
Neg logit contributions
 Dent-0.140
 Nadu-0.135
 Devi-0.132
 Equity-0.125
 Benefit-0.124
Token community
Token ID2055
Feature activation+7.04e-01

Pos logit contributions
 Dent+0.024
 Nadu+0.023
 Devi+0.022
 Equity+0.021
 Benefit+0.021
Neg logit contributions
ipal-0.024
init-0.024
shift-0.022
actory-0.022
ounge-0.022
Token.
Token ID13
Feature activation+8.42e-01

Pos logit contributions
ipal+0.489
init+0.481
shift+0.454
actory+0.453
ounge+0.439
Neg logit contributions
 Dent-0.566
 Nadu-0.543
 Devi-0.531
 Equity-0.497
 Benefit-0.495
Token (
Token ID357
Feature activation+2.17e-01

Pos logit contributions
ipal+0.628
init+0.624
shift+0.588
actory+0.584
ounge+0.567
Neg logit contributions
 Dent-0.622
 Nadu-0.604
 Devi-0.584
iaz-0.548
 Benefit-0.539
TokenPhoto
Token ID6191
Feature activation+3.77e+00

Pos logit contributions
ipal+0.134
init+0.132
shift+0.124
actory+0.123
ounge+0.119
Neg logit contributions
 Dent-0.192
 Nadu-0.185
 Devi-0.181
 Equity-0.170
 Benefit-0.170
Token by
Token ID416
Feature activation-8.88e-02

Pos logit contributions
ipal+2.402
init+2.363
shift+2.219
actory+2.215
ounge+2.124
Neg logit contributions
 Dent-3.201
 Nadu-3.112
 Devi-3.038
iaz-2.842
 Equity-2.837
Token REUTERS
Token ID15862
Feature activation+5.05e+00

Pos logit contributions
 Dent+0.067
 Nadu+0.064
 Devi+0.063
 Equity+0.058
 Benefit+0.058
Neg logit contributions
ipal-0.066
init-0.065
shift-0.062
actory-0.062
ounge-0.060
Token/
Token ID14
Feature activation+3.19e+00

Pos logit contributions
ipal+3.424
init+3.380
shift+3.178
actory+3.172
ounge+3.071
Neg logit contributions
 Dent-4.072
 Nadu-3.936
 Devi-3.826
iaz-3.569
 Equity-3.552
TokenJohn
Token ID7554
Feature activation+8.51e-01

Pos logit contributions
ipal+1.915
init+1.914
shift+1.738
actory+1.712
photo+1.685
Neg logit contributions
 Dent-2.846
 Nadu-2.770
 Devi-2.675
 Benefit-2.516
iaz-2.514
Token S
Token ID311
Feature activation+6.18e-01

Pos logit contributions
init+0.615
ipal+0.601
actory+0.577
shift+0.567
itual+0.555
Neg logit contributions
 Nadu-0.639
 Dent-0.638
 Devi-0.601
iaz-0.574
 Equity-0.561
Tokenomm
Token ID2002
Feature activation+7.98e-02

Pos logit contributions
ipal+0.437
init+0.429
shift+0.405
actory+0.404
ounge+0.391
Neg logit contributions
 Dent-0.492
 Nadu-0.472
 Devi-0.461
 Equity-0.432
 Benefit-0.429
Tokeners
Token ID364
Feature activation+9.12e-01

Pos logit contributions
ipal+0.055
init+0.055
actory+0.051
shift+0.051
ounge+0.049
Neg logit contributions
 Dent-0.064
 Nadu-0.062
 Devi-0.061
 Equity-0.057
 Benefit-0.056
Token her
Token ID607
Feature activation-4.10e-02

Pos logit contributions
ipal+0.391
init+0.386
actory+0.366
shift+0.365
ounge+0.354
Neg logit contributions
 Dent-0.366
 Nadu-0.354
 Devi-0.340
 Benefit-0.319
iaz-0.317
Token.
Token ID13
Feature activation+8.67e-01

Pos logit contributions
 Dent+0.033
 Nadu+0.032
 Devi+0.031
iaz+0.029
 Benefit+0.029
Neg logit contributions
ipal-0.029
init-0.028
shift-0.027
actory-0.027
ounge-0.026
Token (
Token ID357
Feature activation+2.95e-01

Pos logit contributions
ipal+0.655
init+0.650
shift+0.610
actory+0.608
ounge+0.590
Neg logit contributions
 Dent-0.631
 Nadu-0.618
 Devi-0.593
iaz-0.558
 Benefit-0.546
TokenPhoto
Token ID6191
Feature activation+3.98e+00

Pos logit contributions
ipal+0.130
init+0.126
shift+0.115
actory+0.115
ounge+0.109
Neg logit contributions
 Dent-0.313
 Nadu-0.303
 Devi-0.298
 Equity-0.284
 Benefit-0.283
Token by
Token ID416
Feature activation+1.25e-01

Pos logit contributions
ipal+2.669
init+2.621
shift+2.471
actory+2.466
ounge+2.383
Neg logit contributions
 Dent-3.292
 Nadu-3.165
 Devi-3.097
 Equity-2.900
 Benefit-2.890
Token REUTERS
Token ID15862
Feature activation+5.03e+00

Pos logit contributions
ipal+0.088
init+0.086
shift+0.081
actory+0.081
ounge+0.078
Neg logit contributions
 Dent-0.100
 Nadu-0.096
 Devi-0.094
 Equity-0.088
iaz-0.087
Token/
Token ID14
Feature activation+3.14e+00

Pos logit contributions
init+2.750
ipal+2.676
photo+2.565
shift+2.541
actory+2.410
Neg logit contributions
 Dent-4.499
 Nadu-4.457
 Devi-4.305
merce-4.240
 eleph-4.186
TokenCar
Token ID9914
Feature activation+2.11e+00

Pos logit contributions
ipal+1.953
init+1.945
shift+1.795
actory+1.759
photo+1.707
Neg logit contributions
 Dent-2.731
 Nadu-2.666
 Devi-2.573
iaz-2.412
 Benefit-2.407
Tokenlo
Token ID5439
Feature activation-1.93e+00

Pos logit contributions
ipal+0.998
init+0.978
actory+0.898
shift+0.885
ounge+0.841
Neg logit contributions
 Dent-2.160
 Nadu-2.100
 Devi-2.054
 Equity-1.951
 Benefit-1.933
Token Alleg
Token ID26326
Feature activation+3.81e-01

Pos logit contributions
 Dent+1.171
 Nadu+1.126
 Devi+1.077
 Equity+0.987
 Benefit+0.986
Neg logit contributions
ipal-1.709
init-1.691
actory-1.614
shift-1.611
ounge-1.574
Tokenri
Token ID380
Feature activation+2.07e-01

Pos logit contributions
ipal+0.258
init+0.253
shift+0.239
actory+0.238
ounge+0.231
Neg logit contributions
 Dent-0.314
 Nadu-0.301
 Devi-0.295
 Equity-0.276
 Benefit-0.275
Token by
Token ID416
Feature activation-1.80e-01

Pos logit contributions
ipal+2.767
init+2.716
shift+2.559
actory+2.555
ounge+2.467
Neg logit contributions
 Dent-3.447
 Nadu-3.320
 Devi-3.248
 Equity-3.040
 Benefit-3.028
Token John
Token ID1757
Feature activation+1.50e-01

Pos logit contributions
 Dent+0.146
 Nadu+0.140
 Devi+0.137
 Equity+0.128
 Benefit+0.128
Neg logit contributions
ipal-0.125
init-0.122
shift-0.116
actory-0.115
ounge-0.112
Token Moore
Token ID8877
Feature activation-4.03e-01

Pos logit contributions
init+0.114
ipal+0.114
actory+0.109
shift+0.107
itual+0.104
Neg logit contributions
 Dent-0.107
 Nadu-0.105
 Devi-0.100
iaz-0.094
 Equity-0.093
Token/
Token ID14
Feature activation+2.69e+00

Pos logit contributions
 Dent+0.328
 Nadu+0.317
 Devi+0.310
 Equity+0.289
iaz+0.288
Neg logit contributions
ipal-0.275
init-0.270
shift-0.254
actory-0.253
ounge-0.245
TokenGetty
Token ID6633
Feature activation+4.23e+00

Pos logit contributions
ipal+1.373
init+1.351
shift+1.241
actory+1.214
photo+1.173
Neg logit contributions
 Dent-2.625
 Nadu-2.546
 Devi-2.530
iaz-2.372
 Benefit-2.365
Token Images
Token ID5382
Feature activation+5.01e+00

Pos logit contributions
ipal+2.919
init+2.902
actory+2.742
shift+2.713
ounge+2.672
Neg logit contributions
 Dent-3.322
 Nadu-3.209
 Devi-3.147
iaz-2.905
 Benefit-2.903
Token)
Token ID8
Feature activation+1.92e+00

Pos logit contributions
ipal+3.833
init+3.792
actory+3.598
shift+3.593
ounge+3.509
Neg logit contributions
 Dent-3.557
 Nadu-3.425
 Devi-3.346
iaz-3.077
 Equity-3.070
Token Jeff
Token ID5502
Feature activation-5.96e-01

Pos logit contributions
ipal+1.454
init+1.448
shift+1.361
actory+1.351
ounge+1.316
Neg logit contributions
 Dent-1.363
 Nadu-1.340
 Devi-1.286
iaz-1.216
ouri-1.186
Token Sessions
Token ID15184
Feature activation-5.58e-01

Pos logit contributions
 Dent+0.304
 Nadu+0.299
 Devi+0.282
 Benefit+0.252
iaz+0.249
Neg logit contributions
ipal-0.575
init-0.575
shift-0.549
actory-0.549
ounge-0.538
Token Sen
Token ID2311
Feature activation+2.93e-03

Pos logit contributions
 Dent+0.360
 Nadu+0.343
 Devi+0.335
 Equity+0.305
iaz+0.305
Neg logit contributions
ipal-0.475
init-0.469
shift-0.447
actory-0.446
ounge-0.435
Token.
Token ID13
Feature activation+3.36e-01

Pos logit contributions
ipal+0.002
init+0.002
shift+0.002
actory+0.002
ounge+0.002
Neg logit contributions
 Dent-0.003
 Nadu-0.002
 Devi-0.002
 Equity-0.002
iaz-0.002
Token View
Token ID3582
Feature activation+1.09e+00

Pos logit contributions
ipal+0.184
init+0.178
shift+0.164
actory+0.163
photo+0.156
Neg logit contributions
 Dent-0.312
 Nadu-0.306
 Devi-0.298
iaz-0.282
ouri-0.282
Token all
Token ID477
Feature activation-3.04e-01

Pos logit contributions
init+0.808
ipal+0.804
actory+0.770
shift+0.764
 selector+0.732
Neg logit contributions
 Dent-0.827
 Nadu-0.790
 Devi-0.771
 Equity-0.713
 Benefit-0.713
Token New
Token ID968
Feature activation+6.96e-01

Pos logit contributions
 Dent+0.191
 Nadu+0.186
 Devi+0.180
iaz+0.168
 Equity+0.164
Neg logit contributions
ipal-0.258
init-0.257
shift-0.244
actory-0.241
ounge-0.235
Token York
Token ID1971
Feature activation+1.32e+00

Pos logit contributions
init+0.420
ipal+0.414
shift+0.395
actory+0.387
photo+0.367
Neg logit contributions
 Dent-0.607
 Nadu-0.592
 Devi-0.587
iaz-0.546
 Equity-0.540
Token Times
Token ID3782
Feature activation+2.85e+00

Pos logit contributions
init+1.173
ipal+1.172
shift+1.108
actory+1.106
 selector+1.073
Neg logit contributions
 Dent-0.758
 Nadu-0.729
 Devi-0.718
iaz-0.660
merce-0.656
Token newsletters
Token ID16983
Feature activation+4.96e+00

Pos logit contributions
init+1.245
ipal+1.211
shift+1.111
actory+1.105
photo+1.086
Neg logit contributions
 Dent-2.942
 Nadu-2.867
 Devi-2.829
iaz-2.723
 Benefit-2.683
Token.
Token ID13
Feature activation+8.33e-01

Pos logit contributions
init+2.735
ipal+2.555
shift+2.483
actory+2.419
photo+2.372
Neg logit contributions
 Dent-4.625
 Nadu-4.490
 eleph-4.449
 Devi-4.417
merce-4.321
Token
Token ID198
Feature activation+6.99e-01

Pos logit contributions
init+0.534
ipal+0.521
shift+0.497
actory+0.483
photo+0.466
Neg logit contributions
 Dent-0.715
 Nadu-0.696
 Devi-0.681
iaz-0.643
merce-0.633
Token
Token ID198
Feature activation+5.79e-01

Pos logit contributions
init+0.441
ipal+0.429
shift+0.411
actory+0.401
photo+0.386
Neg logit contributions
 Dent-0.608
 Nadu-0.594
 Devi-0.579
iaz-0.543
 Equity-0.540
Token
Token ID447
Feature activation+7.32e-02

Pos logit contributions
ipal+0.376
init+0.373
shift+0.350
actory+0.346
ounge+0.334
Neg logit contributions
 Dent-0.493
 Nadu-0.474
 Devi-0.465
 Equity-0.436
 Benefit-0.435
Token
Token ID250
Feature activation+2.37e-02

Pos logit contributions
ipal+0.034
init+0.034
actory+0.031
shift+0.031
itual+0.029
Neg logit contributions
 Dent-0.075
 Nadu-0.073
 Devi-0.071
 Equity-0.068
iaz-0.068
Token issues
Token ID2428
Feature activation-1.74e+00

Pos logit contributions
ipal+0.150
init+0.148
shift+0.140
actory+0.140
ounge+0.136
Neg logit contributions
 Dent-0.128
 Nadu-0.122
 Devi-0.119
 Equity-0.110
 Benefit-0.110
Token.
Token ID13
Feature activation+3.84e-01

Pos logit contributions
 Dent+1.338
 Nadu+1.280
 Devi+1.251
 Equity+1.166
 Benefit+1.161
Neg logit contributions
ipal-1.280
init-1.259
shift-1.193
actory-1.191
ounge-1.155
Token (
Token ID357
Feature activation+4.72e-02

Pos logit contributions
ipal+0.287
init+0.285
shift+0.269
actory+0.267
ounge+0.260
Neg logit contributions
 Dent-0.283
 Nadu-0.276
 Devi-0.267
iaz-0.250
 Equity-0.246
TokenPhoto
Token ID6191
Feature activation+3.78e+00

Pos logit contributions
ipal+0.019
init+0.018
actory+0.017
shift+0.017
ounge+0.016
Neg logit contributions
 Dent-0.052
 Nadu-0.050
 Devi-0.049
 Equity-0.047
 Benefit-0.047
Token by
Token ID416
Feature activation-8.05e-02

Pos logit contributions
ipal+2.551
init+2.505
shift+2.362
actory+2.357
ounge+2.279
Neg logit contributions
 Dent-3.127
 Nadu-3.002
 Devi-2.939
 Equity-2.753
 Benefit-2.744
Token REUTERS
Token ID15862
Feature activation+4.94e+00

Pos logit contributions
 Dent+0.067
 Nadu+0.064
 Devi+0.063
 Equity+0.059
 Benefit+0.059
Neg logit contributions
ipal-0.054
init-0.053
shift-0.050
actory-0.050
ounge-0.048
Token/
Token ID14
Feature activation+3.09e+00

Pos logit contributions
init+2.700
ipal+2.613
photo+2.521
shift+2.495
actory+2.358
Neg logit contributions
 Dent-4.439
 Nadu-4.403
 Devi-4.263
 eleph-4.192
merce-4.186
TokenGary
Token ID33820
Feature activation+7.97e-01

Pos logit contributions
ipal+1.885
init+1.872
shift+1.719
actory+1.697
photo+1.652
Neg logit contributions
 Dent-2.715
 Nadu-2.659
 Devi-2.579
 Benefit-2.413
iaz-2.410
Token Cameron
Token ID10821
Feature activation+8.13e-01

Pos logit contributions
init+0.496
ipal+0.479
actory+0.456
photo+0.456
shift+0.452
Neg logit contributions
 Nadu-0.672
 Dent-0.646
 Devi-0.622
merce-0.605
ouri-0.605
Token/
Token ID14
Feature activation+2.84e+00

Pos logit contributions
ipal+0.646
init+0.636
shift+0.606
actory+0.605
ounge+0.587
Neg logit contributions
 Dent-0.578
 Nadu-0.549
 Devi-0.536
 Equity-0.497
 Benefit-0.495
TokenFile
Token ID8979
Feature activation+9.61e-01

Pos logit contributions
ipal+1.810
init+1.779
actory+1.663
shift+1.659
ounge+1.591
Neg logit contributions
 Dent-2.438
 Nadu-2.339
 Devi-2.327
 Benefit-2.153
iaz-2.146
Token View
Token ID3582
Feature activation+1.07e+00

Pos logit contributions
ipal+0.112
init+0.108
shift+0.100
actory+0.099
photo+0.095
Neg logit contributions
 Dent-0.191
 Nadu-0.188
 Devi-0.182
iaz-0.173
ouri-0.173
Token all
Token ID477
Feature activation-4.58e-01

Pos logit contributions
init+0.786
ipal+0.783
actory+0.750
shift+0.744
 selector+0.713
Neg logit contributions
 Dent-0.808
 Nadu-0.770
 Devi-0.752
 Equity-0.695
 Benefit-0.695
Token New
Token ID968
Feature activation+5.75e-01

Pos logit contributions
 Dent+0.289
 Nadu+0.281
 Devi+0.271
iaz+0.253
 Equity+0.247
Neg logit contributions
ipal-0.389
init-0.387
shift-0.369
actory-0.364
ounge-0.355
Token York
Token ID1971
Feature activation+1.14e+00

Pos logit contributions
init+0.347
ipal+0.341
shift+0.326
actory+0.319
photo+0.303
Neg logit contributions
 Dent-0.502
 Nadu-0.489
 Devi-0.484
iaz-0.451
ouri-0.445
Token Times
Token ID3782
Feature activation+2.72e+00

Pos logit contributions
init+1.020
ipal+1.018
shift+0.964
actory+0.962
 selector+0.932
Neg logit contributions
 Dent-0.656
 Nadu-0.630
 Devi-0.620
iaz-0.568
merce-0.563
Token newsletters
Token ID16983
Feature activation+4.82e+00

Pos logit contributions
init+1.194
ipal+1.160
shift+1.068
actory+1.061
photo+1.041
Neg logit contributions
 Dent-2.813
 Nadu-2.737
 Devi-2.706
iaz-2.597
 Benefit-2.562
Token.
Token ID13
Feature activation+7.56e-01

Pos logit contributions
init+2.681
ipal+2.520
shift+2.441
actory+2.384
photo+2.331
Neg logit contributions
 Dent-4.479
 Nadu-4.355
 Devi-4.287
 eleph-4.286
merce-4.168
Token
Token ID198
Feature activation+6.89e-01

Pos logit contributions
init+0.485
ipal+0.473
shift+0.452
actory+0.439
photo+0.423
Neg logit contributions
 Dent-0.649
 Nadu-0.632
 Devi-0.619
iaz-0.584
merce-0.576
Token
Token ID198
Feature activation+5.67e-01

Pos logit contributions
init+0.434
ipal+0.421
shift+0.404
actory+0.393
photo+0.379
Neg logit contributions
 Dent-0.600
 Nadu-0.585
 Devi-0.572
iaz-0.535
 Equity-0.533
TokenThe
Token ID464
Feature activation-2.72e-01

Pos logit contributions
ipal+0.364
init+0.360
shift+0.337
actory+0.334
ounge+0.322
Neg logit contributions
 Dent-0.487
 Nadu-0.468
 Devi-0.460
 Equity-0.431
 Benefit-0.430
Token White
Token ID2635
Feature activation-3.34e-01

Pos logit contributions
 Dent+0.215
 Nadu+0.206
 Devi+0.201
 Equity+0.188
 Benefit+0.187
Neg logit contributions
ipal-0.193
init-0.190
shift-0.179
actory-0.179
ounge-0.173
Token/
Token ID14
Feature activation+1.65e+00

Pos logit contributions
ipal+1.827
init+1.809
shift+1.703
actory+1.698
ounge+1.650
Neg logit contributions
 Dent-1.912
 Nadu-1.834
 Devi-1.783
 Equity-1.660
 Benefit-1.659
TokenT
Token ID51
Feature activation+1.07e+00

Pos logit contributions
ipal+0.950
init+0.946
shift+0.872
actory+0.865
ounge+0.827
Neg logit contributions
 Dent-1.516
 Nadu-1.467
 Devi-1.433
iaz-1.350
 Benefit-1.350
TokenNS
Token ID8035
Feature activation+4.52e-01

Pos logit contributions
ipal+0.574
init+0.568
actory+0.519
shift+0.514
ounge+0.498
Neg logit contributions
 Dent-1.030
 Nadu-0.996
 Devi-0.983
 Equity-0.924
 Benefit-0.924
Token via
Token ID2884
Feature activation+1.10e+00

Pos logit contributions
ipal+0.330
init+0.324
shift+0.307
actory+0.307
ounge+0.297
Neg logit contributions
 Dent-0.348
 Nadu-0.333
 Devi-0.325
 Equity-0.303
 Benefit-0.302
Token Getty
Token ID7136
Feature activation+4.68e+00

Pos logit contributions
ipal+0.500
init+0.484
shift+0.444
actory+0.439
ounge+0.414
Neg logit contributions
 Dent-1.155
 Nadu-1.121
 Devi-1.099
 Equity-1.044
iaz-1.044
Token Images
Token ID5382
Feature activation+4.76e+00

Pos logit contributions
init+3.182
ipal+3.165
actory+2.986
shift+2.947
ounge+2.888
Neg logit contributions
 Dent-3.684
 Nadu-3.605
 Devi-3.539
iaz-3.258
 Equity-3.244
Token)
Token ID8
Feature activation+1.71e+00

Pos logit contributions
ipal+3.592
init+3.568
shift+3.374
actory+3.367
ounge+3.288
Neg logit contributions
 Dent-3.422
 Nadu-3.315
 Devi-3.222
iaz-2.971
 Equity-2.948
Token Indiana
Token ID10278
Feature activation+1.61e-01

Pos logit contributions
ipal+1.335
init+1.327
shift+1.249
actory+1.244
ounge+1.207
Neg logit contributions
 Dent-1.198
 Nadu-1.166
 Devi-1.119
iaz-1.047
 Equity-1.035
Token Gov
Token ID10964
Feature activation-3.08e-01

Pos logit contributions
ipal+0.146
init+0.144
actory+0.138
shift+0.137
ounge+0.134
Neg logit contributions
 Dent-0.095
 Nadu-0.091
 Devi-0.088
 Equity-0.080
 Benefit-0.080
Token.
Token ID13
Feature activation+1.55e-01

Pos logit contributions
 Dent+0.242
 Nadu+0.230
 Devi+0.226
 Equity+0.211
 Benefit+0.210
Neg logit contributions
ipal-0.220
init-0.216
shift-0.207
actory-0.206
ounge-0.199
Token Mike
Token ID4995
Feature activation+2.25e-01

Pos logit contributions
ipal+0.109
init+0.106
shift+0.103
actory+0.102
itual+0.098
Neg logit contributions
 Dent-0.125
 Nadu-0.117
 Devi-0.116
 Equity-0.110
 Benefit-0.109
Tokenow
Token ID322
Feature activation+1.84e+00

Pos logit contributions
 Dent+3.255
 Nadu+3.111
 Devi+3.047
 Equity+2.839
 Benefit+2.820
Neg logit contributions
ipal-3.021
init-2.962
shift-2.807
actory-2.803
ounge-2.717
Token support
Token ID1104
Feature activation-1.85e+00

Pos logit contributions
ipal+1.413
init+1.405
actory+1.324
shift+1.316
ounge+1.280
Neg logit contributions
 Dent-1.311
 Nadu-1.292
 Devi-1.229
iaz-1.140
 Benefit-1.140
Token from
Token ID422
Feature activation-4.89e-01

Pos logit contributions
 Dent+1.328
 Nadu+1.250
 Devi+1.232
 Equity+1.143
 Benefit+1.137
Neg logit contributions
ipal-1.453
init-1.424
shift-1.359
actory-1.354
ounge-1.319
Token former
Token ID1966
Feature activation-1.55e-01

Pos logit contributions
 Dent+0.353
 Nadu+0.341
 Devi+0.331
 Equity+0.306
 Benefit+0.306
Neg logit contributions
ipal-0.377
init-0.372
shift-0.353
actory-0.352
ounge-0.342
Token Ku
Token ID12554
Feature activation-2.67e+00

Pos logit contributions
 Dent+0.111
 Nadu+0.107
 Devi+0.104
iaz+0.096
 Benefit+0.095
Neg logit contributions
ipal-0.120
init-0.119
shift-0.113
actory-0.112
ounge-0.109
Token Klux
Token ID45092
Feature activation-5.55e+00

Pos logit contributions
 Dent+1.767
 Nadu+1.676
 Devi+1.647
 Equity+1.526
 Benefit+1.503
Neg logit contributions
ipal-2.252
init-2.226
shift-2.108
actory-2.105
itual-2.038
Token Klan
Token ID31151
Feature activation-2.45e+00

Pos logit contributions
 Dent+3.034
 Nadu+2.854
 Devi+2.766
 Equity+2.488
 Benefit+2.468
Neg logit contributions
ipal-5.328
init-5.258
actory-5.043
shift-5.017
ounge-4.917
Token leader
Token ID3554
Feature activation-6.30e-01

Pos logit contributions
 Dent+1.737
 Nadu+1.655
 Devi+1.616
 Equity+1.493
 Benefit+1.487
Neg logit contributions
ipal-1.945
init-1.915
shift-1.820
actory-1.818
ounge-1.767
Token David
Token ID3271
Feature activation-2.51e-01

Pos logit contributions
 Dent+0.452
 Nadu+0.440
 Devi+0.428
iaz+0.391
 Equity+0.390
Neg logit contributions
ipal-0.492
init-0.484
actory-0.458
shift-0.454
ounge-0.444
Token Duke
Token ID11083
Feature activation-2.01e+00

Pos logit contributions
 Dent+0.140
 Nadu+0.138
 Devi+0.134
 Benefit+0.118
 Equity+0.118
Neg logit contributions
ipal-0.233
init-0.228
shift-0.215
actory-0.214
ounge-0.211
Token.
Token ID13
Feature activation+7.81e-01

Pos logit contributions
 Dent+1.583
 Nadu+1.510
 Devi+1.478
 Equity+1.383
 Benefit+1.377
Neg logit contributions
ipal-1.443
init-1.415
shift-1.346
actory-1.340
ounge-1.298
Token Feed
Token ID18272
Feature activation-7.00e-01

Pos logit contributions
 Dent+0.087
 Nadu+0.084
 Devi+0.081
iaz+0.075
 Equity+0.075
Neg logit contributions
ipal-0.100
init-0.098
shift-0.095
actory-0.094
ounge-0.091
Tokenbooks
Token ID12106
Feature activation-1.69e-01

Pos logit contributions
 Dent+0.574
 Nadu+0.550
 Devi+0.538
 Equity+0.504
 Benefit+0.503
Neg logit contributions
ipal-0.477
init-0.467
shift-0.441
actory-0.440
ounge-0.426
Token,
Token ID11
Feature activation-2.48e-01

Pos logit contributions
 Dent+0.133
 Nadu+0.128
 Devi+0.125
 Equity+0.116
 Benefit+0.116
Neg logit contributions
ipal-0.121
init-0.119
shift-0.113
actory-0.113
ounge-0.109
Token try
Token ID1949
Feature activation-1.46e+00

Pos logit contributions
 Dent+0.188
 Nadu+0.181
 Devi+0.176
 Equity+0.164
iaz+0.164
Neg logit contributions
ipal-0.182
init-0.180
shift-0.172
actory-0.171
ounge-0.165
Token Project
Token ID4935
Feature activation-8.30e-01

Pos logit contributions
 Dent+1.150
 Nadu+1.104
 Devi+1.078
 Equity+1.008
 Benefit+1.003
Neg logit contributions
ipal-1.035
init-1.018
shift-0.966
actory-0.961
ounge-0.931
Token Gutenberg
Token ID20336
Feature activation-4.96e+00

Pos logit contributions
 Dent+0.490
 Nadu+0.463
 Devi+0.448
 Equity+0.408
iaz+0.407
Neg logit contributions
ipal-0.753
init-0.745
shift-0.715
actory-0.713
ounge-0.693
Token (
Token ID357
Feature activation-3.06e-01

Pos logit contributions
 Dent+3.928
 Nadu+3.752
 Devi+3.665
 Benefit+3.441
 Equity+3.422
Neg logit contributions
ipal-3.490
init-3.420
shift-3.238
actory-3.233
ounge-3.143
Tokenwww
Token ID2503
Feature activation-1.25e+00

Pos logit contributions
 Dent+0.264
 Nadu+0.253
 Devi+0.248
 Equity+0.233
 Benefit+0.232
Neg logit contributions
ipal-0.197
init-0.193
shift-0.181
actory-0.181
ounge-0.175
Token.
Token ID13
Feature activation+1.79e-01

Pos logit contributions
 Dent+1.038
 Nadu+0.994
 Devi+0.974
 Equity+0.917
 Benefit+0.906
Neg logit contributions
ipal-0.841
init-0.832
shift-0.783
actory-0.780
ounge-0.749
Tokeng
Token ID70
Feature activation-5.36e-01

Pos logit contributions
ipal+0.115
init+0.113
shift+0.106
actory+0.106
ounge+0.102
Neg logit contributions
 Dent-0.154
 Nadu-0.148
 Devi-0.145
 Equity-0.137
 Benefit-0.136
Tokenutenberg
Token ID19028
Feature activation+1.89e+00

Pos logit contributions
 Dent+0.504
 Nadu+0.486
 Devi+0.476
iaz+0.454
 Benefit+0.451
Neg logit contributions
ipal-0.295
init-0.287
actory-0.267
shift-0.266
ounge-0.256
Token comments
Token ID3651
Feature activation-1.62e+00

Pos logit contributions
 Dent+0.174
 Nadu+0.167
 Devi+0.164
 Equity+0.153
 Benefit+0.153
Neg logit contributions
ipal-0.144
init-0.142
shift-0.134
actory-0.134
ounge-0.129
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
 Dent+1.284
 Nadu+1.230
 Devi+1.203
 Equity+1.126
 Benefit+1.122
Neg logit contributions
ipal-1.147
init-1.125
shift-1.063
actory-1.062
ounge-1.028
Token
Token ID198
Feature activation-1.61e-01

Pos logit contributions
 Dent+0.138
 Nadu+0.132
 Devi+0.129
 Equity+0.119
iaz+0.119
Neg logit contributions
ipal-0.144
init-0.142
shift-0.135
actory-0.134
ounge-0.130
Token
Token ID198
Feature activation-2.50e-01

Pos logit contributions
 Dent+0.130
 Nadu+0.124
 Devi+0.122
 Equity+0.114
 Benefit+0.113
Neg logit contributions
ipal-0.112
init-0.111
shift-0.105
actory-0.104
ounge-0.100
TokenHigh
Token ID11922
Feature activation-5.53e-03

Pos logit contributions
 Dent+0.215
 Nadu+0.206
 Devi+0.202
 Equity+0.190
 Benefit+0.189
Neg logit contributions
ipal-0.161
init-0.158
shift-0.149
actory-0.148
ounge-0.143
Tokenlights
Token ID8091
Feature activation-4.92e+00

Pos logit contributions
 Dent+0.004
 Nadu+0.004
 Devi+0.004
iaz+0.004
 Equity+0.004
Neg logit contributions
ipal-0.004
init-0.004
shift-0.004
actory-0.004
ounge-0.004
Token of
Token ID286
Feature activation-5.72e-01

Pos logit contributions
 Dent+3.865
 Nadu+3.626
 Devi+3.614
 Benefit+3.393
 Equity+3.373
Neg logit contributions
ipal-3.492
init-3.424
actory-3.263
shift-3.224
ounge-3.167
Token this
Token ID428
Feature activation+3.63e-01

Pos logit contributions
 Dent+0.419
 Nadu+0.402
 Devi+0.390
iaz+0.362
 Equity+0.362
Neg logit contributions
ipal-0.438
init-0.432
shift-0.410
actory-0.409
ounge-0.396
Token new
Token ID649
Feature activation+8.30e-01

Pos logit contributions
ipal+0.240
init+0.237
shift+0.225
actory+0.222
ounge+0.213
Neg logit contributions
 Dent-0.302
 Nadu-0.292
 Devi-0.284
iaz-0.267
 Equity-0.265
Token release
Token ID2650
Feature activation+5.44e-01

Pos logit contributions
ipal+0.561
init+0.556
shift+0.527
actory+0.522
ounge+0.501
Neg logit contributions
 Dent-0.677
 Nadu-0.652
 Devi-0.635
iaz-0.594
 Equity-0.593
Token,
Token ID11
Feature activation-7.38e-02

Pos logit contributions
ipal+0.345
init+0.339
shift+0.320
actory+0.316
ounge+0.305
Neg logit contributions
 Dent-0.470
 Nadu-0.452
 Devi-0.442
 Equity-0.415
iaz-0.415
Token subway
Token ID19612
Feature activation-9.75e-01

Pos logit contributions
 Dent+0.160
 Nadu+0.154
 Devi+0.150
 Equity+0.139
iaz+0.139
Neg logit contributions
ipal-0.161
init-0.159
shift-0.152
actory-0.150
ounge-0.146
Token gr
Token ID1036
Feature activation+1.00e-01

Pos logit contributions
 Dent+0.814
 Nadu+0.781
 Devi+0.765
 Equity+0.718
 Benefit+0.715
Neg logit contributions
ipal-0.650
init-0.638
shift-0.601
actory-0.600
ounge-0.580
Tokenates
Token ID689
Feature activation+3.54e-01

Pos logit contributions
ipal+0.078
init+0.077
shift+0.073
actory+0.073
ounge+0.071
Neg logit contributions
 Dent-0.073
 Nadu-0.069
 Devi-0.068
 Equity-0.063
 Benefit-0.062
Token or
Token ID393
Feature activation+2.41e-01

Pos logit contributions
ipal+0.244
init+0.241
shift+0.228
actory+0.226
ounge+0.219
Neg logit contributions
 Dent-0.287
 Nadu-0.276
 Devi-0.270
 Equity-0.253
 Benefit-0.251
Token on
Token ID319
Feature activation+8.43e-02

Pos logit contributions
ipal+0.165
init+0.163
shift+0.155
actory+0.153
ounge+0.148
Neg logit contributions
 Dent-0.195
 Nadu-0.188
 Devi-0.184
 Equity-0.172
iaz-0.172
Token sto
Token ID3995
Feature activation-4.85e+00

Pos logit contributions
ipal+0.061
init+0.060
shift+0.057
actory+0.056
ounge+0.055
Neg logit contributions
 Dent-0.066
 Nadu-0.063
 Devi-0.062
 Equity-0.057
iaz-0.057
Tokenops
Token ID2840
Feature activation-2.55e-01

Pos logit contributions
 Dent+3.293
 Nadu+3.111
 Devi+3.060
iaz+2.816
 Benefit+2.798
Neg logit contributions
ipal-3.892
init-3.783
shift-3.669
actory-3.657
itual-3.519
Token or
Token ID393
Feature activation+1.47e-01

Pos logit contributions
 Dent+0.206
 Nadu+0.198
 Devi+0.193
 Equity+0.181
 Benefit+0.180
Neg logit contributions
ipal-0.177
init-0.174
shift-0.164
actory-0.163
ounge-0.158
Token in
Token ID287
Feature activation-1.76e-01

Pos logit contributions
ipal+0.099
init+0.097
shift+0.092
actory+0.092
ounge+0.089
Neg logit contributions
 Dent-0.121
 Nadu-0.116
 Devi-0.114
 Equity-0.106
 Benefit-0.106
Token encamp
Token ID48020
Feature activation-1.30e+00

Pos logit contributions
 Dent+0.139
 Nadu+0.134
 Devi+0.131
 Equity+0.122
 Benefit+0.122
Neg logit contributions
ipal-0.125
init-0.123
shift-0.116
actory-0.116
ounge-0.112
Tokenments
Token ID902
Feature activation-1.09e+00

Pos logit contributions
 Dent+0.899
 Nadu+0.856
 Devi+0.836
 Equity+0.767
 Benefit+0.765
Neg logit contributions
ipal-1.058
init-1.048
actory-0.998
shift-0.998
ounge-0.966
Token
Token ID119
Feature activation-1.35e-01

Pos logit contributions
 Dent+0.104
 Nadu+0.100
 Devi+0.098
 Benefit+0.093
 Equity+0.093
Neg logit contributions
ipal-0.062
init-0.061
actory-0.056
shift-0.056
itual-0.053
Tokeno
Token ID78
Feature activation-5.07e-01

Pos logit contributions
 Dent+0.098
 Nadu+0.093
 Devi+0.091
 Equity+0.085
 Benefit+0.084
Neg logit contributions
ipal-0.105
init-0.103
shift-0.098
actory-0.098
ounge-0.095
Token Hal
Token ID11023
Feature activation+6.42e-01

Pos logit contributions
 Dent+0.380
 Nadu+0.363
 Devi+0.355
 Equity+0.330
 Benefit+0.329
Neg logit contributions
ipal-0.381
init-0.375
shift-0.356
actory-0.355
ounge-0.344
Tokenep
Token ID538
Feature activation+1.91e-01

Pos logit contributions
ipal+0.534
init+0.526
shift+0.502
actory+0.501
ounge+0.488
Neg logit contributions
 Dent-0.429
 Nadu-0.408
 Devi-0.397
 Equity-0.366
 Benefit-0.364
Tokenā
Token ID10235
Feature activation+4.61e-01

Pos logit contributions
ipal+0.134
init+0.132
shift+0.125
actory+0.124
ounge+0.120
Neg logit contributions
 Dent-0.152
 Nadu-0.146
 Devi-0.142
 Equity-0.133
 Benefit-0.133
Tokennih
Token ID37373
Feature activation-4.84e+00

Pos logit contributions
ipal+0.337
init+0.332
shift+0.314
actory+0.313
ounge+0.304
Neg logit contributions
 Dent-0.357
 Nadu-0.340
 Devi-0.333
 Equity-0.311
 Benefit-0.309
Tokeno
Token ID78
Feature activation-9.91e-01

Pos logit contributions
 Dent+3.932
 Nadu+3.824
 Devi+3.748
iaz+3.542
ouri+3.514
Neg logit contributions
ipal-3.129
init-3.051
shift-2.964
actory-2.934
itual-2.839
Token m
Token ID285
Feature activation-1.55e+00

Pos logit contributions
 Dent+0.760
 Nadu+0.728
 Devi+0.711
 Equity+0.662
 Benefit+0.660
Neg logit contributions
ipal-0.727
init-0.714
shift-0.678
actory-0.677
ounge-0.656
Tokenai
Token ID1872
Feature activation+1.22e+00

Pos logit contributions
 Dent+1.356
 Nadu+1.307
 Devi+1.280
 Equity+1.202
iaz+1.201
Neg logit contributions
ipal-0.967
init-0.947
shift-0.892
actory-0.890
ounge-0.858
Token,
Token ID11
Feature activation-4.29e-01

Pos logit contributions
ipal+0.907
init+0.896
shift+0.840
actory+0.838
ounge+0.815
Neg logit contributions
 Dent-0.932
 Nadu-0.883
 Devi-0.869
 Equity-0.811
 Benefit-0.806
Token n
Token ID299
Feature activation-9.86e-01

Pos logit contributions
 Dent+0.318
 Nadu+0.303
 Devi+0.297
 Equity+0.276
 Benefit+0.274
Neg logit contributions
ipal-0.327
init-0.321
shift-0.304
actory-0.303
ounge-0.295
Token announced
Token ID3414
Feature activation+5.35e-01

Pos logit contributions
 Dent+0.438
 Nadu+0.421
 Devi+0.410
iaz+0.383
 Benefit+0.381
Neg logit contributions
ipal-0.389
init-0.383
shift-0.361
actory-0.358
ounge-0.347
Token an
Token ID281
Feature activation-6.23e-01

Pos logit contributions
ipal+0.402
init+0.394
shift+0.374
actory+0.373
ounge+0.361
Neg logit contributions
 Dent-0.401
 Nadu-0.385
 Devi-0.375
iaz-0.347
 Equity-0.347
Token alliance
Token ID12801
Feature activation-1.47e+00

Pos logit contributions
 Dent+0.474
 Nadu+0.450
 Devi+0.441
 Benefit+0.409
iaz+0.408
Neg logit contributions
ipal-0.466
init-0.459
shift-0.430
actory-0.429
ounge-0.419
Token with
Token ID351
Feature activation-4.43e-02

Pos logit contributions
 Dent+1.108
 Nadu+1.062
 Devi+1.036
 Equity+0.979
 Benefit+0.972
Neg logit contributions
ipal-1.083
init-1.057
shift-1.008
actory-0.996
itual-0.984
Token B
Token ID347
Feature activation+9.66e-02

Pos logit contributions
 Dent+0.030
 Nadu+0.029
 Devi+0.028
iaz+0.026
 Equity+0.026
Neg logit contributions
ipal-0.036
init-0.035
actory-0.033
shift-0.033
ounge-0.032
Tokenibli
Token ID29142
Feature activation-4.75e+00

Pos logit contributions
ipal+0.068
init+0.067
shift+0.063
actory+0.063
ounge+0.061
Neg logit contributions
 Dent-0.077
 Nadu-0.074
 Devi-0.073
 Equity-0.068
 Benefit-0.068
Tokenothe
Token ID20388
Feature activation-1.16e+00

Pos logit contributions
 Dent+3.096
 Nadu+2.928
 Devi+2.859
 Equity+2.649
 Benefit+2.646
Neg logit contributions
ipal-3.972
init-3.882
shift-3.733
actory-3.696
ounge-3.625
Tokenca
Token ID6888
Feature activation+1.40e-01

Pos logit contributions
 Dent+0.933
 Nadu+0.899
 Devi+0.878
 Equity+0.820
 Benefit+0.814
Neg logit contributions
ipal-0.807
init-0.795
shift-0.753
actory-0.749
ounge-0.722
Token to
Token ID284
Feature activation-2.36e-01

Pos logit contributions
ipal+0.109
init+0.107
shift+0.102
actory+0.101
ounge+0.098
Neg logit contributions
 Dent-0.100
 Nadu-0.097
 Devi-0.093
iaz-0.086
 Equity-0.086
Token directly
Token ID3264
Feature activation-2.70e+00

Pos logit contributions
 Dent+0.185
 Nadu+0.179
 Devi+0.174
 Equity+0.161
iaz+0.160
Neg logit contributions
ipal-0.168
init-0.166
shift-0.157
actory-0.156
ounge-0.150
Token sell
Token ID3677
Feature activation-6.41e-01

Pos logit contributions
 Dent+2.078
 Nadu+1.990
 Devi+1.947
 Equity+1.806
 Benefit+1.794
Neg logit contributions
ipal-1.976
init-1.946
shift-1.847
actory-1.840
ounge-1.781
Token Hillary
Token ID5073
Feature activation-1.45e+00

Pos logit contributions
 Dent+0.272
 Nadu+0.264
 Devi+0.254
iaz+0.237
 Equity+0.237
Neg logit contributions
ipal-0.272
init-0.269
shift-0.256
actory-0.254
ounge-0.246
Token Clinton
Token ID2605
Feature activation-2.96e-01

Pos logit contributions
 Dent+1.078
 Nadu+1.029
 Devi+1.006
 Equity+0.934
 Benefit+0.931
Neg logit contributions
ipal-1.097
init-1.079
shift-1.025
actory-1.023
ounge-0.994
Token
Token ID851
Feature activation-3.56e-01

Pos logit contributions
 Dent+0.232
 Nadu+0.222
 Devi+0.217
 Equity+0.203
 Benefit+0.202
Neg logit contributions
ipal-0.211
init-0.208
shift-0.197
actory-0.196
ounge-0.190
Token and
Token ID290
Feature activation+7.50e-02

Pos logit contributions
 Dent+0.273
 Nadu+0.262
 Devi+0.255
 Equity+0.238
iaz+0.238
Neg logit contributions
ipal-0.260
init-0.257
shift-0.243
actory-0.242
ounge-0.234
Token were
Token ID547
Feature activation+2.21e-02

Pos logit contributions
ipal+0.055
init+0.055
shift+0.052
actory+0.052
ounge+0.050
Neg logit contributions
 Dent-0.056
 Nadu-0.054
 Devi-0.052
iaz-0.049
 Equity-0.049
Token silenced
Token ID38086
Feature activation-4.73e+00

Pos logit contributions
ipal+0.015
init+0.015
shift+0.015
actory+0.014
ounge+0.014
Neg logit contributions
 Dent-0.017
 Nadu-0.017
 Devi-0.016
 Equity-0.015
iaz-0.015
Token.
Token ID13
Feature activation-9.14e-02

Pos logit contributions
 Dent+3.590
 Nadu+3.420
 Devi+3.359
 Equity+3.105
 Benefit+3.092
Neg logit contributions
ipal-3.448
init-3.362
shift-3.218
actory-3.203
ounge-3.152
Token 1
Token ID352
Feature activation+1.98e-01

Pos logit contributions
 Dent+0.063
 Nadu+0.061
 Devi+0.058
iaz+0.056
ouri+0.054
Neg logit contributions
ipal-0.072
init-0.072
shift-0.068
actory-0.067
itual-0.065
Token:
Token ID25
Feature activation+2.92e-01

Pos logit contributions
ipal+0.141
init+0.139
shift+0.132
actory+0.131
ounge+0.126
Neg logit contributions
 Dent-0.155
 Nadu-0.149
 Devi-0.145
 Equity-0.136
 Benefit-0.135
Token You
Token ID921
Feature activation-7.95e-03

Pos logit contributions
ipal+0.162
init+0.161
shift+0.150
actory+0.148
itual+0.141
Neg logit contributions
 Dent-0.272
 Nadu-0.266
 Devi-0.259
iaz-0.246
 Equity-0.244
Token have
Token ID423
Feature activation+3.57e-01

Pos logit contributions
 Dent+0.006
 Nadu+0.006
 Devi+0.006
 Equity+0.005
iaz+0.005
Neg logit contributions
ipal-0.006
init-0.006
shift-0.005
actory-0.005
itual-0.005
Token called
Token ID1444
Feature activation-1.79e-01

Pos logit contributions
ipal+0.227
init+0.224
shift+0.211
actory+0.210
itual+0.201
Neg logit contributions
 Dent-0.277
 Nadu-0.265
 Devi-0.259
 Equity-0.244
iaz-0.243
Token by
Token ID416
Feature activation-2.78e-01

Pos logit contributions
 Dent+0.141
 Nadu+0.134
 Devi+0.131
iaz+0.123
 Benefit+0.123
Neg logit contributions
ipal-0.128
init-0.126
shift-0.119
actory-0.119
itual-0.114
Token Chief
Token ID5953
Feature activation-1.68e+00

Pos logit contributions
 Dent+0.187
 Nadu+0.177
 Devi+0.172
iaz+0.160
 Benefit+0.160
Neg logit contributions
ipal-0.231
init-0.226
shift-0.215
actory-0.215
ounge-0.208
Token Minister
Token ID4139
Feature activation-1.48e+00

Pos logit contributions
 Dent+0.935
 Nadu+0.879
 Devi+0.849
iaz+0.765
 Equity+0.765
Neg logit contributions
ipal-1.585
init-1.559
shift-1.497
actory-1.495
ounge-1.458
Token Ar
Token ID943
Feature activation-1.30e-01

Pos logit contributions
 Dent+0.840
 Nadu+0.794
 Devi+0.766
 Equity+0.695
 Benefit+0.693
Neg logit contributions
ipal-1.389
init-1.368
actory-1.309
shift-1.309
ounge-1.275
Tokenvind
Token ID50172
Feature activation-4.61e+00

Pos logit contributions
 Dent+0.099
 Nadu+0.096
 Devi+0.092
iaz+0.087
 Equity+0.086
Neg logit contributions
ipal-0.097
init-0.095
shift-0.091
actory-0.089
ounge-0.086
Token Kejriwal
Token ID42792
Feature activation-1.91e+00

Pos logit contributions
 Dent+1.496
 Nadu+1.341
 Devi+1.266
 Equity+1.038
 Benefit+1.025
Neg logit contributions
ipal-5.430
init-5.370
shift-5.196
actory-5.190
ounge-5.104
Token.
Token ID13
Feature activation-8.20e-01

Pos logit contributions
 Dent+1.516
 Nadu+1.452
 Devi+1.421
 Equity+1.327
 Benefit+1.323
Neg logit contributions
ipal-1.354
init-1.330
shift-1.258
actory-1.256
ounge-1.217
Token
Token ID198
Feature activation-5.11e-01

Pos logit contributions
 Dent+0.558
 Nadu+0.532
 Devi+0.517
iaz+0.479
 Equity+0.477
Neg logit contributions
ipal-0.669
init-0.660
shift-0.628
actory-0.625
ounge-0.607
Token
Token ID198
Feature activation-5.55e-01

Pos logit contributions
 Dent+0.437
 Nadu+0.424
 Devi+0.413
iaz+0.389
 Equity+0.386
Neg logit contributions
init-0.330
ipal-0.325
shift-0.310
actory-0.302
photo-0.290
Token"
Token ID1
Feature activation-1.71e+00

Pos logit contributions
 Dent+0.467
 Nadu+0.448
 Devi+0.440
 Equity+0.412
 Benefit+0.411
Neg logit contributions
ipal-0.366
init-0.360
shift-0.339
actory-0.337
ounge-0.326
Token invent
Token ID8067
Feature activation-4.48e+00

Pos logit contributions
 Dent+0.651
 Nadu+0.627
 Devi+0.614
 Equity+0.578
 Benefit+0.576
Neg logit contributions
ipal-0.449
init-0.440
shift-0.413
actory-0.412
ounge-0.396
Tokenories
Token ID1749
Feature activation+2.34e-01

Pos logit contributions
 Dent+1.319
 Nadu+1.191
 Devi+1.149
iaz+0.917
 Equity+0.911
Neg logit contributions
ipal-5.278
init-5.232
shift-5.072
actory-5.037
itual-5.004
Token,
Token ID11
Feature activation-4.39e-01

Pos logit contributions
ipal+0.161
init+0.159
shift+0.150
actory+0.149
ounge+0.145
Neg logit contributions
 Dent-0.189
 Nadu-0.181
 Devi-0.177
 Equity-0.166
 Benefit-0.165
Token two
Token ID734
Feature activation-6.79e-02

Pos logit contributions
 Dent+0.340
 Nadu+0.325
 Devi+0.318
 Equity+0.296
 Benefit+0.295
Neg logit contributions
ipal-0.319
init-0.314
shift-0.298
actory-0.297
ounge-0.288
Token product
Token ID1720
Feature activation+6.02e-01

Pos logit contributions
 Dent+0.057
 Nadu+0.055
 Devi+0.054
 Equity+0.050
 Benefit+0.050
Neg logit contributions
ipal-0.045
init-0.044
shift-0.042
actory-0.041
ounge-0.040
Token catalog
Token ID18388
Feature activation-4.58e+00

Pos logit contributions
ipal+0.381
init+0.376
shift+0.353
actory+0.351
ounge+0.339
Neg logit contributions
 Dent-0.522
 Nadu-0.501
 Devi-0.491
 Equity-0.460
 Benefit-0.459
Tokens
Token ID82
Feature activation-5.00e-01

Pos logit contributions
 Dent+2.740
 Nadu+2.582
 Devi+2.517
 Equity+2.284
 Benefit+2.279
Neg logit contributions
ipal-4.086
init-4.009
actory-3.852
shift-3.837
itual-3.768
Token,
Token ID11
Feature activation-5.11e-01

Pos logit contributions
 Dent+0.388
 Nadu+0.371
 Devi+0.364
 Equity+0.339
 Benefit+0.338
Neg logit contributions
ipal-0.363
init-0.356
actory-0.337
shift-0.337
itual-0.326
Token and
Token ID290
Feature activation-3.33e-01

Pos logit contributions
 Dent+0.398
 Nadu+0.381
 Devi+0.373
 Equity+0.348
 Benefit+0.346
Neg logit contributions
ipal-0.369
init-0.362
shift-0.344
actory-0.343
ounge-0.332
Token two
Token ID734
Feature activation+1.56e-01

Pos logit contributions
 Dent+0.262
 Nadu+0.251
 Devi+0.245
 Equity+0.228
 Benefit+0.228
Neg logit contributions
ipal-0.238
init-0.234
shift-0.222
actory-0.221
ounge-0.214
Token payment
Token ID6074
Feature activation+1.20e-01

Pos logit contributions
ipal+0.102
init+0.100
shift+0.094
actory+0.094
ounge+0.091
Neg logit contributions
 Dent-0.132
 Nadu-0.127
 Devi-0.124
 Equity-0.116
iaz-0.116
Token track
Token ID2610
Feature activation-1.39e-01

Pos logit contributions
ipal+1.247
init+1.221
shift+1.159
actory+1.141
ounge+1.097
Neg logit contributions
 Dent-1.810
 Nadu-1.731
 Devi-1.690
 Equity-1.602
iaz-1.601
Token of
Token ID286
Feature activation-4.07e-01

Pos logit contributions
 Dent+0.105
 Nadu+0.100
 Devi+0.099
iaz+0.092
 Benefit+0.092
Neg logit contributions
ipal-0.103
init-0.101
actory-0.095
shift-0.095
itual-0.093
Token two
Token ID734
Feature activation-1.39e-02

Pos logit contributions
 Dent+0.324
 Nadu+0.310
 Devi+0.303
 Equity+0.283
 Benefit+0.282
Neg logit contributions
ipal-0.287
init-0.282
shift-0.267
actory-0.266
ounge-0.258
Token sets
Token ID5621
Feature activation-5.42e-01

Pos logit contributions
 Dent+0.011
 Nadu+0.011
 Devi+0.011
 Equity+0.010
 Benefit+0.010
Neg logit contributions
ipal-0.010
init-0.009
shift-0.009
actory-0.009
ounge-0.009
Token of
Token ID286
Feature activation-7.33e-01

Pos logit contributions
 Dent+0.453
 Nadu+0.435
 Devi+0.426
 Equity+0.398
 Benefit+0.398
Neg logit contributions
ipal-0.362
init-0.357
shift-0.338
actory-0.334
ounge-0.323
Token invent
Token ID8067
Feature activation-4.48e+00

Pos logit contributions
 Dent+0.651
 Nadu+0.627
 Devi+0.614
 Equity+0.578
 Benefit+0.576
Neg logit contributions
ipal-0.449
init-0.440
shift-0.413
actory-0.412
ounge-0.396
Tokenories
Token ID1749
Feature activation+2.34e-01

Pos logit contributions
 Dent+1.319
 Nadu+1.191
 Devi+1.149
iaz+0.917
 Equity+0.911
Neg logit contributions
ipal-5.278
init-5.232
shift-5.072
actory-5.037
itual-5.004
Token,
Token ID11
Feature activation-4.39e-01

Pos logit contributions
ipal+0.161
init+0.159
shift+0.150
actory+0.149
ounge+0.145
Neg logit contributions
 Dent-0.189
 Nadu-0.181
 Devi-0.177
 Equity-0.166
 Benefit-0.165
Token two
Token ID734
Feature activation-6.79e-02

Pos logit contributions
 Dent+0.340
 Nadu+0.325
 Devi+0.318
 Equity+0.296
 Benefit+0.295
Neg logit contributions
ipal-0.319
init-0.314
shift-0.298
actory-0.297
ounge-0.288
Token product
Token ID1720
Feature activation+6.02e-01

Pos logit contributions
 Dent+0.057
 Nadu+0.055
 Devi+0.054
 Equity+0.050
 Benefit+0.050
Neg logit contributions
ipal-0.045
init-0.044
shift-0.042
actory-0.041
ounge-0.040
Token catalog
Token ID18388
Feature activation-4.58e+00

Pos logit contributions
ipal+0.381
init+0.376
shift+0.353
actory+0.351
ounge+0.339
Neg logit contributions
 Dent-0.522
 Nadu-0.501
 Devi-0.491
 Equity-0.460
 Benefit-0.459
Token Greenland
Token ID30155
Feature activation-3.69e-01

Pos logit contributions
 Dent+0.636
 Nadu+0.609
 Devi+0.596
 Equity+0.555
 Benefit+0.554
Neg logit contributions
ipal-0.588
init-0.578
shift-0.547
actory-0.546
ounge-0.530
Token
Token ID447
Feature activation+2.84e-01

Pos logit contributions
 Dent+0.269
 Nadu+0.258
 Devi+0.251
 Equity+0.231
 Benefit+0.231
Neg logit contributions
ipal-0.283
init-0.279
shift-0.266
actory-0.265
ounge-0.259
Token
Token ID247
Feature activation-2.77e-01

Pos logit contributions
ipal+0.204
init+0.200
actory+0.190
shift+0.187
ounge+0.181
Neg logit contributions
 Dent-0.224
 Nadu-0.214
 Devi-0.211
 Equity-0.196
 Benefit-0.194
Tokens
Token ID82
Feature activation+6.28e-02

Pos logit contributions
 Dent+0.201
 Nadu+0.190
 Devi+0.189
 Equity+0.173
iaz+0.171
Neg logit contributions
init-0.219
ipal-0.218
shift-0.208
actory-0.205
itual-0.198
Token ice
Token ID4771
Feature activation-6.24e-01

Pos logit contributions
ipal+0.043
init+0.042
shift+0.040
actory+0.040
ounge+0.038
Neg logit contributions
 Dent-0.051
 Nadu-0.049
 Devi-0.048
 Equity-0.045
 Benefit-0.045
Token sheet
Token ID9629
Feature activation-4.47e+00

Pos logit contributions
 Dent+0.383
 Nadu+0.362
 Devi+0.351
 Equity+0.321
 Benefit+0.320
Neg logit contributions
ipal-0.554
init-0.546
shift-0.523
actory-0.522
ounge-0.509
Token to
Token ID284
Feature activation+8.26e-02

Pos logit contributions
 Dent+3.001
 Nadu+2.955
 Devi+2.814
 Benefit+2.560
 Equity+2.555
Neg logit contributions
ipal-3.619
init-3.529
actory-3.409
shift-3.349
itual-3.331
Token start
Token ID923
Feature activation-2.79e-01

Pos logit contributions
ipal+0.056
init+0.055
shift+0.053
actory+0.052
ounge+0.050
Neg logit contributions
 Dent-0.068
 Nadu-0.065
 Devi-0.064
 Equity-0.060
 Benefit-0.059
Token losing
Token ID6078
Feature activation+1.12e+00

Pos logit contributions
 Dent+0.224
 Nadu+0.215
 Devi+0.210
 Equity+0.196
 Benefit+0.196
Neg logit contributions
ipal-0.195
init-0.192
shift-0.181
actory-0.181
ounge-0.175
Token more
Token ID517
Feature activation+1.12e-01

Pos logit contributions
ipal+0.702
init+0.691
shift+0.650
actory+0.645
ounge+0.616
Neg logit contributions
 Dent-0.969
 Nadu-0.933
 Devi-0.913
 Equity-0.862
iaz-0.860
Token ice
Token ID4771
Feature activation-9.77e-01

Pos logit contributions
ipal+0.069
init+0.068
shift+0.064
actory+0.064
ounge+0.061
Neg logit contributions
 Dent-0.098
 Nadu-0.095
 Devi-0.093
 Equity-0.087
 Benefit-0.087
Token ice
Token ID4771
Feature activation-3.45e-01

Pos logit contributions
 Dent+0.856
 Nadu+0.820
 Devi+0.803
 Equity+0.752
 Benefit+0.749
Neg logit contributions
ipal-0.725
init-0.712
shift-0.672
actory-0.671
ounge-0.649
Token from
Token ID422
Feature activation-5.04e-01

Pos logit contributions
 Dent+0.284
 Nadu+0.271
 Devi+0.266
 Equity+0.250
iaz+0.249
Neg logit contributions
ipal-0.233
init-0.230
shift-0.217
actory-0.216
itual-0.208
Token the
Token ID262
Feature activation+3.07e-01

Pos logit contributions
 Dent+0.386
 Nadu+0.369
 Devi+0.360
 Equity+0.336
 Benefit+0.335
Neg logit contributions
ipal-0.371
init-0.365
shift-0.346
actory-0.345
ounge-0.334
Token central
Token ID4318
Feature activation+1.65e+00

Pos logit contributions
ipal+0.204
init+0.203
shift+0.191
actory+0.190
ounge+0.182
Neg logit contributions
 Dent-0.253
 Nadu-0.242
 Devi-0.237
 Equity-0.224
iaz-0.223
Token ice
Token ID4771
Feature activation-5.54e-01

Pos logit contributions
ipal+1.103
init+1.097
shift+1.038
actory+1.024
ounge+0.986
Neg logit contributions
 Dent-1.349
 Nadu-1.289
 Devi-1.264
 Equity-1.186
iaz-1.186
Token sheet
Token ID9629
Feature activation-4.43e+00

Pos logit contributions
 Dent+0.272
 Nadu+0.252
 Devi+0.244
 Equity+0.218
 Benefit+0.215
Neg logit contributions
ipal-0.559
init-0.556
shift-0.536
actory-0.531
ounge-0.519
Token;
Token ID26
Feature activation+5.14e-01

Pos logit contributions
 Dent+3.354
 Nadu+3.214
 Devi+3.146
 Benefit+2.903
 Equity+2.892
Neg logit contributions
ipal-3.257
init-3.174
actory-3.031
shift-3.010
ounge-2.960
Token but
Token ID475
Feature activation-4.97e-01

Pos logit contributions
ipal+0.368
init+0.364
shift+0.345
actory+0.342
itual+0.330
Neg logit contributions
 Dent-0.401
 Nadu-0.383
 Devi-0.374
iaz-0.352
 Equity-0.352
Token even
Token ID772
Feature activation+6.92e-02

Pos logit contributions
 Dent+0.386
 Nadu+0.369
 Devi+0.361
 Equity+0.338
iaz+0.336
Neg logit contributions
ipal-0.359
init-0.354
shift-0.336
actory-0.334
itual-0.322
Token in
Token ID287
Feature activation+1.18e-01

Pos logit contributions
ipal+0.049
init+0.048
shift+0.045
actory+0.045
itual+0.043
Neg logit contributions
 Dent-0.055
 Nadu-0.052
 Devi-0.051
iaz-0.048
 Equity-0.048
Token a
Token ID257
Feature activation-5.46e-02

Pos logit contributions
ipal+0.088
init+0.087
shift+0.082
actory+0.082
itual+0.079
Neg logit contributions
 Dent-0.089
 Nadu-0.085
 Devi-0.083
 Equity-0.078
iaz-0.077
Token refused
Token ID6520
Feature activation+1.96e-01

Pos logit contributions
 Dent+0.083
 Nadu+0.080
 Devi+0.079
 Equity+0.074
iaz+0.074
Neg logit contributions
ipal-0.064
init-0.063
shift-0.059
actory-0.059
ounge-0.057
Token one
Token ID530
Feature activation-4.24e-01

Pos logit contributions
ipal+0.149
init+0.147
shift+0.140
actory+0.139
itual+0.135
Neg logit contributions
 Dent-0.144
 Nadu-0.139
 Devi-0.136
iaz-0.125
 Equity-0.125
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
 Dent+0.341
 Nadu+0.327
 Devi+0.320
 Equity+0.299
 Benefit+0.298
Neg logit contributions
ipal-0.295
init-0.290
shift-0.274
actory-0.273
ounge-0.264
Token From
Token ID3574
Feature activation-1.06e+00

Pos logit contributions
 Dent+0.140
 Nadu+0.137
 Devi+0.132
iaz+0.124
 Benefit+0.120
Neg logit contributions
ipal-0.165
init-0.164
shift-0.156
actory-0.154
itual-0.150
Token Ed
Token ID1717
Feature activation+9.70e-01

Pos logit contributions
 Dent+0.790
 Nadu+0.760
 Devi+0.742
 Equity+0.686
iaz+0.686
Neg logit contributions
ipal-0.790
init-0.781
shift-0.742
actory-0.738
ounge-0.713
Token Koch
Token ID17009
Feature activation-4.40e+00

Pos logit contributions
ipal+0.766
init+0.762
shift+0.719
actory+0.715
itual+0.691
Neg logit contributions
 Dent-0.684
 Nadu-0.660
 Devi-0.644
 Equity-0.592
 Benefit-0.589
Token on
Token ID319
Feature activation+2.84e-03

Pos logit contributions
 Dent+3.326
 Nadu+3.158
 Devi+3.080
 Equity+2.887
iaz+2.874
Neg logit contributions
ipal-3.226
init-3.178
actory-3.024
shift-3.011
ounge-2.950
Token down
Token ID866
Feature activation-6.51e-01

Pos logit contributions
ipal+0.002
init+0.002
shift+0.002
actory+0.002
ounge+0.002
Neg logit contributions
 Dent-0.002
 Nadu-0.002
 Devi-0.002
 Equity-0.002
 Benefit-0.002
Token,
Token ID11
Feature activation-6.31e-02

Pos logit contributions
 Dent+0.501
 Nadu+0.479
 Devi+0.465
 Equity+0.436
 Benefit+0.434
Neg logit contributions
ipal-0.477
init-0.468
actory-0.445
shift-0.441
ounge-0.433
Token every
Token ID790
Feature activation+7.55e-01

Pos logit contributions
 Dent+0.047
 Nadu+0.045
 Devi+0.044
iaz+0.041
 Equity+0.041
Neg logit contributions
ipal-0.047
init-0.047
shift-0.044
actory-0.044
itual-0.043
Token mayor
Token ID9591
Feature activation-1.71e+00

Pos logit contributions
ipal+0.530
init+0.522
shift+0.498
actory+0.491
ounge+0.471
Neg logit contributions
 Dent-0.596
 Nadu-0.577
 Devi-0.563
 Equity-0.522
 Benefit-0.520
Token the
Token ID262
Feature activation-4.04e-02

Pos logit contributions
 Dent+0.114
 Nadu+0.110
 Devi+0.107
 Equity+0.099
iaz+0.098
Neg logit contributions
ipal-0.127
init-0.125
shift-0.119
actory-0.119
ounge-0.116
Token new
Token ID649
Feature activation+1.10e+00

Pos logit contributions
 Dent+0.030
 Nadu+0.029
 Devi+0.029
iaz+0.026
 Equity+0.026
Neg logit contributions
ipal-0.030
init-0.030
shift-0.028
actory-0.028
ounge-0.027
Token search
Token ID2989
Feature activation-2.39e+00

Pos logit contributions
ipal+0.805
init+0.800
shift+0.756
actory+0.747
ounge+0.731
Neg logit contributions
 Dent-0.842
 Nadu-0.810
 Devi-0.792
iaz-0.731
 Benefit-0.728
Token deal
Token ID1730
Feature activation-1.10e+00

Pos logit contributions
 Dent+1.948
 Nadu+1.870
 Devi+1.828
 Equity+1.729
 Benefit+1.721
Neg logit contributions
ipal-1.625
init-1.586
actory-1.506
shift-1.501
itual-1.454
Token with
Token ID351
Feature activation-6.49e-03

Pos logit contributions
 Dent+0.893
 Nadu+0.856
 Devi+0.840
 Equity+0.784
 Benefit+0.780
Neg logit contributions
ipal-0.760
init-0.750
shift-0.709
actory-0.705
ounge-0.683
Token Google
Token ID3012
Feature activation-4.39e+00

Pos logit contributions
 Dent+0.005
 Nadu+0.005
 Devi+0.004
iaz+0.004
 Equity+0.004
Neg logit contributions
ipal-0.005
init-0.005
shift-0.005
actory-0.005
ounge-0.004
Token aren
Token ID3588
Feature activation+5.42e-01

Pos logit contributions
 Dent+3.451
 Nadu+3.308
 Devi+3.217
 Equity+3.028
 Benefit+3.028
Neg logit contributions
ipal-3.130
init-3.057
actory-2.900
shift-2.895
itual-2.810
Token't
Token ID470
Feature activation+1.48e-01

Pos logit contributions
init+0.243
ipal+0.239
shift+0.221
actory+0.215
itual+0.198
Neg logit contributions
 Dent-0.575
 Nadu-0.558
 Devi-0.553
 Equity-0.521
iaz-0.518
Token yet
Token ID1865
Feature activation+2.57e-01

Pos logit contributions
ipal+0.099
init+0.098
actory+0.093
shift+0.092
ounge+0.089
Neg logit contributions
 Dent-0.122
 Nadu-0.117
 Devi-0.115
iaz-0.108
 Equity-0.107
Token clear
Token ID1598
Feature activation+3.10e-01

Pos logit contributions
ipal+0.164
init+0.162
actory+0.154
shift+0.152
ounge+0.147
Neg logit contributions
 Dent-0.219
 Nadu-0.211
 Devi-0.206
 Benefit-0.194
 Equity-0.194
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
ipal+0.218
init+0.214
shift+0.202
actory+0.202
ounge+0.196
Neg logit contributions
 Dent-0.247
 Nadu-0.237
 Devi-0.232
 Equity-0.217
 Benefit-0.216
Token a
Token ID257
Feature activation-6.01e-01

Pos logit contributions
 Dent+0.724
 Nadu+0.691
 Devi+0.676
 Equity+0.627
 Benefit+0.624
Neg logit contributions
ipal-0.747
init-0.735
shift-0.699
actory-0.695
ounge-0.675
Token loophole
Token ID35723
Feature activation-1.81e+00

Pos logit contributions
 Dent+0.502
 Nadu+0.482
 Devi+0.472
 Equity+0.442
iaz+0.440
Neg logit contributions
ipal-0.400
init-0.392
shift-0.372
actory-0.369
ounge-0.356
Token that
Token ID326
Feature activation-5.13e-01

Pos logit contributions
 Dent+1.404
 Nadu+1.344
 Devi+1.314
 Equity+1.225
 Benefit+1.221
Neg logit contributions
ipal-1.312
init-1.290
shift-1.222
actory-1.220
ounge-1.183
Token could
Token ID714
Feature activation-5.15e-01

Pos logit contributions
 Dent+0.408
 Nadu+0.390
 Devi+0.382
 Equity+0.357
iaz+0.356
Neg logit contributions
ipal-0.359
init-0.355
shift-0.337
actory-0.334
ounge-0.323
Token guarantee
Token ID9149
Feature activation-9.25e-01

Pos logit contributions
 Dent+0.412
 Nadu+0.395
 Devi+0.387
 Equity+0.362
iaz+0.358
Neg logit contributions
ipal-0.359
init-0.354
shift-0.337
actory-0.334
ounge-0.322
Token fossil
Token ID12584
Feature activation-4.35e+00

Pos logit contributions
 Dent+0.712
 Nadu+0.681
 Devi+0.666
 Equity+0.621
 Benefit+0.619
Neg logit contributions
ipal-0.677
init-0.665
shift-0.631
actory-0.629
ounge-0.610
Token fuel
Token ID5252
Feature activation-2.37e+00

Pos logit contributions
 Dent+3.231
 Nadu+3.134
 Devi+3.039
 Benefit+2.839
 Equity+2.823
Neg logit contributions
ipal-3.248
init-3.184
shift-3.024
actory-2.999
ounge-2.954
Token production
Token ID3227
Feature activation-2.86e+00

Pos logit contributions
 Dent+2.011
 Nadu+1.942
 Devi+1.894
 Equity+1.781
 Benefit+1.780
Neg logit contributions
ipal-1.537
init-1.502
shift-1.415
actory-1.408
ounge-1.367
Token past
Token ID1613
Feature activation-1.66e+00

Pos logit contributions
 Dent+2.221
 Nadu+2.128
 Devi+2.079
 Equity+1.946
 Benefit+1.942
Neg logit contributions
ipal-2.061
init-2.021
shift-1.913
actory-1.909
ounge-1.855
Token 20
Token ID1160
Feature activation-4.30e-03

Pos logit contributions
 Dent+1.154
 Nadu+1.099
 Devi+1.071
 Equity+0.987
iaz+0.984
Neg logit contributions
ipal-1.336
init-1.315
actory-1.254
shift-1.254
ounge-1.213
Token45
Token ID2231
Feature activation-1.25e+00

Pos logit contributions
 Dent+0.004
 Nadu+0.004
 Devi+0.004
 Equity+0.004
 Benefit+0.004
Neg logit contributions
ipal-0.003
init-0.002
shift-0.002
actory-0.002
ounge-0.002
Token on
Token ID319
Feature activation+5.49e-01

Pos logit contributions
ipal+0.958
init+0.944
actory+0.877
shift+0.877
ounge+0.842
Neg logit contributions
 Dent-1.429
 Nadu-1.373
 Devi-1.350
 Equity-1.269
 Benefit-1.266
Token,
Token ID11
Feature activation-2.59e-01

Pos logit contributions
ipal+0.389
init+0.383
shift+0.362
actory+0.360
ounge+0.348
Neg logit contributions
 Dent-0.434
 Nadu-0.416
 Devi-0.407
 Equity-0.380
 Benefit-0.378
Token then
Token ID788
Feature activation+5.78e-01

Pos logit contributions
 Dent+0.199
 Nadu+0.190
 Devi+0.186
 Equity+0.174
 Benefit+0.173
Neg logit contributions
ipal-0.189
init-0.186
shift-0.176
actory-0.176
ounge-0.171
Token open
Token ID1280
Feature activation+4.06e-01

Pos logit contributions
ipal+0.411
init+0.404
shift+0.385
actory+0.382
ounge+0.369
Neg logit contributions
 Dent-0.456
 Nadu-0.438
 Devi-0.428
 Equity-0.400
iaz-0.397
Token the
Token ID262
Feature activation-2.14e-01

Pos logit contributions
ipal+0.306
init+0.301
shift+0.287
actory+0.285
ounge+0.277
Neg logit contributions
 Dent-0.302
 Nadu-0.289
 Devi-0.282
 Equity-0.262
iaz-0.261
Token catalog
Token ID18388
Feature activation-4.35e+00

Pos logit contributions
 Dent+0.146
 Nadu+0.139
 Devi+0.136
 Equity+0.125
iaz+0.125
Neg logit contributions
ipal-0.175
init-0.172
shift-0.164
actory-0.164
ounge-0.159
Token like
Token ID588
Feature activation-8.28e-02

Pos logit contributions
 Dent+3.289
 Nadu+3.121
 Devi+3.070
 Benefit+2.868
 Equity+2.849
Neg logit contributions
ipal-3.165
init-3.121
actory-2.935
shift-2.922
itual-2.847
Token you
Token ID345
Feature activation+1.69e-01

Pos logit contributions
 Dent+0.063
 Nadu+0.060
 Devi+0.058
 Equity+0.055
iaz+0.054
Neg logit contributions
ipal-0.061
init-0.061
shift-0.057
actory-0.057
ounge-0.055
Token would
Token ID561
Feature activation+7.06e-03

Pos logit contributions
ipal+0.101
init+0.100
shift+0.093
actory+0.093
ounge+0.089
Neg logit contributions
 Dent-0.152
 Nadu-0.146
 Devi-0.143
 Equity-0.135
 Benefit-0.135
Token any
Token ID597
Feature activation+9.16e-01

Pos logit contributions
ipal+0.005
init+0.005
shift+0.005
actory+0.005
ounge+0.005
Neg logit contributions
 Dent-0.006
 Nadu-0.005
 Devi-0.005
 Equity-0.005
 Benefit-0.005
Token ebook
Token ID47179
Feature activation-2.99e-01

Pos logit contributions
ipal+0.679
init+0.670
shift+0.642
actory+0.639
ounge+0.619
Neg logit contributions
 Dent-0.682
 Nadu-0.661
 Devi-0.639
iaz-0.594
 Equity-0.594
TokenIn
Token ID818
Feature activation-2.39e-01

Pos logit contributions
 Dent+0.275
 Nadu+0.264
 Devi+0.259
 Equity+0.243
 Benefit+0.242
Neg logit contributions
ipal-0.207
init-0.205
shift-0.193
actory-0.190
ounge-0.184
Token all
Token ID477
Feature activation-1.75e+00

Pos logit contributions
 Dent+0.193
 Nadu+0.185
 Devi+0.181
 Equity+0.169
iaz+0.169
Neg logit contributions
ipal-0.165
init-0.163
shift-0.154
actory-0.153
ounge-0.148
Token,
Token ID11
Feature activation-4.26e-01

Pos logit contributions
 Dent+1.317
 Nadu+1.255
 Devi+1.228
 Equity+1.146
 Benefit+1.133
Neg logit contributions
ipal-1.312
init-1.285
shift-1.223
actory-1.220
ounge-1.191
Token the
Token ID262
Feature activation-5.66e-01

Pos logit contributions
 Dent+0.330
 Nadu+0.316
 Devi+0.310
 Equity+0.288
 Benefit+0.288
Neg logit contributions
ipal-0.308
init-0.304
shift-0.287
actory-0.286
ounge-0.277
Token ice
Token ID4771
Feature activation-7.20e-01

Pos logit contributions
 Dent+0.456
 Nadu+0.438
 Devi+0.428
 Equity+0.401
 Benefit+0.400
Neg logit contributions
ipal-0.392
init-0.386
shift-0.365
actory-0.363
ounge-0.351
Token sheet
Token ID9629
Feature activation-4.34e+00

Pos logit contributions
 Dent+0.550
 Nadu+0.523
 Devi+0.513
 Equity+0.478
 Benefit+0.475
Neg logit contributions
ipal-0.531
init-0.524
shift-0.498
actory-0.494
ounge-0.479
Token contains
Token ID4909
Feature activation-1.27e+00

Pos logit contributions
 Dent+3.343
 Nadu+3.228
 Devi+3.122
 Benefit+2.900
 Equity+2.893
Neg logit contributions
ipal-3.126
init-3.048
actory-2.916
shift-2.873
ounge-2.830
Token enough
Token ID1576
Feature activation-3.74e-01

Pos logit contributions
 Dent+1.076
 Nadu+1.034
 Devi+1.013
 Equity+0.951
 Benefit+0.948
Neg logit contributions
ipal-0.826
init-0.810
shift-0.762
actory-0.761
ounge-0.735
Token water
Token ID1660
Feature activation+5.92e-01

Pos logit contributions
 Dent+0.322
 Nadu+0.309
 Devi+0.303
 Equity+0.285
 Benefit+0.284
Neg logit contributions
ipal-0.240
init-0.235
shift-0.221
actory-0.221
ounge-0.213
Token to
Token ID284
Feature activation+1.46e-01

Pos logit contributions
ipal+0.438
init+0.431
shift+0.410
actory+0.406
ounge+0.394
Neg logit contributions
 Dent-0.450
 Nadu-0.430
 Devi-0.421
 Equity-0.392
 Benefit-0.391
Token raise
Token ID5298
Feature activation+6.93e-01

Pos logit contributions
ipal+0.105
init+0.103
shift+0.098
actory+0.097
ounge+0.094
Neg logit contributions
 Dent-0.115
 Nadu-0.110
 Devi-0.108
 Equity-0.101
iaz-0.100
Token and
Token ID290
Feature activation+2.37e-01

Pos logit contributions
ipal+0.092
init+0.090
shift+0.085
actory+0.085
ounge+0.083
Neg logit contributions
 Dent-0.105
 Nadu-0.101
 Devi-0.099
 Equity-0.092
 Benefit-0.092
Token evolve
Token ID18101
Feature activation-7.03e-01

Pos logit contributions
ipal+0.173
init+0.171
shift+0.162
actory+0.161
ounge+0.156
Neg logit contributions
 Dent-0.183
 Nadu-0.175
 Devi-0.171
 Equity-0.159
iaz-0.159
Token to
Token ID284
Feature activation+4.98e-02

Pos logit contributions
 Dent+0.570
 Nadu+0.546
 Devi+0.535
 Equity+0.501
 Benefit+0.499
Neg logit contributions
ipal-0.485
init-0.476
actory-0.449
shift-0.448
ounge-0.435
Token fill
Token ID6070
Feature activation-8.47e-01

Pos logit contributions
ipal+0.036
init+0.035
shift+0.034
actory+0.034
ounge+0.032
Neg logit contributions
 Dent-0.039
 Nadu-0.037
 Devi-0.036
 Equity-0.034
 Benefit-0.034
Token ecological
Token ID25047
Feature activation+3.90e-01

Pos logit contributions
 Dent+0.638
 Nadu+0.610
 Devi+0.594
 Equity+0.554
 Benefit+0.551
Neg logit contributions
ipal-0.634
init-0.624
shift-0.590
actory-0.590
ounge-0.574
Token nic
Token ID9200
Feature activation-4.31e+00

Pos logit contributions
ipal+0.342
init+0.338
shift+0.326
actory+0.325
ounge+0.316
Neg logit contributions
 Dent-0.239
 Nadu-0.226
 Devi-0.222
iaz-0.201
 Benefit-0.200
Tokenhes
Token ID956
Feature activation+6.92e-03

Pos logit contributions
 Dent+3.537
 Nadu+3.387
 Devi+3.321
iaz+3.126
 Equity+3.119
Neg logit contributions
ipal-2.880
init-2.840
shift-2.679
actory-2.663
ounge-2.586
Token left
Token ID1364
Feature activation-1.17e+00

Pos logit contributions
ipal+0.005
init+0.005
shift+0.004
actory+0.004
ounge+0.004
Neg logit contributions
 Dent-0.006
 Nadu-0.005
 Devi-0.005
 Equity-0.005
 Benefit-0.005
Token vacant
Token ID23957
Feature activation-1.06e+00

Pos logit contributions
 Dent+0.913
 Nadu+0.874
 Devi+0.856
 Equity+0.800
 Benefit+0.797
Neg logit contributions
ipal-0.843
init-0.832
shift-0.788
actory-0.787
ounge-0.758
Token after
Token ID706
Feature activation+6.27e-01

Pos logit contributions
 Dent+0.861
 Nadu+0.827
 Devi+0.810
 Equity+0.758
 Benefit+0.755
Neg logit contributions
ipal-0.732
init-0.720
shift-0.679
actory-0.679
ounge-0.655
Token the
Token ID262
Feature activation-2.17e-01

Pos logit contributions
ipal+0.460
init+0.453
shift+0.429
actory+0.429
ounge+0.411
Neg logit contributions
 Dent-0.477
 Nadu-0.460
 Devi-0.452
 Equity-0.419
iaz-0.418
Token partnerships
Token ID22867
Feature activation-1.27e+00

Pos logit contributions
 Dent+0.336
 Nadu+0.324
 Devi+0.316
iaz+0.293
 Benefit+0.292
Neg logit contributions
ipal-0.315
init-0.313
actory-0.295
shift-0.295
ounge-0.287
Token with
Token ID351
Feature activation+2.48e-01

Pos logit contributions
 Dent+1.022
 Nadu+0.981
 Devi+0.960
 Equity+0.894
 Benefit+0.892
Neg logit contributions
ipal-0.883
init-0.872
shift-0.821
actory-0.820
ounge-0.796
Token search
Token ID2989
Feature activation-3.12e+00

Pos logit contributions
ipal+0.171
init+0.170
shift+0.160
actory+0.160
ounge+0.154
Neg logit contributions
 Dent-0.199
 Nadu-0.192
 Devi-0.187
iaz-0.175
 Benefit-0.174
Token engines
Token ID11874
Feature activation-2.22e+00

Pos logit contributions
 Dent+2.479
 Nadu+2.371
 Devi+2.316
 Equity+2.190
 Benefit+2.174
Neg logit contributions
ipal-2.190
init-2.142
shift-2.030
actory-2.023
itual-1.956
Token like
Token ID588
Feature activation-1.95e-01

Pos logit contributions
 Dent+1.660
 Nadu+1.584
 Devi+1.548
 Equity+1.441
 Benefit+1.436
Neg logit contributions
ipal-1.676
init-1.647
shift-1.564
actory-1.562
ounge-1.514
Token Google
Token ID3012
Feature activation-4.30e+00

Pos logit contributions
 Dent+0.123
 Nadu+0.121
 Devi+0.115
iaz+0.106
ouri+0.104
Neg logit contributions
ipal-0.166
init-0.165
shift-0.158
actory-0.156
ounge-0.153
Token,
Token ID11
Feature activation-4.56e-02

Pos logit contributions
 Dent+3.238
 Nadu+3.086
 Devi+3.014
 Equity+2.831
 Benefit+2.812
Neg logit contributions
ipal-3.208
init-3.153
shift-3.001
actory-2.997
itual-2.899
Token Yahoo
Token ID16551
Feature activation-3.15e+00

Pos logit contributions
 Dent+0.033
 Nadu+0.032
 Devi+0.031
iaz+0.029
 Equity+0.028
Neg logit contributions
ipal-0.035
init-0.035
shift-0.033
actory-0.033
ounge-0.032
Token,
Token ID11
Feature activation-7.06e-02

Pos logit contributions
 Dent+2.299
 Nadu+2.158
 Devi+2.098
 Equity+1.992
 Benefit+1.966
Neg logit contributions
ipal-2.464
init-2.373
actory-2.292
shift-2.289
itual-2.234
Token Duck
Token ID21867
Feature activation-1.08e+00

Pos logit contributions
 Dent+0.050
 Nadu+0.049
 Devi+0.047
iaz+0.044
 Equity+0.043
Neg logit contributions
ipal-0.055
init-0.054
shift-0.052
actory-0.051
ounge-0.050
TokenD
Token ID35
Feature activation+2.17e-01

Pos logit contributions
 Dent+0.798
 Nadu+0.758
 Devi+0.739
 Equity+0.690
 Benefit+0.686
Neg logit contributions
ipal-0.826
init-0.810
actory-0.770
shift-0.768
ounge-0.749
Token don
Token ID836
Feature activation+1.93e-01

Pos logit contributions
ipal+0.523
init+0.521
shift+0.499
actory+0.490
ounge+0.474
Neg logit contributions
 Dent-0.602
 Nadu-0.578
 Devi-0.568
iaz-0.529
 Equity-0.528
Token't
Token ID470
Feature activation+4.59e-01

Pos logit contributions
init+0.086
ipal+0.086
shift+0.079
actory+0.076
itual+0.071
Neg logit contributions
 Dent-0.204
 Nadu-0.198
 Devi-0.196
 Equity-0.185
iaz-0.184
Token know
Token ID760
Feature activation+1.83e-01

Pos logit contributions
init+0.311
ipal+0.311
shift+0.299
actory+0.294
 selector+0.282
Neg logit contributions
 Dent-0.371
 Nadu-0.357
 Devi-0.350
 Equity-0.327
iaz-0.325
Token who
Token ID508
Feature activation+1.59e-01

Pos logit contributions
ipal+0.127
init+0.125
shift+0.118
actory+0.117
ounge+0.114
Neg logit contributions
 Dent-0.145
 Nadu-0.142
 Devi-0.137
iaz-0.129
 Equity-0.128
Token the
Token ID262
Feature activation-1.49e-01

Pos logit contributions
ipal+0.117
init+0.115
actory+0.107
shift+0.107
ounge+0.103
Neg logit contributions
 Dent-0.122
 Nadu-0.118
 Devi-0.115
iaz-0.107
 Equity-0.106
Token Koch
Token ID17009
Feature activation-4.25e+00

Pos logit contributions
 Dent+0.120
 Nadu+0.116
 Devi+0.114
 Equity+0.106
 Benefit+0.106
Neg logit contributions
ipal-0.103
init-0.101
shift-0.095
actory-0.095
ounge-0.092
Token brothers
Token ID9397
Feature activation-1.00e+00

Pos logit contributions
 Dent+3.119
 Nadu+2.980
 Devi+2.881
 Benefit+2.736
 Equity+2.730
Neg logit contributions
ipal-3.173
init-3.125
shift-2.992
actory-2.955
ounge-2.914
Token are
Token ID389
Feature activation+4.51e-02

Pos logit contributions
 Dent+0.675
 Nadu+0.642
 Devi+0.623
 Equity+0.578
 Benefit+0.576
Neg logit contributions
ipal-0.830
init-0.819
shift-0.781
actory-0.780
ounge-0.760
Token."
Token ID526
Feature activation-8.12e-01

Pos logit contributions
ipal+0.032
init+0.032
shift+0.030
actory+0.030
ounge+0.029
Neg logit contributions
 Dent-0.035
 Nadu-0.034
 Devi-0.033
 Equity-0.031
 Benefit-0.031
Token
Token ID198
Feature activation-1.52e-01

Pos logit contributions
 Dent+0.612
 Nadu+0.586
 Devi+0.572
 Equity+0.532
 Benefit+0.530
Neg logit contributions
ipal-0.606
init-0.596
shift-0.566
actory-0.564
ounge-0.547
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
 Dent+0.130
 Nadu+0.126
 Devi+0.123
 Equity+0.115
iaz+0.115
Neg logit contributions
init-0.099
ipal-0.097
shift-0.093
actory-0.091
photo-0.087
Token
Token ID198
Feature activation+2.27e-01

Pos logit contributions
init+0.292
ipal+0.284
shift+0.273
actory+0.266
photo+0.255
Neg logit contributions
 Dent-0.398
 Nadu-0.388
 Devi-0.379
iaz-0.354
 Equity-0.353
TokenFord
Token ID37308
Feature activation-1.01e+00

Pos logit contributions
ipal+0.144
init+0.142
shift+0.133
actory+0.133
ounge+0.128
Neg logit contributions
 Dent-0.196
 Nadu-0.189
 Devi-0.185
 Equity-0.174
 Benefit-0.173
Token,
Token ID11
Feature activation-3.34e-01

Pos logit contributions
 Dent+0.721
 Nadu+0.687
 Devi+0.671
 Equity+0.622
 Benefit+0.619
Neg logit contributions
ipal-0.788
init-0.775
shift-0.738
actory-0.736
ounge-0.716
Token America
Token ID2253
Feature activation+2.91e-01

Pos logit contributions
 Dent+0.251
 Nadu+0.241
 Devi+0.235
iaz+0.217
 Equity+0.217
Neg logit contributions
ipal-0.250
init-0.247
shift-0.234
actory-0.234
ounge-0.226
Token's
Token ID338
Feature activation+7.75e-01

Pos logit contributions
ipal+0.226
init+0.222
shift+0.211
actory+0.210
ounge+0.205
Neg logit contributions
 Dent-0.211
 Nadu-0.201
 Devi-0.196
 Equity-0.182
 Benefit-0.182
Token truck
Token ID7779
Feature activation+2.89e+00

Pos logit contributions
ipal+0.524
init+0.518
actory+0.487
shift+0.485
ounge+0.468
Neg logit contributions
 Dent-0.631
 Nadu-0.607
 Devi-0.596
iaz-0.560
 Equity-0.554
Token leader
Token ID3554
Feature activation+4.75e-01

Pos logit contributions
ipal+2.056
init+2.033
actory+1.921
shift+1.915
ounge+1.850
Neg logit contributions
 Dent-2.267
 Nadu-2.168
 Devi-2.128
 Equity-1.983
 Benefit-1.973
Token,
Token ID11
Feature activation-3.14e-01

Pos logit contributions
ipal+0.336
init+0.331
shift+0.313
actory+0.312
ounge+0.302
Neg logit contributions
 Dent-0.377
 Nadu-0.361
 Devi-0.353
 Equity-0.329
 Benefit-0.329
Token today
Token ID1909
Feature activation+1.24e+00

Pos logit contributions
 Dent+0.244
 Nadu+0.233
 Devi+0.228
 Equity+0.212
 Benefit+0.212
Neg logit contributions
ipal-0.227
init-0.223
shift-0.211
actory-0.211
ounge-0.204
Token introduced
Token ID5495
Feature activation-5.84e-01

Pos logit contributions
ipal+0.961
init+0.953
shift+0.897
actory+0.896
ounge+0.864
Neg logit contributions
 Dent-0.893
 Nadu-0.861
 Devi-0.829
 Equity-0.770
iaz-0.770
Token the
Token ID262
Feature activation+3.99e-02

Pos logit contributions
 Dent+0.415
 Nadu+0.396
 Devi+0.386
 Equity+0.358
 Benefit+0.356
Neg logit contributions
ipal-0.461
init-0.454
shift-0.432
actory-0.431
ounge-0.419
Token
Token ID247
Feature activation-2.73e-01

Pos logit contributions
 Dent+0.090
 Nadu+0.086
 Devi+0.084
 Equity+0.078
 Benefit+0.077
Neg logit contributions
ipal-0.094
init-0.093
actory-0.088
shift-0.088
ounge-0.085
Tokens
Token ID82
Feature activation+3.07e-02

Pos logit contributions
 Dent+0.190
 Nadu+0.181
 Devi+0.176
 Equity+0.163
 Benefit+0.162
Neg logit contributions
ipal-0.221
init-0.218
shift-0.207
actory-0.207
ounge-0.201
Token punches
Token ID25495
Feature activation-1.09e+00

Pos logit contributions
ipal+0.021
init+0.021
actory+0.020
shift+0.020
ounge+0.019
Neg logit contributions
 Dent-0.024
 Nadu-0.023
 Devi-0.023
 Equity-0.021
 Benefit-0.021
Token had
Token ID550
Feature activation-7.75e-01

Pos logit contributions
 Dent+0.872
 Nadu+0.836
 Devi+0.818
 Equity+0.764
 Benefit+0.762
Neg logit contributions
ipal-0.765
init-0.751
shift-0.710
actory-0.708
ounge-0.686
Token blown
Token ID16318
Feature activation+1.17e-01

Pos logit contributions
 Dent+0.613
 Nadu+0.590
 Devi+0.576
 Equity+0.540
iaz+0.537
Neg logit contributions
ipal-0.546
init-0.539
shift-0.510
actory-0.507
ounge-0.490
Token Brook
Token ID7590
Feature activation+3.08e+00

Pos logit contributions
ipal+0.087
init+0.087
shift+0.082
actory+0.082
ounge+0.079
Neg logit contributions
 Dent-0.087
 Nadu-0.084
 Devi-0.082
 Equity-0.077
iaz-0.076
Token
Token ID447
Feature activation-1.82e-01

Pos logit contributions
ipal+2.368
init+2.341
shift+2.221
actory+2.188
 scrambled+2.104
Neg logit contributions
 Dent-2.199
 Nadu-2.139
 Devi-2.073
 Equity-1.945
 Benefit-1.910
Token
Token ID247
Feature activation-6.87e-01

Pos logit contributions
 Dent+0.137
 Nadu+0.132
 Devi+0.129
 Equity+0.120
 Benefit+0.120
Neg logit contributions
ipal-0.136
init-0.134
actory-0.127
shift-0.126
ounge-0.122
Tokens
Token ID82
Feature activation-3.05e-02

Pos logit contributions
 Dent+0.464
 Nadu+0.443
 Devi+0.433
 Equity+0.398
 Benefit+0.396
Neg logit contributions
ipal-0.570
init-0.563
shift-0.535
actory-0.535
ounge-0.519
Token eye
Token ID4151
Feature activation+8.86e-01

Pos logit contributions
 Dent+0.026
 Nadu+0.025
 Devi+0.025
 Equity+0.023
iaz+0.023
Neg logit contributions
ipal-0.019
init-0.019
shift-0.018
actory-0.018
ounge-0.017
Token up
Token ID510
Feature activation+9.01e-01

Pos logit contributions
ipal+0.698
init+0.689
shift+0.656
actory+0.654
ounge+0.635
Neg logit contributions
 Dent-0.630
 Nadu-0.601
 Devi-0.586
 Equity-0.543
 Benefit-0.540
Token and
Token ID290
Feature activation+8.25e-02

Pos logit contributions
ipal+0.177
init+0.173
shift+0.164
actory+0.163
ounge+0.158
Neg logit contributions
 Dent-0.206
 Nadu-0.198
 Devi-0.193
 Equity-0.181
 Benefit-0.180
Token stem
Token ID10717
Feature activation-5.30e-01

Pos logit contributions
ipal+0.057
init+0.055
shift+0.053
actory+0.052
ounge+0.051
Neg logit contributions
 Dent-0.066
 Nadu-0.064
 Devi-0.063
 Equity-0.059
iaz-0.058
Token.
Token ID13
Feature activation+4.25e-01

Pos logit contributions
 Dent+0.430
 Nadu+0.411
 Devi+0.403
 Equity+0.377
 Benefit+0.376
Neg logit contributions
ipal-0.367
init-0.360
actory-0.340
shift-0.340
ounge-0.329
Token View
Token ID3582
Feature activation+5.34e-01

Pos logit contributions
ipal+0.344
init+0.339
shift+0.325
actory+0.321
ounge+0.313
Neg logit contributions
 Dent-0.290
 Nadu-0.279
 Devi-0.270
iaz-0.251
 Equity-0.249
Token Full
Token ID6462
Feature activation-1.24e-01

Pos logit contributions
ipal+0.378
init+0.373
actory+0.355
shift+0.355
ounge+0.341
Neg logit contributions
 Dent-0.421
 Nadu-0.404
 Devi-0.394
 Equity-0.367
iaz-0.366
Token Caption
Token ID11260
Feature activation+5.20e+00

Pos logit contributions
 Dent+0.084
 Nadu+0.081
 Devi+0.078
 Equity+0.072
 Benefit+0.072
Neg logit contributions
ipal-0.101
init-0.100
shift-0.095
actory-0.095
ounge-0.092
Token Adam
Token ID7244
Feature activation+1.08e+00

Pos logit contributions
ipal+3.148
init+3.072
shift+2.897
actory+2.872
photo+2.751
Neg logit contributions
 Dent-4.453
 Nadu-4.413
 Devi-4.256
iaz-4.126
merce-4.033
Token Glenn
Token ID17551
Feature activation+1.23e+00

Pos logit contributions
ipal+0.882
init+0.871
shift+0.827
actory+0.827
ounge+0.801
Neg logit contributions
 Dent-0.737
 Nadu-0.708
 Devi-0.687
 Equity-0.636
 Benefit-0.631
Token
Token ID198
Feature activation+3.05e-01

Pos logit contributions
ipal+0.905
init+0.897
shift+0.844
actory+0.842
ounge+0.817
Neg logit contributions
 Dent-0.935
 Nadu-0.898
 Devi-0.875
 Equity-0.816
 Benefit-0.813
Token
Token ID198
Feature activation+1.56e-01

Pos logit contributions
init+0.199
ipal+0.195
shift+0.187
actory+0.182
photo+0.176
Neg logit contributions
 Dent-0.260
 Nadu-0.252
 Devi-0.246
iaz-0.230
 Equity-0.229
TokenC
Token ID34
Feature activation+5.04e-01

Pos logit contributions
ipal+0.094
init+0.092
actory+0.086
shift+0.086
ounge+0.083
Neg logit contributions
 Dent-0.140
 Nadu-0.135
 Devi-0.132
 Equity-0.125
 Benefit-0.124
Token the
Token ID262
Feature activation-1.29e-01

Pos logit contributions
 Dent+0.051
 Nadu+0.049
 Devi+0.048
iaz+0.044
 Equity+0.044
Neg logit contributions
ipal-0.049
init-0.049
shift-0.046
actory-0.046
itual-0.044
Token doctor
Token ID6253
Feature activation-1.66e-01

Pos logit contributions
 Dent+0.102
 Nadu+0.098
 Devi+0.095
 Equity+0.089
iaz+0.089
Neg logit contributions
ipal-0.092
init-0.091
shift-0.086
actory-0.086
ounge-0.083
Token of
Token ID286
Feature activation+2.00e-01

Pos logit contributions
 Dent+0.132
 Nadu+0.127
 Devi+0.124
 Equity+0.116
 Benefit+0.115
Neg logit contributions
ipal-0.117
init-0.115
shift-0.108
actory-0.108
ounge-0.105
Token Catholic
Token ID7835
Feature activation+1.63e-01

Pos logit contributions
ipal+0.151
init+0.149
actory+0.140
shift+0.140
ounge+0.136
Neg logit contributions
 Dent-0.149
 Nadu-0.143
 Devi-0.139
iaz-0.129
 Benefit-0.129
Token truth
Token ID3872
Feature activation-6.19e-02

Pos logit contributions
ipal+0.114
init+0.113
shift+0.105
actory+0.105
itual+0.102
Neg logit contributions
 Dent-0.129
 Nadu-0.125
 Devi-0.122
iaz-0.114
 Benefit-0.113
Token ought
Token ID10783
Feature activation+2.90e+00

Pos logit contributions
 Dent+0.049
 Nadu+0.047
 Devi+0.046
 Equity+0.043
 Benefit+0.043
Neg logit contributions
ipal-0.044
init-0.043
shift-0.041
actory-0.041
ounge-0.039
Token not
Token ID407
Feature activation-5.34e-01

Pos logit contributions
ipal+2.177
init+2.146
shift+2.033
actory+2.030
ounge+1.969
Neg logit contributions
 Dent-2.176
 Nadu-2.082
 Devi-2.032
 Equity-1.888
 Benefit-1.882
Token only
Token ID691
Feature activation-2.24e-01

Pos logit contributions
 Dent+0.381
 Nadu+0.364
 Devi+0.353
 Equity+0.329
 Benefit+0.327
Neg logit contributions
ipal-0.421
init-0.412
shift-0.392
actory-0.392
ounge-0.382
Token to
Token ID284
Feature activation-1.70e-01

Pos logit contributions
 Dent+0.161
 Nadu+0.153
 Devi+0.150
 Equity+0.139
 Benefit+0.138
Neg logit contributions
ipal-0.176
init-0.172
shift-0.164
actory-0.164
ounge-0.159
Token teach
Token ID4545
Feature activation+7.09e-01

Pos logit contributions
 Dent+0.133
 Nadu+0.128
 Devi+0.125
 Equity+0.117
iaz+0.116
Neg logit contributions
ipal-0.121
init-0.120
shift-0.113
actory-0.113
ounge-0.109
Token the
Token ID262
Feature activation+3.00e-01

Pos logit contributions
ipal+0.504
init+0.499
shift+0.470
actory+0.467
itual+0.454
Neg logit contributions
 Dent-0.551
 Nadu-0.536
 Devi-0.517
iaz-0.485
 Equity-0.481
Token income
Token ID3739
Feature activation+5.83e-02

Pos logit contributions
ipal+0.013
init+0.013
shift+0.012
actory+0.012
ounge+0.012
Neg logit contributions
 Dent-0.017
 Nadu-0.016
 Devi-0.016
iaz-0.015
 Equity-0.015
Token for
Token ID329
Feature activation+8.35e-01

Pos logit contributions
ipal+0.039
init+0.039
shift+0.036
actory+0.036
ounge+0.035
Neg logit contributions
 Dent-0.048
 Nadu-0.046
 Devi-0.045
 Equity-0.042
iaz-0.042
Token his
Token ID465
Feature activation+5.74e-01

Pos logit contributions
ipal+0.601
init+0.593
shift+0.560
actory+0.560
ounge+0.545
Neg logit contributions
 Dent-0.636
 Nadu-0.622
 Devi-0.604
iaz-0.565
 Equity-0.556
Token spouse
Token ID16731
Feature activation+4.04e-01

Pos logit contributions
ipal+0.392
init+0.385
shift+0.363
actory+0.361
ounge+0.352
Neg logit contributions
 Dent-0.460
 Nadu-0.448
 Devi-0.436
iaz-0.409
 Equity-0.404
Token,
Token ID11
Feature activation+4.79e-01

Pos logit contributions
ipal+0.287
init+0.284
shift+0.267
actory+0.265
ounge+0.259
Neg logit contributions
 Dent-0.316
 Nadu-0.304
 Devi-0.296
iaz-0.277
 Equity-0.276
Token according
Token ID1864
Feature activation+2.97e+00

Pos logit contributions
ipal+0.341
init+0.337
shift+0.318
actory+0.316
ounge+0.309
Neg logit contributions
 Dent-0.371
 Nadu-0.360
 Devi-0.348
iaz-0.328
 Equity-0.324
Token to
Token ID284
Feature activation+6.80e-01

Pos logit contributions
ipal+1.902
init+1.900
shift+1.770
actory+1.741
itual+1.669
Neg logit contributions
 Dent-2.450
 Nadu-2.415
 Devi-2.349
iaz-2.206
ouri-2.185
Token his
Token ID465
Feature activation+4.78e-01

Pos logit contributions
ipal+0.484
init+0.475
shift+0.449
actory+0.449
ounge+0.435
Neg logit contributions
 Dent-0.532
 Nadu-0.516
 Devi-0.500
iaz-0.465
 Equity-0.463
Token disclosure
Token ID13019
Feature activation-3.03e-01

Pos logit contributions
ipal+0.327
init+0.320
shift+0.302
actory+0.301
ounge+0.293
Neg logit contributions
 Dent-0.388
 Nadu-0.376
 Devi-0.365
iaz-0.341
 Benefit-0.338
Token statement
Token ID2643
Feature activation+2.07e+00

Pos logit contributions
 Dent+0.282
 Nadu+0.272
 Devi+0.267
 Equity+0.252
 Benefit+0.251
Neg logit contributions
ipal-0.173
init-0.170
shift-0.158
actory-0.158
ounge-0.152
Token.
Token ID13
Feature activation+1.79e-01

Pos logit contributions
ipal+1.402
init+1.384
shift+1.299
actory+1.297
ounge+1.253
Neg logit contributions
 Dent-1.696
 Nadu-1.642
 Devi-1.588
 Equity-1.491
 Benefit-1.486
Token,
Token ID11
Feature activation+1.65e-01

Pos logit contributions
ipal+0.693
init+0.678
shift+0.641
actory+0.634
ounge+0.612
Neg logit contributions
 Dent-0.928
 Nadu-0.899
 Devi-0.877
iaz-0.824
 Benefit-0.823
Token though
Token ID996
Feature activation+1.59e+00

Pos logit contributions
ipal+0.112
init+0.111
shift+0.104
actory+0.103
ounge+0.100
Neg logit contributions
 Dent-0.134
 Nadu-0.129
 Devi-0.126
iaz-0.118
 Benefit-0.118
Token:
Token ID25
Feature activation+6.71e-01

Pos logit contributions
ipal+0.938
init+0.916
shift+0.857
actory+0.854
ounge+0.823
Neg logit contributions
 Dent-1.456
 Nadu-1.400
 Devi-1.375
 Equity-1.298
 Benefit-1.293
Token Would
Token ID10928
Feature activation-3.62e-01

Pos logit contributions
ipal+0.534
init+0.529
shift+0.504
actory+0.502
ounge+0.489
Neg logit contributions
 Dent-0.459
 Nadu-0.446
 Devi-0.430
iaz-0.402
ouri-0.393
Token Os
Token ID8834
Feature activation+6.67e-01

Pos logit contributions
 Dent+0.277
 Nadu+0.267
 Devi+0.259
iaz+0.242
 Equity+0.241
Neg logit contributions
ipal-0.265
init-0.261
shift-0.247
actory-0.246
ounge-0.239
Tokenwe
Token ID732
Feature activation+6.56e-01

Pos logit contributions
ipal+0.404
init+0.399
shift+0.381
actory+0.372
ounge+0.358
Neg logit contributions
 Dent-0.609
 Nadu-0.583
 Devi-0.570
 Equity-0.537
 Benefit-0.534
Tokeniler
Token ID5329
Feature activation+9.08e-01

Pos logit contributions
ipal+0.314
init+0.313
actory+0.292
shift+0.285
ounge+0.264
Neg logit contributions
 Dent-0.688
 Nadu-0.655
 Devi-0.646
 Equity-0.620
 Benefit-0.607
Token,
Token ID11
Feature activation+8.76e-02

Pos logit contributions
ipal+0.626
init+0.618
shift+0.588
actory+0.582
ounge+0.564
Neg logit contributions
 Dent-0.732
 Nadu-0.706
 Devi-0.692
 Equity-0.643
iaz-0.639
Token as
Token ID355
Feature activation+4.97e-01

Pos logit contributions
ipal+0.061
init+0.061
shift+0.057
actory+0.056
ounge+0.055
Neg logit contributions
 Dent-0.069
 Nadu-0.067
 Devi-0.065
iaz-0.061
 Equity-0.061
Token unprepared
Token ID45102
Feature activation-1.24e+00

Pos logit contributions
ipal+0.383
init+0.381
shift+0.361
actory+0.360
ounge+0.349
Neg logit contributions
 Dent-0.353
 Nadu-0.346
 Devi-0.333
iaz-0.309
 Equity-0.309
Token as
Token ID355
Feature activation+7.51e-01

Pos logit contributions
 Dent+0.959
 Nadu+0.917
 Devi+0.897
 Equity+0.836
 Benefit+0.833
Neg logit contributions
ipal-0.905
init-0.890
shift-0.843
actory-0.841
ounge-0.816
Token The
Token ID383
Feature activation-2.37e-01

Pos logit contributions
ipal+0.295
init+0.292
shift+0.277
actory+0.273
ounge+0.266
Neg logit contributions
 Dent-0.262
 Nadu-0.255
 Devi-0.245
iaz-0.230
 Equity-0.227
Token Company
Token ID5834
Feature activation+1.81e+00

Pos logit contributions
 Dent+0.168
 Nadu+0.161
 Devi+0.157
 Equity+0.145
iaz+0.144
Neg logit contributions
ipal-0.187
init-0.184
shift-0.175
actory-0.175
ounge-0.170
Token of
Token ID286
Feature activation+1.79e-01

Pos logit contributions
ipal+1.255
init+1.248
shift+1.182
actory+1.163
ounge+1.133
Neg logit contributions
 Dent-1.425
 Nadu-1.390
 Devi-1.340
 Equity-1.255
iaz-1.253
Token the
Token ID262
Feature activation+6.40e-01

Pos logit contributions
ipal+0.140
init+0.138
shift+0.132
actory+0.131
ounge+0.127
Neg logit contributions
 Dent-0.126
 Nadu-0.123
 Devi-0.118
iaz-0.110
 Equity-0.109
Token Ring
Token ID12569
Feature activation+1.02e+00

Pos logit contributions
ipal+0.536
init+0.532
shift+0.513
actory+0.508
ounge+0.496
Neg logit contributions
 Dent-0.409
 Nadu-0.397
 Devi-0.377
 Equity-0.349
iaz-0.348
Token are
Token ID389
Feature activation+6.53e-01

Pos logit contributions
ipal+0.730
init+0.723
shift+0.686
actory+0.678
ounge+0.659
Neg logit contributions
 Dent-0.798
 Nadu-0.767
 Devi-0.747
 Equity-0.700
iaz-0.694
Token nine
Token ID5193
Feature activation+1.50e+00

Pos logit contributions
ipal+0.416
init+0.413
shift+0.386
actory+0.384
ounge+0.368
Neg logit contributions
 Dent-0.558
 Nadu-0.538
 Devi-0.526
 Equity-0.496
iaz-0.496
Token in
Token ID287
Feature activation+4.83e-01

Pos logit contributions
ipal+1.022
init+1.010
shift+0.951
actory+0.944
itual+0.906
Neg logit contributions
 Dent-1.226
 Nadu-1.181
 Devi-1.151
 Equity-1.079
iaz-1.079
Token number
Token ID1271
Feature activation+9.26e-01

Pos logit contributions
ipal+0.281
init+0.277
shift+0.258
actory+0.256
ounge+0.246
Neg logit contributions
 Dent-0.442
 Nadu-0.427
 Devi-0.419
 Equity-0.394
iaz-0.394
Token:
Token ID25
Feature activation+1.16e+00

Pos logit contributions
ipal+0.644
init+0.634
shift+0.598
actory+0.596
ounge+0.577
Neg logit contributions
 Dent-0.744
 Nadu-0.715
 Devi-0.699
 Equity-0.654
 Benefit-0.651
Token Fro
Token ID9734
Feature activation+2.87e+00

Pos logit contributions
ipal+0.936
init+0.921
shift+0.877
actory+0.872
ounge+0.845
Neg logit contributions
 Dent-0.791
 Nadu-0.764
 Devi-0.734
iaz-0.685
 Equity-0.684
Token regulating
Token ID26379
Feature activation+1.91e-01

Pos logit contributions
ipal+0.095
init+0.093
shift+0.088
actory+0.087
ounge+0.084
Neg logit contributions
 Dent-0.110
 Nadu-0.105
 Devi-0.103
 Equity-0.096
 Benefit-0.096
Token the
Token ID262
Feature activation+2.16e-01

Pos logit contributions
ipal+0.137
init+0.134
shift+0.127
actory+0.126
ounge+0.121
Neg logit contributions
 Dent-0.150
 Nadu-0.143
 Devi-0.140
 Equity-0.131
 Benefit-0.131
Token use
Token ID779
Feature activation-3.25e-02

Pos logit contributions
ipal+0.142
init+0.139
shift+0.131
actory+0.130
ounge+0.125
Neg logit contributions
 Dent-0.181
 Nadu-0.174
 Devi-0.170
 Equity-0.160
 Benefit-0.160
Token of
Token ID286
Feature activation+2.19e-01

Pos logit contributions
 Dent+0.025
 Nadu+0.024
 Devi+0.024
 Equity+0.022
 Benefit+0.022
Neg logit contributions
ipal-0.023
init-0.023
actory-0.022
shift-0.022
ounge-0.021
Token the
Token ID262
Feature activation+3.90e-01

Pos logit contributions
ipal+0.154
init+0.151
shift+0.143
actory+0.142
itual+0.137
Neg logit contributions
 Dent-0.174
 Nadu-0.167
 Devi-0.163
 Benefit-0.153
 Equity-0.153
Token agricultural
Token ID14240
Feature activation+1.25e+00

Pos logit contributions
ipal+0.275
init+0.269
shift+0.254
actory+0.253
ounge+0.243
Neg logit contributions
 Dent-0.308
 Nadu-0.296
 Devi-0.288
 Benefit-0.270
 Equity-0.270
Token lands
Token ID8604
Feature activation+1.37e-01

Pos logit contributions
ipal+0.813
init+0.798
actory+0.753
shift+0.751
ounge+0.715
Neg logit contributions
 Dent-1.052
 Nadu-1.008
 Devi-0.989
 Equity-0.928
 Benefit-0.927
Token.
Token ID13
Feature activation+2.83e-01

Pos logit contributions
ipal+0.096
init+0.095
shift+0.089
actory+0.089
ounge+0.086
Neg logit contributions
 Dent-0.109
 Nadu-0.104
 Devi-0.102
 Equity-0.095
 Benefit-0.095
Token Such
Token ID8013
Feature activation+3.04e-01

Pos logit contributions
ipal+0.210
init+0.207
shift+0.196
actory+0.194
itual+0.188
Neg logit contributions
 Dent-0.209
 Nadu-0.202
 Devi-0.196
iaz-0.185
 Equity-0.182
Token changes
Token ID2458
Feature activation-1.43e-01

Pos logit contributions
ipal+0.213
init+0.209
shift+0.199
actory+0.198
 selector+0.188
Neg logit contributions
 Dent-0.244
 Nadu-0.229
 Devi-0.227
iaz-0.213
 Benefit-0.213
Token could
Token ID714
Feature activation+3.26e-01

Pos logit contributions
 Dent+0.115
 Nadu+0.110
 Devi+0.108
 Equity+0.101
 Benefit+0.101
Neg logit contributions
ipal-0.100
init-0.098
shift-0.093
actory-0.093
ounge-0.089
Token Turner
Token ID15406
Feature activation+4.32e-01

Pos logit contributions
ipal+0.368
init+0.363
shift+0.346
actory+0.345
ounge+0.336
Neg logit contributions
 Dent-0.305
 Nadu-0.290
 Devi-0.283
 Equity-0.261
 Benefit-0.260
Token,
Token ID11
Feature activation-1.86e-01

Pos logit contributions
ipal+0.299
init+0.294
shift+0.277
actory+0.276
ounge+0.267
Neg logit contributions
 Dent-0.349
 Nadu-0.336
 Devi-0.327
 Equity-0.307
iaz-0.306
Token but
Token ID475
Feature activation-9.84e-01

Pos logit contributions
 Dent+0.147
 Nadu+0.141
 Devi+0.136
iaz+0.129
 Equity+0.128
Neg logit contributions
ipal-0.132
init-0.130
shift-0.122
actory-0.121
ounge-0.118
Token it
Token ID340
Feature activation-2.50e-01

Pos logit contributions
 Dent+0.755
 Nadu+0.722
 Devi+0.699
iaz+0.656
 Equity+0.653
Neg logit contributions
ipal-0.721
init-0.712
shift-0.672
actory-0.670
ounge-0.645
Token has
Token ID468
Feature activation-4.17e-01

Pos logit contributions
 Dent+0.202
 Nadu+0.194
 Devi+0.189
 Equity+0.177
 Benefit+0.176
Neg logit contributions
ipal-0.175
init-0.172
shift-0.162
actory-0.161
ounge-0.156
Token inexpl
Token ID33199
Feature activation+4.09e-01

Pos logit contributions
 Dent+0.317
 Nadu+0.304
 Devi+0.295
 Equity+0.276
iaz+0.275
Neg logit contributions
ipal-0.308
init-0.305
shift-0.288
actory-0.285
ounge-0.277
Tokenicably
Token ID41685
Feature activation+5.89e-01

Pos logit contributions
init+0.243
ipal+0.241
actory+0.222
shift+0.219
itual+0.212
Neg logit contributions
 Dent-0.379
 Nadu-0.368
 Devi-0.360
 Benefit-0.339
 Equity-0.338
Token been
Token ID587
Feature activation+2.56e-01

Pos logit contributions
ipal+0.416
init+0.413
shift+0.388
actory+0.380
 scrambled+0.373
Neg logit contributions
 Dent-0.463
 Nadu-0.448
 Devi-0.432
 Equity-0.408
iaz-0.406
Token censored
Token ID43847
Feature activation-1.49e+00

Pos logit contributions
ipal+0.148
init+0.146
shift+0.137
actory+0.134
ounge+0.130
Neg logit contributions
 Dent-0.235
 Nadu-0.227
 Devi-0.221
 Benefit-0.211
 Equity-0.210
Token by
Token ID416
Feature activation-3.46e-02

Pos logit contributions
 Dent+1.170
 Nadu+1.120
 Devi+1.096
 Equity+1.023
 Benefit+1.019
Neg logit contributions
ipal-1.061
init-1.042
shift-0.987
actory-0.985
ounge-0.954
Token the
Token ID262
Feature activation+1.03e-01

Pos logit contributions
 Dent+0.025
 Nadu+0.024
 Devi+0.024
iaz+0.022
 Benefit+0.022
Neg logit contributions
ipal-0.026
init-0.026
shift-0.025
actory-0.024
ounge-0.024
Token of
Token ID286
Feature activation-8.29e-02

Pos logit contributions
 Dent+0.407
 Nadu+0.389
 Devi+0.381
 Equity+0.355
 Benefit+0.354
Neg logit contributions
ipal-0.362
init-0.356
actory-0.335
shift-0.335
ounge-0.325
Token debris
Token ID16468
Feature activation-1.03e-01

Pos logit contributions
 Dent+0.061
 Nadu+0.058
 Devi+0.057
 Equity+0.053
 Benefit+0.052
Neg logit contributions
ipal-0.064
init-0.063
shift-0.059
actory-0.059
ounge-0.058
Token it
Token ID340
Feature activation+1.62e-01

Pos logit contributions
 Dent+0.079
 Nadu+0.076
 Devi+0.074
 Equity+0.070
iaz+0.069
Neg logit contributions
ipal-0.075
init-0.074
shift-0.071
actory-0.070
ounge-0.068
Token takes
Token ID2753
Feature activation-7.84e-01

Pos logit contributions
ipal+0.107
init+0.106
actory+0.099
shift+0.099
ounge+0.095
Neg logit contributions
 Dent-0.135
 Nadu-0.131
 Devi-0.127
 Equity-0.121
 Benefit-0.120
Token to
Token ID284
Feature activation+7.27e-02

Pos logit contributions
 Dent+0.578
 Nadu+0.552
 Devi+0.539
 Equity+0.501
 Benefit+0.499
Neg logit contributions
ipal-0.599
init-0.589
shift-0.560
actory-0.559
ounge-0.542
Token kill
Token ID1494
Feature activation+2.23e-01

Pos logit contributions
ipal+0.044
init+0.043
shift+0.041
actory+0.041
ounge+0.038
Neg logit contributions
 Dent-0.065
 Nadu-0.063
 Devi-0.062
 Equity-0.058
iaz-0.058
Token a
Token ID257
Feature activation-5.00e-02

Pos logit contributions
ipal+0.186
init+0.184
shift+0.176
actory+0.175
ounge+0.170
Neg logit contributions
 Dent-0.148
 Nadu-0.140
 Devi-0.137
 Equity-0.127
iaz-0.126
Token turtle
Token ID28699
Feature activation-7.10e-01

Pos logit contributions
 Dent+0.039
 Nadu+0.038
 Devi+0.037
 Equity+0.035
 Benefit+0.034
Neg logit contributions
ipal-0.036
init-0.035
shift-0.033
actory-0.033
ounge-0.032
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
 Dent+0.569
 Nadu+0.546
 Devi+0.534
 Equity+0.500
 Benefit+0.498
Neg logit contributions
ipal-0.496
init-0.487
shift-0.460
actory-0.460
ounge-0.445
Token
Token ID198
Feature activation-2.66e-01

Pos logit contributions
 Dent+0.232
 Nadu+0.222
 Devi+0.217
 Equity+0.202
 Benefit+0.201
Neg logit contributions
ipal-0.221
init-0.217
shift-0.206
actory-0.206
ounge-0.199
Token
Token ID198
Feature activation-3.73e-01

Pos logit contributions
 Dent+0.228
 Nadu+0.222
 Devi+0.217
iaz+0.202
 Equity+0.202
Neg logit contributions
init-0.172
ipal-0.169
shift-0.161
actory-0.157
photo-0.150
Token to
Token ID284
Feature activation+3.67e-01

Pos logit contributions
 Dent+0.945
 Nadu+0.895
 Devi+0.881
 Equity+0.817
 Benefit+0.810
Neg logit contributions
ipal-0.996
init-0.981
actory-0.938
shift-0.935
itual-0.905
Token ethics
Token ID14458
Feature activation+4.07e-01

Pos logit contributions
ipal+0.253
init+0.247
shift+0.234
actory+0.233
ounge+0.226
Neg logit contributions
 Dent-0.297
 Nadu-0.285
 Devi-0.279
iaz-0.260
 Benefit-0.260
Token commissioner
Token ID16248
Feature activation-3.20e-01

Pos logit contributions
ipal+0.335
init+0.330
shift+0.314
actory+0.314
ounge+0.305
Neg logit contributions
 Dent-0.277
 Nadu-0.263
 Devi-0.257
 Equity-0.237
 Benefit-0.236
Token,
Token ID11
Feature activation-1.18e-01

Pos logit contributions
 Dent+0.245
 Nadu+0.234
 Devi+0.229
 Equity+0.213
 Benefit+0.212
Neg logit contributions
ipal-0.235
init-0.231
shift-0.219
actory-0.219
itual-0.212
Token would
Token ID561
Feature activation-4.33e-01

Pos logit contributions
 Dent+0.097
 Nadu+0.093
 Devi+0.091
 Equity+0.085
 Benefit+0.085
Neg logit contributions
ipal-0.080
init-0.078
shift-0.074
actory-0.074
ounge-0.071
Token be
Token ID307
Feature activation+4.83e-02

Pos logit contributions
 Dent+0.356
 Nadu+0.342
 Devi+0.335
 Equity+0.313
 Benefit+0.312
Neg logit contributions
ipal-0.293
init-0.289
shift-0.273
actory-0.272
ounge-0.263
Token affected
Token ID5676
Feature activation+6.07e-01

Pos logit contributions
ipal+0.032
init+0.031
shift+0.029
actory+0.029
ounge+0.028
Neg logit contributions
 Dent-0.040
 Nadu-0.039
 Devi-0.038
iaz-0.036
 Benefit-0.036
Token.
Token ID13
Feature activation-5.26e-01

Pos logit contributions
ipal+0.420
init+0.414
shift+0.390
actory+0.390
ounge+0.377
Neg logit contributions
 Dent-0.489
 Nadu-0.469
 Devi-0.460
 Equity-0.430
 Benefit-0.428
Token
Token ID198
Feature activation-6.31e-02

Pos logit contributions
 Dent+0.382
 Nadu+0.366
 Devi+0.357
iaz+0.331
 Equity+0.330
Neg logit contributions
ipal-0.405
init-0.399
shift-0.379
actory-0.377
ounge-0.367
Token
Token ID198
Feature activation-2.14e-01

Pos logit contributions
 Dent+0.054
 Nadu+0.053
 Devi+0.052
iaz+0.048
 Equity+0.048
Neg logit contributions
init-0.040
ipal-0.040
shift-0.038
actory-0.037
photo-0.035
TokenPar
Token ID10044
Feature activation-6.72e-01

Pos logit contributions
 Dent+0.178
 Nadu+0.171
 Devi+0.168
 Equity+0.157
 Benefit+0.157
Neg logit contributions
ipal-0.142
init-0.140
shift-0.132
actory-0.131
ounge-0.127
Token.
Token ID13
Feature activation+1.15e-01

Pos logit contributions
 Dent+0.595
 Nadu+0.571
 Devi+0.558
 Equity+0.522
 Benefit+0.520
Neg logit contributions
ipal-0.502
init-0.494
shift-0.466
actory-0.465
ounge-0.450
Token<|endoftext|>
Token ID50256
Feature activation+1.21e+00

Pos logit contributions
ipal+0.080
init+0.079
shift+0.074
actory+0.074
ounge+0.072
Neg logit contributions
 Dent-0.092
 Nadu-0.089
 Devi-0.087
 Equity-0.081
 Benefit-0.081
TokenC
Token ID34
Feature activation+4.67e-01

Pos logit contributions
ipal+0.780
init+0.771
shift+0.724
actory+0.718
ounge+0.693
Neg logit contributions
 Dent-1.033
 Nadu-0.991
 Devi-0.972
 Equity-0.912
 Benefit-0.909
Tokenort
Token ID419
Feature activation+7.24e-01

Pos logit contributions
ipal+0.358
init+0.353
actory+0.334
shift+0.333
ounge+0.324
Neg logit contributions
 Dent-0.345
 Nadu-0.329
 Devi-0.323
 Equity-0.298
 Benefit-0.296
Tokenic
Token ID291
Feature activation-1.56e+00

Pos logit contributions
ipal+0.479
init+0.470
shift+0.443
actory+0.442
ounge+0.427
Neg logit contributions
 Dent-0.607
 Nadu-0.583
 Devi-0.571
 Equity-0.535
 Benefit-0.534
Tokenotrop
Token ID34248
Feature activation-2.03e+00

Pos logit contributions
 Dent+0.967
 Nadu+0.915
 Devi+0.896
 Equity+0.816
 Benefit+0.814
Neg logit contributions
ipal-1.372
init-1.354
shift-1.290
actory-1.288
ounge-1.259
Tokenin
Token ID259
Feature activation-5.79e-01

Pos logit contributions
 Dent+1.567
 Nadu+1.502
 Devi+1.469
 Equity+1.369
 Benefit+1.361
Neg logit contributions
ipal-1.490
init-1.467
actory-1.385
shift-1.384
ounge-1.339
Token-
Token ID12
Feature activation-1.17e-01

Pos logit contributions
 Dent+0.466
 Nadu+0.447
 Devi+0.437
 Equity+0.409
 Benefit+0.407
Neg logit contributions
ipal-0.402
init-0.395
shift-0.373
actory-0.372
ounge-0.360
Tokenre
Token ID260
Feature activation-1.73e+00

Pos logit contributions
 Dent+0.088
 Nadu+0.084
 Devi+0.083
 Equity+0.077
 Benefit+0.076
Neg logit contributions
ipal-0.088
init-0.087
shift-0.083
actory-0.082
itual-0.079
Tokenleasing
Token ID48764
Feature activation-1.00e+00

Pos logit contributions
 Dent+1.374
 Nadu+1.306
 Devi+1.281
iaz+1.204
 Equity+1.203
Neg logit contributions
ipal-1.213
init-1.183
shift-1.130
actory-1.119
ounge-1.102
Token factor
Token ID5766
Feature activation-1.34e+00

Pos logit contributions
 Dent+0.810
 Nadu+0.775
 Devi+0.759
 Equity+0.710
 Benefit+0.707
Neg logit contributions
ipal-0.697
init-0.683
shift-0.646
actory-0.644
ounge-0.624
Token record
Token ID1700
Feature activation+1.34e+00

Pos logit contributions
ipal+0.136
init+0.133
shift+0.124
actory+0.123
ounge+0.118
Neg logit contributions
 Dent-0.232
 Nadu-0.224
 Devi-0.219
 Equity-0.207
 Benefit-0.207
Token with
Token ID351
Feature activation+6.82e-01

Pos logit contributions
ipal+1.003
init+0.988
shift+0.937
actory+0.934
ounge+0.907
Neg logit contributions
 Dent-0.998
 Nadu-0.957
 Devi-0.934
 Equity-0.870
 Benefit-0.866
Token 18
Token ID1248
Feature activation+1.07e+00

Pos logit contributions
ipal+0.425
init+0.418
actory+0.392
shift+0.391
ounge+0.377
Neg logit contributions
 Dent-0.595
 Nadu-0.573
 Devi-0.563
 Equity-0.529
 Benefit-0.529
Token,
Token ID11
Feature activation+2.26e-01

Pos logit contributions
ipal+0.707
init+0.696
actory+0.656
shift+0.655
ounge+0.631
Neg logit contributions
 Dent-0.896
 Nadu-0.860
 Devi-0.842
 Equity-0.790
 Benefit-0.788
Token355
Token ID28567
Feature activation+1.84e-01

Pos logit contributions
ipal+0.139
init+0.136
shift+0.127
actory+0.127
ounge+0.122
Neg logit contributions
 Dent-0.200
 Nadu-0.193
 Devi-0.189
 Equity-0.178
 Benefit-0.177
Token career
Token ID3451
Feature activation-1.95e-01

Pos logit contributions
ipal+0.111
init+0.109
actory+0.102
shift+0.102
ounge+0.098
Neg logit contributions
 Dent-0.165
 Nadu-0.159
 Devi-0.156
 Equity-0.147
 Benefit-0.147
Token yards
Token ID5695
Feature activation+9.60e-01

Pos logit contributions
 Dent+0.172
 Nadu+0.165
 Devi+0.162
 Equity+0.152
 Benefit+0.152
Neg logit contributions
ipal-0.120
init-0.118
shift-0.111
actory-0.111
ounge-0.106
Token.
Token ID13
Feature activation+4.41e-01

Pos logit contributions
ipal+0.660
init+0.648
actory+0.611
shift+0.609
ounge+0.588
Neg logit contributions
 Dent-0.778
 Nadu-0.747
 Devi-0.730
 Equity-0.688
 Benefit-0.684
Token
Token ID198
Feature activation+2.97e-01

Pos logit contributions
ipal+0.315
init+0.312
shift+0.295
actory+0.293
ounge+0.284
Neg logit contributions
 Dent-0.340
 Nadu-0.329
 Devi-0.320
 Equity-0.299
iaz-0.298
Token
Token ID198
Feature activation+1.76e-01

Pos logit contributions
init+0.192
ipal+0.188
shift+0.179
actory+0.175
photo+0.168
Neg logit contributions
 Dent-0.255
 Nadu-0.248
 Devi-0.242
 Equity-0.226
iaz-0.226
TokenC
Token ID34
Feature activation+9.76e-01

Pos logit contributions
ipal+0.112
init+0.111
shift+0.104
actory+0.103
ounge+0.100
Neg logit contributions
 Dent-0.151
 Nadu-0.145
 Devi-0.143
 Equity-0.134
 Benefit-0.134
Token're
Token ID821
Feature activation+9.91e-01

Pos logit contributions
ipal+0.186
init+0.185
shift+0.175
actory+0.175
ounge+0.168
Neg logit contributions
 Dent-0.208
 Nadu-0.200
 Devi-0.196
iaz-0.183
 Equity-0.183
Token not
Token ID407
Feature activation-6.65e-01

Pos logit contributions
ipal+0.652
init+0.650
shift+0.605
actory+0.603
ounge+0.580
Neg logit contributions
 Dent-0.826
 Nadu-0.796
 Devi-0.775
iaz-0.734
 Benefit-0.731
Token ready
Token ID3492
Feature activation-1.85e+00

Pos logit contributions
 Dent+0.547
 Nadu+0.526
 Devi+0.514
iaz+0.483
 Benefit+0.481
Neg logit contributions
ipal-0.449
init-0.444
shift-0.417
actory-0.417
ounge-0.401
Token to
Token ID284
Feature activation-6.74e-02

Pos logit contributions
 Dent+1.292
 Nadu+1.230
 Devi+1.195
 Equity+1.113
 Benefit+1.105
Neg logit contributions
ipal-1.470
init-1.446
shift-1.379
actory-1.376
ounge-1.343
Token show
Token ID905
Feature activation+1.37e+00

Pos logit contributions
 Dent+0.054
 Nadu+0.052
 Devi+0.051
 Equity+0.047
iaz+0.047
Neg logit contributions
ipal-0.047
init-0.047
actory-0.044
shift-0.044
ounge-0.042
Token you
Token ID345
Feature activation-1.92e-01

Pos logit contributions
ipal+0.951
init+0.939
shift+0.892
actory+0.888
ounge+0.853
Neg logit contributions
 Dent-1.099
 Nadu-1.059
 Devi-1.029
iaz-0.970
 Benefit-0.960
Token what
Token ID644
Feature activation+8.54e-03

Pos logit contributions
 Dent+0.143
 Nadu+0.137
 Devi+0.133
iaz+0.125
 Benefit+0.123
Neg logit contributions
ipal-0.144
init-0.143
shift-0.136
actory-0.135
ounge-0.130
Token we
Token ID356
Feature activation+4.55e-01

Pos logit contributions
ipal+0.007
init+0.006
shift+0.006
actory+0.006
ounge+0.006
Neg logit contributions
 Dent-0.006
 Nadu-0.006
 Devi-0.006
iaz-0.005
 Equity-0.005
Token've
Token ID1053
Feature activation+4.36e-01

Pos logit contributions
ipal+0.322
init+0.318
actory+0.303
shift+0.299
ounge+0.287
Neg logit contributions
 Dent-0.359
 Nadu-0.348
 Devi-0.339
iaz-0.316
 Equity-0.315
Token been
Token ID587
Feature activation+2.33e-01

Pos logit contributions
ipal+0.324
init+0.322
actory+0.303
shift+0.302
ounge+0.291
Neg logit contributions
 Dent-0.330
 Nadu-0.318
 Devi-0.306
iaz-0.288
 Benefit-0.287
Token working
Token ID1762
Feature activation-1.35e-01

Pos logit contributions
ipal+0.143
init+0.142
shift+0.133
actory+0.133
ounge+0.126
Neg logit contributions
 Dent-0.206
 Nadu-0.199
 Devi-0.193
iaz-0.183
 Equity-0.183
Token Jade
Token ID23386
Feature activation+1.66e+00

Pos logit contributions
 Dent+0.536
 Nadu+0.515
 Devi+0.504
 Equity+0.470
 Benefit+0.470
Neg logit contributions
ipal-0.449
init-0.442
shift-0.418
actory-0.416
ounge-0.402
Token Helm
Token ID28351
Feature activation-3.32e+00

Pos logit contributions
ipal+1.492
init+1.480
shift+1.424
actory+1.411
ounge+1.379
Neg logit contributions
 Dent-0.982
 Nadu-0.922
 Devi-0.892
 Equity-0.813
 Benefit-0.810
Token 15
Token ID1315
Feature activation+3.22e-01

Pos logit contributions
 Dent+2.966
 Nadu+2.820
 Devi+2.809
 Equity+2.649
 Benefit+2.644
Neg logit contributions
ipal-2.031
init-1.949
actory-1.842
shift-1.827
ounge-1.795
Token operation
Token ID4905
Feature activation+6.08e-01

Pos logit contributions
ipal+0.211
init+0.208
shift+0.196
actory+0.196
ounge+0.188
Neg logit contributions
 Dent-0.271
 Nadu-0.261
 Devi-0.255
 Equity-0.239
 Benefit-0.238
Token across
Token ID1973
Feature activation-6.80e-01

Pos logit contributions
ipal+0.428
init+0.424
shift+0.402
actory+0.399
ounge+0.385
Neg logit contributions
 Dent-0.481
 Nadu-0.461
 Devi-0.450
 Equity-0.420
iaz-0.418
Token the
Token ID262
Feature activation+4.32e-02

Pos logit contributions
 Dent+0.483
 Nadu+0.460
 Devi+0.449
 Equity+0.416
 Benefit+0.414
Neg logit contributions
ipal-0.538
init-0.529
shift-0.503
actory-0.502
ounge-0.489
Token southwest
Token ID26283
Feature activation+1.86e+00

Pos logit contributions
ipal+0.029
init+0.028
shift+0.026
actory+0.026
ounge+0.025
Neg logit contributions
 Dent-0.036
 Nadu-0.035
 Devi-0.034
 Equity-0.032
 Benefit-0.032
Token continue
Token ID2555
Feature activation+2.97e-01

Pos logit contributions
ipal+1.316
init+1.297
shift+1.232
actory+1.224
ounge+1.184
Neg logit contributions
 Dent-1.458
 Nadu-1.401
 Devi-1.366
 Benefit-1.269
iaz-1.268
Token to
Token ID284
Feature activation+1.19e-02

Pos logit contributions
ipal+0.223
init+0.219
shift+0.208
actory+0.207
ounge+0.201
Neg logit contributions
 Dent-0.223
 Nadu-0.213
 Devi-0.208
 Equity-0.193
 Benefit-0.193
Token suggest
Token ID1950
Feature activation-1.06e-01

Pos logit contributions
ipal+0.008
init+0.008
shift+0.008
actory+0.008
ounge+0.007
Neg logit contributions
 Dent-0.010
 Nadu-0.009
 Devi-0.009
 Equity-0.008
 Benefit-0.008
Token that
Token ID326
Feature activation-1.31e-01

Pos logit contributions
 Dent+0.081
 Nadu+0.078
 Devi+0.076
 Equity+0.071
 Benefit+0.070
Neg logit contributions
ipal-0.077
init-0.076
shift-0.072
actory-0.072
ounge-0.069
Token first
Token ID717
Feature activation-1.21e+00

Pos logit contributions
 Dent+0.373
 Nadu+0.361
 Devi+0.353
 Equity+0.331
 Benefit+0.330
Neg logit contributions
ipal-0.280
init-0.276
shift-0.259
actory-0.258
ounge-0.249
Token it
Token ID340
Feature activation-6.38e-01

Pos logit contributions
 Dent+0.857
 Nadu+0.822
 Devi+0.800
 Equity+0.741
 Benefit+0.737
Neg logit contributions
ipal-0.946
init-0.935
shift-0.889
actory-0.888
ounge-0.861
Token blew
Token ID17948
Feature activation-2.93e-02

Pos logit contributions
 Dent+0.504
 Nadu+0.484
 Devi+0.472
 Equity+0.444
 Benefit+0.441
Neg logit contributions
ipal-0.453
init-0.447
shift-0.421
actory-0.421
ounge-0.407
Token me
Token ID502
Feature activation-5.51e-01

Pos logit contributions
 Dent+0.023
 Nadu+0.022
 Devi+0.022
iaz+0.021
 Equity+0.020
Neg logit contributions
ipal-0.020
init-0.020
shift-0.019
actory-0.019
ounge-0.018
Token away
Token ID1497
Feature activation+3.24e-02

Pos logit contributions
 Dent+0.456
 Nadu+0.438
 Devi+0.429
 Equity+0.402
 Benefit+0.400
Neg logit contributions
ipal-0.370
init-0.364
shift-0.343
actory-0.342
ounge-0.331
Token",
Token ID1600
Feature activation-2.97e+00

Pos logit contributions
ipal+0.023
init+0.023
shift+0.022
actory+0.022
ounge+0.021
Neg logit contributions
 Dent-0.025
 Nadu-0.024
 Devi-0.024
 Equity-0.022
 Benefit-0.022
Token Ms
Token ID6997
Feature activation-4.89e-01

Pos logit contributions
 Dent+2.130
 Nadu+2.002
 Devi+1.960
 Equity+1.815
 Benefit+1.811
Neg logit contributions
ipal-2.347
init-2.298
shift-2.194
actory-2.185
ounge-2.130
Token Al
Token ID978
Feature activation-8.69e-01

Pos logit contributions
 Dent+0.358
 Nadu+0.341
 Devi+0.333
 Equity+0.309
 Benefit+0.308
Neg logit contributions
ipal-0.377
init-0.370
shift-0.352
actory-0.351
ounge-0.342
Tokenbr
Token ID1671
Feature activation+1.77e+00

Pos logit contributions
 Dent+0.798
 Nadu+0.770
 Devi+0.757
 Equity+0.712
 Benefit+0.705
Neg logit contributions
ipal-0.517
init-0.510
shift-0.478
actory-0.469
ounge-0.451
Tokenitton
Token ID47304
Feature activation+2.63e-01

Pos logit contributions
init+0.509
ipal+0.497
shift+0.428
actory+0.416
ounge+0.400
Neg logit contributions
 Dent-2.158
 Devi-2.100
 Nadu-2.097
 Equity-2.007
 Benefit-1.992
Token said
Token ID531
Feature activation-7.39e-01

Pos logit contributions
ipal+0.174
init+0.171
shift+0.161
actory+0.160
ounge+0.156
Neg logit contributions
 Dent-0.219
 Nadu-0.213
 Devi-0.206
 Equity-0.195
 Benefit-0.194
Token was
Token ID373
Feature activation-3.02e-01

Pos logit contributions
ipal+0.284
init+0.280
shift+0.263
actory+0.263
ounge+0.253
Neg logit contributions
 Dent-0.333
 Nadu-0.320
 Devi-0.312
 Equity-0.295
 Benefit-0.293
Token as
Token ID355
Feature activation+2.14e-01

Pos logit contributions
 Dent+0.221
 Nadu+0.210
 Devi+0.205
 Equity+0.192
 Benefit+0.190
Neg logit contributions
ipal-0.232
init-0.228
shift-0.217
actory-0.216
itual-0.210
Token if
Token ID611
Feature activation-2.81e-01

Pos logit contributions
ipal+0.150
init+0.147
actory+0.139
shift+0.139
itual+0.133
Neg logit contributions
 Dent-0.171
 Nadu-0.164
 Devi-0.159
 Equity-0.150
 Benefit-0.149
Token at
Token ID379
Feature activation-5.24e-01

Pos logit contributions
 Dent+0.208
 Nadu+0.199
 Devi+0.193
 Equity+0.181
iaz+0.180
Neg logit contributions
ipal-0.212
init-0.209
shift-0.199
actory-0.198
ounge-0.191
Token this
Token ID428
Feature activation-6.07e-02

Pos logit contributions
 Dent+0.392
 Nadu+0.375
 Devi+0.367
 Equity+0.342
 Benefit+0.340
Neg logit contributions
ipal-0.393
init-0.388
shift-0.367
actory-0.367
ounge-0.356
Token moment
Token ID2589
Feature activation-3.16e+00

Pos logit contributions
 Dent+0.036
 Nadu+0.034
 Devi+0.033
 Equity+0.030
 Benefit+0.030
Neg logit contributions
ipal-0.055
init-0.054
shift-0.052
actory-0.052
ounge-0.050
Token they
Token ID484
Feature activation-5.49e-01

Pos logit contributions
 Dent+2.314
 Nadu+2.209
 Devi+2.158
 Equity+1.990
 Benefit+1.983
Neg logit contributions
ipal-2.426
init-2.386
shift-2.263
actory-2.259
ounge-2.206
Token shared
Token ID4888
Feature activation+6.42e-02

Pos logit contributions
 Dent+0.445
 Nadu+0.426
 Devi+0.417
 Equity+0.391
 Benefit+0.389
Neg logit contributions
ipal-0.379
init-0.373
shift-0.352
actory-0.352
ounge-0.340
Token a
Token ID257
Feature activation-1.04e-01

Pos logit contributions
ipal+0.052
init+0.052
shift+0.049
actory+0.049
ounge+0.048
Neg logit contributions
 Dent-0.044
 Nadu-0.042
 Devi-0.041
 Equity-0.038
 Benefit-0.037
Token single
Token ID2060
Feature activation+3.41e-01

Pos logit contributions
 Dent+0.084
 Nadu+0.080
 Devi+0.078
 Equity+0.073
 Benefit+0.073
Neg logit contributions
ipal-0.073
init-0.072
shift-0.068
actory-0.068
ounge-0.065
Token awareness
Token ID9359
Feature activation+2.25e-02

Pos logit contributions
ipal+0.235
init+0.231
shift+0.219
actory+0.219
ounge+0.211
Neg logit contributions
 Dent-0.275
 Nadu-0.264
 Devi-0.258
 Equity-0.241
iaz-0.241
Token Title
Token ID11851
Feature activation-8.74e-01

Pos logit contributions
 Dent+0.282
 Nadu+0.269
 Devi+0.263
 Equity+0.242
 Benefit+0.242
Neg logit contributions
ipal-0.308
init-0.303
shift-0.289
actory-0.287
ounge-0.279
Token VI
Token ID13889
Feature activation-1.07e+00

Pos logit contributions
 Dent+0.690
 Nadu+0.661
 Devi+0.647
 Equity+0.603
 Benefit+0.602
Neg logit contributions
ipal-0.621
init-0.611
shift-0.578
actory-0.576
ounge-0.558
Token of
Token ID286
Feature activation-6.59e-01

Pos logit contributions
 Dent+0.861
 Nadu+0.825
 Devi+0.808
 Equity+0.756
 Benefit+0.753
Neg logit contributions
ipal-0.743
init-0.730
shift-0.689
actory-0.689
ounge-0.667
Token the
Token ID262
Feature activation-4.38e-03

Pos logit contributions
 Dent+0.478
 Nadu+0.457
 Devi+0.446
 Benefit+0.413
 Equity+0.412
Neg logit contributions
ipal-0.510
init-0.502
shift-0.478
actory-0.475
ounge-0.462
Token Civil
Token ID7511
Feature activation-9.07e-01

Pos logit contributions
 Dent+0.003
 Nadu+0.002
 Devi+0.002
 Benefit+0.002
iaz+0.002
Neg logit contributions
ipal-0.004
init-0.004
shift-0.004
actory-0.004
itual-0.004
Token Rights
Token ID6923
Feature activation-3.25e+00

Pos logit contributions
 Dent+0.503
 Nadu+0.479
 Devi+0.465
iaz+0.419
ouri+0.410
Neg logit contributions
ipal-0.851
init-0.837
actory-0.798
shift-0.797
itual-0.779
Token Act
Token ID2191
Feature activation-2.22e+00

Pos logit contributions
 Dent+1.441
 Nadu+1.335
 Devi+1.285
iaz+1.115
 Benefit+1.112
Neg logit contributions
ipal-3.440
init-3.398
shift-3.270
actory-3.263
itual-3.196
Token of
Token ID286
Feature activation-9.58e-01

Pos logit contributions
 Dent+1.735
 Nadu+1.658
 Devi+1.624
 Equity+1.524
 Benefit+1.510
Neg logit contributions
ipal-1.600
init-1.562
actory-1.492
shift-1.486
ounge-1.435
Token 1964
Token ID17575
Feature activation-2.30e+00

Pos logit contributions
 Dent+0.659
 Nadu+0.633
 Devi+0.618
iaz+0.559
ouri+0.558
Neg logit contributions
init-0.767
ipal-0.766
actory-0.730
shift-0.725
ounge-0.709
Token.
Token ID13
Feature activation-2.78e-01

Pos logit contributions
 Dent+1.793
 Nadu+1.720
 Devi+1.680
 Equity+1.570
 Benefit+1.562
Neg logit contributions
ipal-1.660
init-1.627
actory-1.550
shift-1.547
ounge-1.500
Token It
Token ID632
Feature activation-1.59e-01

Pos logit contributions
 Dent+0.186
 Nadu+0.178
 Devi+0.173
iaz+0.161
 Equity+0.157
Neg logit contributions
ipal-0.228
init-0.225
shift-0.216
actory-0.214
itual-0.208
Token available
Token ID1695
Feature activation-1.08e+00

Pos logit contributions
 Dent+0.566
 Nadu+0.542
 Devi+0.531
 Equity+0.496
 Benefit+0.494
Neg logit contributions
ipal-0.498
init-0.491
shift-0.464
actory-0.464
ounge-0.446
Token.
Token ID13
Feature activation-1.23e-01

Pos logit contributions
 Dent+0.835
 Nadu+0.799
 Devi+0.781
 Equity+0.728
 Benefit+0.726
Neg logit contributions
ipal-0.784
init-0.771
shift-0.731
actory-0.729
ounge-0.707
Token
Token ID198
Feature activation+7.81e-02

Pos logit contributions
 Dent+0.093
 Nadu+0.089
 Devi+0.087
iaz+0.081
 Equity+0.080
Neg logit contributions
ipal-0.091
init-0.090
shift-0.085
actory-0.085
ounge-0.082
Token
Token ID198
Feature activation-1.18e-01

Pos logit contributions
init+0.050
ipal+0.049
shift+0.047
actory+0.046
photo+0.044
Neg logit contributions
 Dent-0.067
 Nadu-0.065
 Devi-0.064
 Equity-0.060
iaz-0.059
TokenB
Token ID33
Feature activation+5.67e-01

Pos logit contributions
 Dent+0.100
 Nadu+0.096
 Devi+0.094
 Equity+0.088
 Benefit+0.087
Neg logit contributions
ipal-0.078
init-0.077
shift-0.072
actory-0.072
ounge-0.070
Tokenast
Token ID459
Feature activation-2.82e+00

Pos logit contributions
ipal+0.450
init+0.444
shift+0.422
actory+0.422
ounge+0.410
Neg logit contributions
 Dent-0.402
 Nadu-0.383
 Devi-0.373
 Equity-0.345
 Benefit-0.344
Tokenian
Token ID666
Feature activation-3.39e-01

Pos logit contributions
 Dent+2.077
 Nadu+1.982
 Devi+1.938
 Equity+1.798
 Benefit+1.789
Neg logit contributions
ipal-2.157
init-2.124
shift-2.014
actory-2.013
ounge-1.953
Token said
Token ID531
Feature activation-5.15e-02

Pos logit contributions
 Dent+0.266
 Nadu+0.255
 Devi+0.249
 Equity+0.232
 Benefit+0.232
Neg logit contributions
ipal-0.243
init-0.240
shift-0.226
actory-0.225
ounge-0.219
Token he
Token ID339
Feature activation+2.57e-01

Pos logit contributions
 Dent+0.038
 Nadu+0.036
 Devi+0.035
iaz+0.033
 Equity+0.033
Neg logit contributions
ipal-0.039
init-0.039
actory-0.037
shift-0.037
ounge-0.036
Token found
Token ID1043
Feature activation+4.70e-04

Pos logit contributions
ipal+0.175
init+0.173
actory+0.162
shift+0.162
ounge+0.156
Neg logit contributions
 Dent-0.210
 Nadu-0.202
 Devi-0.197
 Benefit-0.185
 Equity-0.185
Token it
Token ID340
Feature activation+3.31e-01

Pos logit contributions
ipal+0.000
init+0.000
actory+0.000
shift+0.000
ounge+0.000
Neg logit contributions
 Dent-0.000
 Nadu-0.000
 Devi-0.000
iaz-0.000
 Benefit-0.000
Token he
Token ID339
Feature activation-6.39e-01

Pos logit contributions
 Dent+0.801
 Nadu+0.767
 Devi+0.749
 Equity+0.699
 Benefit+0.696
Neg logit contributions
ipal-0.753
init-0.740
shift-0.701
actory-0.700
ounge-0.678
Token fell
Token ID3214
Feature activation-1.09e-01

Pos logit contributions
 Dent+0.530
 Nadu+0.510
 Devi+0.498
 Equity+0.468
 Benefit+0.467
Neg logit contributions
ipal-0.429
init-0.421
shift-0.396
actory-0.396
ounge-0.383
Token down
Token ID866
Feature activation-3.61e-01

Pos logit contributions
 Dent+0.088
 Nadu+0.084
 Devi+0.082
 Equity+0.078
 Benefit+0.077
Neg logit contributions
ipal-0.075
init-0.074
shift-0.070
actory-0.069
ounge-0.067
Token on
Token ID319
Feature activation-1.81e-01

Pos logit contributions
 Dent+0.291
 Nadu+0.279
 Devi+0.273
 Equity+0.256
 Benefit+0.255
Neg logit contributions
ipal-0.250
init-0.246
shift-0.232
actory-0.231
ounge-0.224
Token his
Token ID465
Feature activation-9.11e-01

Pos logit contributions
 Dent+0.136
 Nadu+0.130
 Devi+0.127
 Equity+0.118
 Benefit+0.118
Neg logit contributions
ipal-0.135
init-0.133
shift-0.126
actory-0.126
ounge-0.122
Token knees
Token ID14475
Feature activation-2.98e+00

Pos logit contributions
 Dent+0.703
 Nadu+0.673
 Devi+0.658
 Equity+0.613
 Benefit+0.611
Neg logit contributions
ipal-0.664
init-0.653
shift-0.619
actory-0.618
ounge-0.599
Token.
Token ID13
Feature activation-1.43e-01

Pos logit contributions
 Dent+2.270
 Nadu+2.159
 Devi+2.124
 Equity+1.953
 Benefit+1.953
Neg logit contributions
ipal-2.201
init-2.166
actory-2.064
shift-2.053
ounge-2.004
Token
Token ID564
Feature activation-3.37e-03

Pos logit contributions
 Dent+0.100
 Nadu+0.096
 Devi+0.093
iaz+0.087
 Equity+0.087
Neg logit contributions
ipal-0.112
init-0.111
shift-0.106
actory-0.105
ounge-0.102
Token
Token ID250
Feature activation+2.32e-01

Pos logit contributions
 Dent+0.003
 Nadu+0.003
 Devi+0.003
iaz+0.003
 Equity+0.003
Neg logit contributions
ipal-0.002
init-0.002
actory-0.001
shift-0.001
itual-0.001
TokenFor
Token ID1890
Feature activation-2.57e-01

Pos logit contributions
ipal+0.150
init+0.149
shift+0.141
actory+0.138
ounge+0.133
Neg logit contributions
 Dent-0.197
 Nadu-0.190
 Devi-0.186
 Equity-0.175
 Benefit-0.174
Tokengive
Token ID26535
Feature activation-1.95e+00

Pos logit contributions
 Dent+0.194
 Nadu+0.185
 Devi+0.181
 Equity+0.169
 Benefit+0.167
Neg logit contributions
ipal-0.192
init-0.188
shift-0.179
actory-0.178
ounge-0.172