INDEX
Explanations
references to people named Kevin
mentions of the name "Kevin"
New Auto-Interp
Negative Logits
Sov
-0.79
opium
-0.76
gib
-0.69
inaccessible
-0.67
observ
-0.65
suppress
-0.64
sem
-0.62
INE
-0.62
âĹı
-0.62
+++
-0.62
POSITIVE LOGITS
Kevin
3.18
Kevin
2.84
Stephen
1.53
Jamie
1.51
Larry
1.51
Steve
1.50
Shaun
1.47
Chris
1.47
Brendan
1.47
Justin
1.46
Activations Density 0.023%