INDEX
Explanations
mentions of the Sundance Film Festival
references to film festivals, particularly Sundance and Cannes
New Auto-Interp
Negative Logits
posit
-0.88
lectic
-0.76
vernment
-0.76
acters
-0.72
itably
-0.71
iliary
-0.69
therap
-0.67
berus
-0.65
clipboard
-0.64
hazard
-0.64
POSITIVE LOGITS
Sund
1.02
rained
0.97
ered
0.90
Sund
0.89
inguished
0.87
ance
0.86
icator
0.78
oing
0.77
vik
0.76
arb
0.75
Activations Density 0.027%