INDEX
Explanations
instances of the word "time" preceded by specific context related to actions or events
mentions of "time."
New Auto-Interp
Negative Logits
ourt
-0.73
ipation
-0.73
XT
-0.72
addy
-0.71
oret
-0.71
arts
-0.69
inth
-0.68
irs
-0.67
extraord
-0.66
erto
-0.65
POSITIVE LOGITS
frame
0.82
someone
0.76
somebody
0.72
consuming
0.72
frames
0.68
frame
0.66
round
0.66
bitten
0.65
tasted
0.62
lapse
0.61
Activations Density 0.051%