INDEX
Explanations
phrases containing the word "gate"
references to the word "gate" in various contexts
New Auto-Interp
Negative Logits
icio
-0.71
arya
-0.68
escription
-0.66
urgy
-0.65
achine
-0.65
ember
-0.64
inished
-0.64
inances
-0.64
etitive
-0.63
Norm
-0.62
POSITIVE LOGITS
gate
1.07
way
1.00
ways
0.91
Gate
0.88
keeper
0.88
boro
0.87
keepers
0.79
heads
0.76
plot
0.75
head
0.74
Activations Density 0.009%