INDEX
Explanations
phrases that emphasize the concept of "matter" or significance in various contexts
New Auto-Interp
Negative Logits
ote
-0.18
runner
-0.18
sy
-0.17
other
-0.16
onda
-0.16
ery
-0.15
vie
-0.15
ynth
-0.15
iris
-0.15
ru
-0.15
POSITIVE LOGITS
-of
0.22
horn
0.19
urg
0.16
èĻ«
0.15
úb
0.15
amt
0.15
hf
0.15
inals
0.15
UIG
0.15
ìĦľëĬĶ
0.15
Activations Density 0.026%