Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     droits
    1.33
     aquesta
    1.33
     enfer
    1.31
    setwd
    1.30
     direitos
    1.29
     éditions
    1.29
     ediciones
    1.28
     ré
    1.25
     Mend
    1.21
     заказ
    1.21
    POSITIVE LOGITS
    ل
    1.20
    odd
    1.18
    k
    1.15
     hypothetical
    1.12
    ாக்க
    1.08
    ार
    1.06
     ونص
    1.05
     ticking
    1.04
    ر
    1.00
    m
    1.00
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.