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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    croft
    -0.84
    ©¶æ¥µ
    -0.75
    AGE
    -0.74
    naire
    -0.72
    Ń·
    -0.69
    ģĸ
    -0.69
     Weinstein
    -0.67
    WAY
    -0.65
    ZI
    -0.65
     Wraith
    -0.65
    POSITIVE LOGITS
    agnetic
    0.81
    uten
    0.78
    tem
    0.77
    ilib
    0.72
    orns
    0.67
     mism
    0.63
    eneg
    0.63
    awar
    0.63
    ilit
    0.62
    ubb
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.