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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Brands
    -0.74
    oline
    -0.69
    onso
    -0.68
    oca
    -0.66
    isle
    -0.65
     sponsorship
    -0.65
    amily
    -0.64
    itamin
    -0.63
    oice
    -0.63
    espie
    -0.62
    POSITIVE LOGITS
    chest
    0.75
    ãģŁ
    0.71
     å¤
    0.70
    --------------------
    0.66
     sher
    0.65
     snapped
    0.65
     Kinder
    0.64
    ãģ¦
    0.64
    chedel
    0.64
     scram
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.