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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sylv
    -0.82
    heast
    -0.75
    ghan
    -0.74
     Bagg
    -0.74
    ople
    -0.73
    ilus
    -0.71
     deregulation
    -0.69
    ricular
    -0.69
    anza
    -0.67
     ILCS
    -0.67
    POSITIVE LOGITS
    OTA
    0.66
    statement
    0.66
    cius
    0.64
    ciating
    0.63
     martial
    0.63
    ĨĴ
    0.62
    SHIP
    0.62
    PRES
    0.61
    igning
    0.61
     dice
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.