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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cynthia
    -0.68
     Sharing
    -0.67
    ĨĴ
    -0.65
     Kirin
    -0.65
     Taken
    -0.64
     Dialogue
    -0.64
     Devi
    -0.63
    zees
    -0.62
     Corpus
    -0.62
    IDA
    -0.61
    POSITIVE LOGITS
    hern
    0.95
    atche
    0.77
    plet
    0.75
    netflix
    0.73
    susp
    0.65
    si
    0.63
    kus
    0.63
    amiya
    0.62
    perties
    0.62
    ker
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.