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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ivas
    -0.88
    oidal
    -0.82
    zos
    -0.82
    iasco
    -0.80
    ortium
    -0.80
    lain
    -0.78
    oresc
    -0.74
    rane
    -0.74
    rification
    -0.73
    heast
    -0.71
    POSITIVE LOGITS
    tag
    0.69
    Ü
    0.62
    worthy
    0.61
     fictitious
    0.58
    venture
    0.57
    å¸
    0.57
    especially
    0.56
     distressed
    0.56
    tags
    0.55
    given
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.