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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Datuak
    -0.67
     <",
    -0.67
    jsii
    -0.58
    ʺ
    -0.58
     comune
    -0.56
    ㅤ
    -0.56
     ANGELES
    -0.56
    RegressionTest
    -0.56
    vatar
    -0.55
    Demografia
    -0.55
    POSITIVE LOGITS
     myſelf
    0.88
    ſelves
    0.83
     Beſ
    0.79
    ftance
    0.78
    ftances
    0.78
     Anſ
    0.77
     Reſ
    0.75
    RenderAtEndOf
    0.75
     auffi
    0.73
     itſelf
    0.72
    Act Density 0.159%

    No Known Activations