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

    Neuronpedia

    INDEX
    Explanations

    symbols or expressions related to mathematical or logical notation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Majefty
    -0.89
     pleaſure
    -0.79
     كومونز
    -0.79
     للاسماء
    -0.77
     purpoſe
    -0.77
     raiſ
    -0.75
    DrawerToggle
    -0.75
     Theſe
    -0.73
    encodeWith
    -0.73
     ſtre
    -0.71
    POSITIVE LOGITS
    </strong>
    0.50
     himo
    0.46
    G
    0.45
     G
    0.45
    madol
    0.45
    ti
    0.44
     us
    0.44
    AspNetCore
    0.44
     anyone
    0.43
     aceite
    0.42
    Act Density 0.000%

    No Known Activations