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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical expressions and equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.57
    الإنجليزية
    -0.50
    RectangleBorder
    -0.49
     disponibilités
    -0.49
    +#+#
    -0.49
    raborty
    -0.49
    (!__
    -0.48
    Personensuche
    -0.48
    Хьажоргаш
    -0.47
    /******/
    -0.47
    POSITIVE LOGITS
     Efq
    0.81
    ſelves
    0.79
     Anſ
    0.74
     itſelf
    0.72
     fevere
    0.72
     preſent
    0.71
     myſelf
    0.71
    neſs
    0.69
     ſeveral
    0.69
     reaſon
    0.68
    Act Density 0.015%

    No Known Activations