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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mathematical and theoretical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulemon
    -0.61
    chengladbach
    -0.57
    richtet
    -0.53
    AutoScale
    -0.52
    gonic
    -0.52
    unref
    -0.51
    aced
    -0.51
    endregion
    -0.51
    ような
    -0.51
    istoitu
    -0.51
    POSITIVE LOGITS
    fulness
    0.93
    neſs
    0.81
    veness
    0.77
    Carcinogenicity
    0.74
     itſelf
    0.73
    teness
    0.73
    IGENCE
    0.72
    wness
    0.71
    ateness
    0.69
     ence
    0.68
    Act Density 0.922%

    No Known Activations