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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting related to text structure in mathematical or technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MMdd
    -0.79
    ness
    -0.79
    原始内容存档于
    -0.75
    出版年
    -0.73
    bber
    -0.73
     չ
    -0.71
     createState
    -0.71
    šķ
    -0.71
     bers
    -0.70
     stanovnika
    -0.70
    POSITIVE LOGITS
    [toxicity=0]
    1.56
     }^{*}$
    1.05
    /}
    0.91
    *)
    0.82
     *}$
    0.81
     endblock
    0.80
     $*$
    0.79
    migrationBuilder
    0.78
    帖最后由
    0.78
    ')]
    0.77
    Act Density 0.012%

    No Known Activations