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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a sentence or paragraph, indicated by specific formatting tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.89
     createState
    -0.87
    IntoConstraints
    -0.86
     ligiloj
    -0.86
     pleaſure
    -0.85
     stanovnika
    -0.85
    IsMutable
    -0.85
    出版年
    -0.84
    bootstrapcdn
    -0.83
    oredCriteria
    -0.83
    POSITIVE LOGITS
    [toxicity=0]
    1.93
     }^{*}$
    0.93
    帖最后由
    0.92
    /}
    0.79
     {*}
    0.74
     *}$
    0.71
     .=
    0.70
    *
    0.69
     *
    0.69
    ்கள்
    0.69
    Act Density 0.010%

    No Known Activations