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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or limitations in actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.77
    errHandler
    -0.74
     ModelExpression
    -0.73
    AddHtmlAttribute
    -0.69
     cref
    -0.67
    aarrggbb
    -0.65
    )';
    -0.65
    culable
    -0.65
    .*")]
    -0.64
    *}[
    -0.63
    POSITIVE LOGITS
     лишь
    0.61
     thôi
    0.60
     sahaja
    0.59
     einzigen
    0.57
     one
    0.57
     saja
    0.55
     één
    0.53
    单纯
    0.52
     aspet
    0.52
     ever
    0.51
    Act Density 0.451%

    No Known Activations