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

    Neuronpedia

    INDEX
    Explanations

    occurrences of opening and closing brackets and parentheses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stdc
    -0.64
    ()]
    -0.64
     me
    -0.60
     b
    -0.56
    קישורים
    -0.56
     Fal
    -0.55
     man
    -0.55
    Laure
    -0.54
     cards
    -0.54
     n
    -0.54
    POSITIVE LOGITS
     uſe
    0.88
     purpoſe
    0.86
     greateſt
    0.85
     myſelf
    0.83
     ſhould
    0.82
     ſeveral
    0.81
     Reſ
    0.81
     uſed
    0.79
     pleaſure
    0.79
     Houſe
    0.79
    Act Density 0.135%

    No Known Activations