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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fran
    -0.73
    alan
    -0.69
     of
    -0.67
    ondy
    -0.67
    widetilde
    -0.66
     vol
    -0.62
    nungs
    -0.62
    P
    -0.61
     NED
    -0.61
     olo
    -0.60
    POSITIVE LOGITS
    $;
    1.46
    ;;;
    1.30
    }$;
    1.25
    _;
    1.24
    AndEndTag
    1.23
    +;
    1.23
    ;;;;
    1.22
    .;
    1.19
    ,:);
    1.16
    icolon
    1.15
    Act Density 0.163%

    No Known Activations