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

    Neuronpedia

    INDEX
    Explanations

    structures related to code syntax and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     of
    -0.77
     fran
    -0.73
    widetilde
    -0.69
     top
    -0.63
     un
    -0.63
    P
    -0.62
     de
    -0.62
     vol
    -0.61
     bos
    -0.61
     zun
    -0.60
    POSITIVE LOGITS
    ;");
    1.62
    $;
    1.61
    ;;;
    1.60
    ;;;;
    1.50
    ,:);
    1.50
    ?;
    1.49
    ]';
    1.49
    ()]);
    1.47
    }$;
    1.46
    ;";
    1.46
    Act Density 0.398%

    No Known Activations