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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual usage in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %");
    -0.96
    ValueStyle
    -0.78
    StructEnd
    -0.75
    oa̍t
    -0.74
    ...');
    -0.74
    */;
    -0.72
    %";
    -0.71
    /");
    -0.70
    })();
    -0.69
    ...");
    -0.69
    POSITIVE LOGITS
    so
    0.55
    <eos>
    0.51
     then
    0.50
     really
    0.48
     corret
    0.48
     so
    0.47
     puissent
    0.45
     again
    0.44
    gaz
    0.44
    fiez
    0.44
    Act Density 0.753%

    No Known Activations