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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and associated formatting elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -1.03
     Theſe
    -0.97
     itſelf
    -0.96
     Paglinawan
    -0.94
     Efq
    -0.94
     Houſe
    -0.93
     Inſ
    -0.92
     purpoſe
    -0.91
     Eſ
    -0.91
     myſelf
    -0.91
    POSITIVE LOGITS
    .
    0.96
    ↵
    0.87
    <eos>
    0.85
    ,
    0.80
    ↵↵
    0.74
    ?
    0.71
     is
    0.70
    ;
    0.70
     (
    0.69
    (
    0.67
    Act Density 0.010%

    No Known Activations