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

    Neuronpedia

    INDEX
    Explanations

    terms indicating fame or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.76
    onges
    -0.69
    zyj
    -0.65
     condens
    -0.65
    ILON
    -0.64
     PhpStorm
    -0.64
     spie
    -0.63
    witched
    -0.63
     droppings
    -0.63
     Quill
    -0.62
    POSITIVE LOGITS
     known
    1.00
    known
    0.96
    Known
    0.94
     Known
    0.92
     bekend
    0.90
    KNOWN
    0.90
    famous
    0.89
     reputation
    0.89
     bekan
    0.86
     Bekannt
    0.84
    Act Density 0.135%

    No Known Activations