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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampie
    -0.16
    ÙĬÙĥÙĬ
    -0.14
     Dig
    -0.14
    ichte
    -0.13
    icensing
    -0.13
     Gonzalez
    -0.13
    ieren
    -0.13
    oten
    -0.13
    ogle
    -0.13
    itaire
    -0.13
    POSITIVE LOGITS
     Eld
    0.15
    oard
    0.15
    unger
    0.14
    飾
    0.14
    inis
    0.14
    onis
    0.13
    ASP
    0.13
     Phong
    0.13
    Pok
    0.13
    /Home
    0.13
    Act Density 0.003%

    No Known Activations