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

    Neuronpedia

    INDEX
    Explanations

    references to layers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /chat
    -0.17
    âm
    -0.15
    oy
    -0.15
    ÑĨин
    -0.15
     Bros
    -0.14
    beeld
    -0.14
    (CancellationToken
    -0.14
    aggi
    -0.14
    enty
    -0.13
    ioni
    -0.13
    POSITIVE LOGITS
    .masksToBounds
    0.16
    forms
    0.15
     seedu
    0.15
    een
    0.14
    icals
    0.14
    .tmp
    0.14
    istrovstvÃŃ
    0.14
    halt
    0.14
    anon
    0.14
    theon
    0.13
    Act Density 0.008%

    No Known Activations