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

    Neuronpedia

    INDEX
    Explanations

    declarations and statements of intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hey
    -0.18
    dra
    -0.15
    acre
    -0.15
    ongan
    -0.15
    falls
    -0.14
    jm
    -0.14
    .CodeAnalysis
    -0.14
    ิล
    -0.14
    cit
    -0.14
    ossip
    -0.13
    POSITIVE LOGITS
    (strict
    0.18
    /assert
    0.17
    ibrate
    0.16
    obuf
    0.16
    ibrator
    0.16
    edly
    0.16
    EditingStyle
    0.16
     RectTransform
    0.15
    ounced
    0.15
    atively
    0.15
    Act Density 0.023%

    No Known Activations