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

    Neuronpedia

    INDEX
    Explanations

    elements related to societal issues and critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÙĤاب
    -0.15
    landa
    -0.15
    еÑĩ
    -0.15
    .bunifuFlatButton
    -0.14
    etag
    -0.14
    ses
    -0.14
    [random
    -0.14
    зÑĮ
    -0.14
    apel
    -0.14
    eydi
    -0.14
    POSITIVE LOGITS
     Buckley
    0.17
    ahr
    0.16
     which
    0.15
     increasingly
    0.14
     will
    0.14
    بÙĪÙĦ
    0.13
    è¡ĵ
    0.13
     Ald
    0.13
     who
    0.13
     for
    0.13
    Act Density 0.004%

    No Known Activations