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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases indicating actions or important details in reports or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anga
    -0.16
    ÙĪÛĮÙĩ
    -0.15
    _variant
    -0.15
    AGER
    -0.14
     Eag
    -0.14
     Styles
    -0.13
    è¡¥
    -0.13
    ÙĬرة
    -0.13
    ÏĦε
    -0.13
     Willis
    -0.13
    POSITIVE LOGITS
    .ssl
    0.15
    491
    0.15
    TPL
    0.14
     Cord
    0.14
     cord
    0.14
    arend
    0.14
    _secure
    0.14
     Recover
    0.13
    @show
    0.13
    alus
    0.13
    Act Density 0.004%

    No Known Activations