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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity or diversity across various categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avin
    -0.17
    inen
    -0.17
    á»ĵng
    -0.15
    byn
    -0.15
    usted
    -0.14
    reater
    -0.14
    osg
    -0.14
    oste
    -0.14
    ideon
    -0.14
    je
    -0.14
    POSITIVE LOGITS
    alam
    0.16
    ırak
    0.14
    Ïĩ
    0.14
    Unchecked
    0.14
    ToPoint
    0.14
    å»
    0.14
    ãĤŃãĥ³ãĤ°
    0.14
    кÑĥл
    0.13
    dad
    0.13
    ãĤ¾
    0.13
    Act Density 0.023%

    No Known Activations