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

    Neuronpedia

    INDEX
    Explanations

    words related to classification categories and entities in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vor
    -0.15
     dagen
    -0.14
    uel
    -0.14
     strain
    -0.14
    icht
    -0.13
    gnu
    -0.13
    abase
    -0.13
    ика
    -0.13
    εÏį
    -0.13
    pcf
    -0.13
    POSITIVE LOGITS
    ote
    0.16
    uby
    0.16
    ocab
    0.15
    anlı
    0.15
    257
    0.15
    otate
    0.15
    822
    0.15
    adius
    0.15
    arel
    0.15
    ë¹ĦìķĦ
    0.15
    Act Density 0.030%

    No Known Activations