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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to categorization and classification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acket
    -0.17
    iler
    -0.16
     èĩªåĬ¨çĶŁæĪIJ
    -0.16
     æŀ
    -0.15
    )const
    -0.15
    ODULE
    -0.14
     оÑģÑĮ
    -0.14
    apı
    -0.14
    asic
    -0.14
    OfWork
    -0.14
    POSITIVE LOGITS
    pais
    0.15
     Robertson
    0.14
    rais
    0.14
     Silk
    0.13
     Wich
    0.13
     Speaking
    0.13
     ...(
    0.13
    exampleInput
    0.13
    abolic
    0.13
    edd
    0.13
    Act Density 0.026%

    No Known Activations