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

    Neuronpedia

    INDEX
    Explanations

    words related to rankings or classifications of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amba
    -0.16
    èĥ
    -0.14
    378
    -0.13
     ç¬
    -0.13
    łģ
    -0.13
    kov
    -0.13
    inez
    -0.13
    TimeString
    -0.13
    ington
    -0.13
    ABCDE
    -0.13
    POSITIVE LOGITS
    ãģ¡ãģ¯
    0.17
    quist
    0.16
    ascimento
    0.15
    zell
    0.15
     Epoch
    0.15
    .PropTypes
    0.14
     Erk
    0.14
    awai
    0.14
    nie
    0.14
    MW
    0.14
    Act Density 0.044%

    No Known Activations