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

    Neuronpedia

    INDEX
    Explanations

    adverbs that indicate frequency or timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogie
    -0.17
    微软éĽħé»ij
    -0.15
    ome
    -0.14
    vard
    -0.14
    .nlm
    -0.14
    vap
    -0.14
    olation
    -0.14
    ubi
    -0.13
    گراÙĨ
    -0.13
    оÑĤо
    -0.13
    POSITIVE LOGITS
     whose
    0.17
    езда
    0.15
    EEDED
    0.15
     Copp
    0.15
    whose
    0.14
    ýv
    0.14
     worth
    0.14
     which
    0.14
    æĿ¥çļĦ
    0.14
     cui
    0.14
    Act Density 0.188%

    No Known Activations