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

    Neuronpedia

    INDEX
    Explanations

    different punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ego
    -0.17
    OperationException
    -0.15
    _lookup
    -0.15
    nameof
    -0.15
    owitz
    -0.15
    olik
    -0.15
    ãĤ¹ãĤ¯
    -0.14
    PARSE
    -0.14
    ,eg
    -0.14
    nahme
    -0.14
    POSITIVE LOGITS
     bud
    0.17
    TK
    0.15
     bottled
    0.15
    ä¸įè¿ĩ
    0.15
    buat
    0.15
     Hok
    0.14
    odate
    0.14
     hik
    0.14
    stem
    0.14
     testament
    0.14
    Act Density 0.006%

    No Known Activations