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

    Neuronpedia

    INDEX
    Explanations

    references to the significance and importance of various concepts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    779
    -0.15
    ubi
    -0.14
    cken
    -0.14
    oque
    -0.13
    _TYP
    -0.13
    å°¼äºļ
    -0.13
    roti
    -0.13
    idual
    -0.13
     Brewer
    -0.13
    Audit
    -0.13
    POSITIVE LOGITS
     importance
    0.21
     Importance
    0.19
    веÑģÑĤи
    0.15
     er
    0.15
    ÑĨеÑĢ
    0.14
     cog
    0.14
    pig
    0.14
    à¤ł
    0.14
    (commit
    0.14
    _flutter
    0.14
    Act Density 0.171%

    No Known Activations