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

    Neuronpedia

    INDEX
    Explanations

    references to statistics and metrics related to performance or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NR
    -0.17
    orro
    -0.15
    ently
    -0.15
    missive
    -0.14
     eser
    -0.14
     Party
    -0.14
    errated
    -0.14
    ÏģÏĩ
    -0.14
    _frm
    -0.14
    ÙĬس
    -0.13
    POSITIVE LOGITS
    aya
    0.16
    ANGO
    0.15
    tember
    0.14
    ryn
    0.14
    ãĥĥãĥĹ
    0.14
     пÑĢод
    0.14
    PropTypes
    0.13
     metro
    0.13
    æŀ
    0.13
    aga
    0.13
    Act Density 0.023%

    No Known Activations