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

    Neuronpedia

    INDEX
    Explanations

    themes related to documentation and validation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.22
    /her
    -0.17
    /or
    -0.17
    /to
    -0.16
    osit
    -0.16
    /out
    -0.15
    /of
    -0.14
    aping
    -0.14
    /how
    -0.14
    kol
    -0.14
    POSITIVE LOGITS
    /report
    0.18
    ulate
    0.16
    ä¸Ģä¸ĭ
    0.15
    çļĦæĺ¯
    0.15
     ÑģобоÑİ
    0.15
    ÏĬκ
    0.15
    /debug
    0.13
    ÅĤa
    0.13
    uft
    0.13
    lý
    0.13
    Act Density 1.903%

    No Known Activations