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

    Neuronpedia

    INDEX
    Explanations

    quantitative metrics related to performance and impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abbage
    -0.16
    omanip
    -0.16
    orr
    -0.16
    itzer
    -0.15
    aná
    -0.15
    má
    -0.15
    eres
    -0.15
     Bulls
    -0.14
    ãĤıãģĽ
    -0.14
    orry
    -0.14
    POSITIVE LOGITS
     since
    0.16
    Disposition
    0.15
    -s
    0.15
    LOPT
    0.15
     odd
    0.14
     conf
    0.14
     Ing
    0.14
    hoff
    0.14
     disin
    0.14
     ing
    0.14
    Act Density 0.329%

    No Known Activations