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

    Neuronpedia

    INDEX
    Explanations

    information about authors and their backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsch
    -0.19
     Meyer
    -0.16
    suz
    -0.15
    panies
    -0.15
    htags
    -0.15
    isz
    -0.15
    imir
    -0.14
    AC
    -0.14
     ragaz
    -0.14
     GPLv
    -0.14
    POSITIVE LOGITS
    adil
    0.18
    ayet
    0.17
    enheim
    0.15
    andin
    0.14
    oss
    0.14
     together
    0.14
     cra
    0.14
     consult
    0.13
    ILD
    0.13
    autop
    0.13
    Act Density 0.037%

    No Known Activations