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

    Neuronpedia

    INDEX
    Explanations

    key terms related to authorization and acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uez
    -0.17
    .Keyword
    -0.15
    rossover
    -0.15
    estro
    -0.14
    aira
    -0.14
    rance
    -0.14
    rika
    -0.14
    scenes
    -0.14
    anches
    -0.14
    elden
    -0.14
    POSITIVE LOGITS
    thon
    0.16
    urg
    0.15
     mun
    0.15
     Mun
    0.15
    osh
    0.15
    697
    0.14
    trace
    0.14
     trace
    0.14
    aos
    0.14
     Muse
    0.13
    Act Density 0.021%

    No Known Activations