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

    Neuronpedia

    INDEX
    Explanations

    references to regulatory and compliance topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rist
    -0.14
    omp
    -0.14
    ÑħÑĸд
    -0.14
    BUR
    -0.14
    ataire
    -0.14
    -0.14
     åł
    -0.13
    gp
    -0.13
     Ent
    -0.13
     waivers
    -0.13
    POSITIVE LOGITS
    usage
    0.17
    ANDOM
    0.16
     usage
    0.16
    ãĥ³ãĥķ
    0.16
    estro
    0.15
    rides
    0.15
    enstein
    0.14
     </>↵
    0.14
    usement
    0.14
     Affero
    0.13
    Act Density 0.008%

    No Known Activations