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

    Neuronpedia

    INDEX
    Explanations

    academic or scholarly references to texts and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roker
    -0.15
    uen
    -0.14
    HY
    -0.14
    otts
    -0.13
     daily
    -0.13
     Esper
    -0.13
    933
    -0.13
    ÏĦίοÏħ
    -0.12
     combined
    -0.12
    INC
    -0.12
    POSITIVE LOGITS
    ENTE
    0.20
    ATUS
    0.17
    ente
    0.17
     ogs
    0.16
    .MixedReality
    0.16
    /goto
    0.15
    IDX
    0.14
    tember
    0.14
    ride
    0.14
    idak
    0.14
    Act Density 0.037%

    No Known Activations