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

    Neuronpedia

    INDEX
    Explanations

    references to user interface elements and their functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uty
    -0.18
     Rosenberg
    -0.15
    wed
    -0.15
    jo
    -0.14
     Kem
    -0.14
    ais
    -0.14
    *)"
    -0.14
     hod
    -0.14
    wake
    -0.14
    rch
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.17
    bedPane
    0.16
    icensed
    0.15
    mapped
    0.14
    argon
    0.14
    laus
    0.14
    cob
    0.14
    osomal
    0.14
    arus
    0.14
    avanaugh
    0.14
    Act Density 0.033%

    No Known Activations