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

    Neuronpedia

    INDEX
    Explanations

    references to well-known actors and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utters
    -0.16
    ajas
    -0.15
    azers
    -0.15
    nothrow
    -0.15
     vår
    -0.15
    /Set
    -0.14
    utura
    -0.14
    yonel
    -0.14
    .disc
    -0.14
    dbg
    -0.13
    POSITIVE LOGITS
     role
    0.60
     roles
    0.60
    role
    0.48
     Roles
    0.47
    roles
    0.46
     Role
    0.46
    -role
    0.46
    Role
    0.43
    Roles
    0.43
     ROLE
    0.40
    Act Density 0.114%

    No Known Activations