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

    Neuronpedia

    INDEX
    Explanations

    references to character roles in films and television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anken
    -0.17
    assin
    -0.17
    ccione
    -0.16
    ManagerInterface
    -0.15
    ÑĪÑĤов
    -0.15
    arrass
    -0.15
    ald
    -0.14
    gressor
    -0.14
    aint
    -0.14
    èĥŀ
    -0.14
    POSITIVE LOGITS
     characters
    0.20
    iaux
    0.20
     Characters
    0.17
     character
    0.16
     Lens
    0.16
     Hort
    0.15
     Character
    0.15
     Mrs
    0.15
     young
    0.14
     Young
    0.14
    Act Density 0.975%

    No Known Activations