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

    Neuronpedia

    INDEX
    Explanations

    names of actors and their roles in films or productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aptive
    -0.18
    artz
    -0.15
    utivo
    -0.14
    792
    -0.14
    721
    -0.14
    ecz
    -0.14
    OpenHelper
    -0.14
    639
    -0.14
    NW
    -0.13
    ÅĦst
    -0.13
    POSITIVE LOGITS
     actors
    0.21
     cast
    0.21
    饰
    0.20
     actor
    0.19
     acting
    0.19
     Actors
    0.18
    æ¼Ķ
    0.17
    飾
    0.17
    (actor
    0.17
     casting
    0.16
    Act Density 0.150%

    No Known Activations