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

    Neuronpedia

    INDEX
    Explanations

    names of actors and their roles in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.80
    примеча
    -0.79
    NOPQRST
    -0.79
    twimg
    -0.77
    Skocz
    -0.76
    сылкі
    -0.76
     myſelf
    -0.72
    .*")]
    -0.70
     ſeveral
    -0.69
    ритори
    -0.68
    POSITIVE LOGITS
     portraying
    0.92
     playing
    0.91
     portray
    0.81
    playing
    0.78
     portrayal
    0.78
     portrays
    0.77
     reprises
    0.72
     Playing
    0.72
    Playing
    0.71
     interpretar
    0.66
    Act Density 0.128%

    No Known Activations