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

    Neuronpedia

    INDEX
    Explanations

    actors or characters and identify who they are playing

    oai_token-act-pair · gpt-3.5-turbo

    references to actors and their roles in films or shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.81
    sonian
    -0.77
    vier
    -0.76
    ensable
    -0.73
    ware
    -0.71
     metabol
    -0.71
     redist
    -0.70
    Weather
    -0.68
     Gallup
    -0.68
    umar
    -0.67
    POSITIVE LOGITS
     Judd
    0.97
    acters
    0.84
     actors
    0.84
     portraying
    0.84
     actresses
    0.83
    rano
    0.83
     Natalie
    0.80
     HIM
    0.80
     actor
    0.79
     Gina
    0.78
    Act Density 0.221%

    No Known Activations