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

    Neuronpedia

    INDEX
    Explanations

    discussions about interpersonal relationships and character dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    appearing before actors' names

    np_acts-logits-general · gemini-2.0-flash

    actors starring in roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.66
    atimes
    -0.58
    ValueStyle
    -0.57
    itudinal
    -0.54
    Dorothy
    -0.54
    Abit
    -0.53
     дописавши
    -0.53
     conformité
    -0.53
    +#+#
    -0.52
     Sécurité
    -0.51
    POSITIVE LOGITS
     actors
    1.04
     actor
    1.01
     actores
    0.91
     Actors
    0.89
    Actors
    0.88
     actress
    0.88
     Actor
    0.81
     actresses
    0.79
     cast
    0.79
     star
    0.75
    Act Density 0.188%

    No Known Activations