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

    Neuronpedia

    INDEX
    Explanations

    words related to animated content

    oai_token-act-pair · gpt-3.5-turbo

    terms related to animated films and series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orr
    -0.85
    hoff
    -0.78
    rank
    -0.76
    umbing
    -0.73
    agher
    -0.72
    yer
    -0.72
    ledge
    -0.71
    inness
    -0.71
     Lawyers
    -0.71
    marked
    -0.71
    POSITIVE LOGITS
     GIF
    1.02
     gif
    0.88
    agus
    0.75
    ebted
    0.74
    ocument
    0.74
    cember
    0.71
    atable
    0.70
     characters
    0.70
     cartoons
    0.68
    netflix
    0.67
    Act Density 0.016%

    No Known Activations