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

    Neuronpedia

    INDEX
    Explanations

    mentions of being socially excluded or labeled as an outsider

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cast" and its variations, indicating a focus on typecasting or categorizing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.70
     pocket
    -0.70
     li
    -0.66
     ultr
    -0.66
     Fruit
    -0.65
     Flor
    -0.65
     Ju
    -0.63
     ammon
    -0.63
     PL
    -0.62
     pharmac
    -0.62
    POSITIVE LOGITS
    cast
    4.79
    casts
    3.69
    casting
    2.76
    CAST
    2.17
    Cast
    2.05
    casters
    1.92
    caster
    1.82
     cast
    1.57
     Cast
    1.48
     casts
    1.39
    Act Density 0.010%

    No Known Activations