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

    Neuronpedia

    INDEX
    Explanations

    references to the entertainment industry, specifically Hollywood

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Hollywood"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arity
    -0.85
    cific
    -0.80
    ktop
    -0.79
    İĭ
    -0.79
    unin
    -0.78
    avez
    -0.75
    onian
    -0.74
    etheless
    -0.72
    uter
    -0.71
    aternity
    -0.71
    POSITIVE LOGITS
     Reporter
    1.10
     Hills
    1.05
     Studios
    0.94
     studios
    0.92
     Boulevard
    0.91
     Pictures
    0.89
     Hollywood
    0.89
     blockbuster
    0.88
     movies
    0.88
     celebrities
    0.84
    Act Density 0.039%

    No Known Activations