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

    Neuronpedia

    INDEX
    Explanations

    references to the film industry

    oai_token-act-pair · gpt-3.5-turbo

    references to films and the film industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rique
    -0.69
    owder
    -0.67
    etheless
    -0.66
    lished
    -0.65
    utherford
    -0.62
     probable
    -0.62
    ptoms
    -0.62
    ursed
    -0.61
    uckles
    -0.59
    ained
    -0.58
    POSITIVE LOGITS
    lihood
    0.80
    rities
    0.70
     ridic
    0.69
    hang
    0.68
    wright
    0.66
     portraying
    0.65
     depicting
    0.65
     portrays
    0.64
     Boat
    0.64
    culosis
    0.62
    Act Density 0.418%

    No Known Activations