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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "movie."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilities
    -0.86
    withstanding
    -0.74
     Haitian
    -0.72
    ords
    -0.69
    odox
    -0.68
    raham
    -0.67
    etheless
    -0.66
    urst
    -0.65
    theless
    -0.64
    otic
    -0.64
    POSITIVE LOGITS
    goers
    1.11
     theaters
    1.06
     theater
    1.01
     movies
    0.95
    eers
    0.91
     buffs
    0.91
     theatre
    0.91
     movie
    0.90
     theat
    0.88
    Lens
    0.87
    Act Density 0.046%

    No Known Activations