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

    Neuronpedia

    INDEX
    Explanations

    mentions of movie theaters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of movie theaters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pages
    -0.80
    doms
    -0.77
    laus
    -0.76
    opher
    -0.71
    LER
    -0.69
    TON
    -0.64
    erous
    -0.63
    vous
    -0.63
    eros
    -0.62
    drawn
    -0.62
    POSITIVE LOGITS
     theaters
    1.05
     theater
    1.00
     Theater
    0.90
    goers
    0.87
     kios
    0.85
     theat
    0.82
    plex
    0.82
     theatre
    0.81
     Royale
    0.77
    ror
    0.71
    Act Density 0.012%

    No Known Activations