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

    Neuronpedia

    INDEX
    Explanations

    references to theaters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of theaters and theatrical productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nir
    -0.80
    doms
    -0.78
    ilies
    -0.73
    ortium
    -0.69
    nesty
    -0.68
    hee
    -0.68
    pages
    -0.67
    vironment
    -0.66
    tan
    -0.66
    rontal
    -0.65
    POSITIVE LOGITS
    goers
    1.07
     marqu
    1.04
    wright
    0.98
     theatre
    0.95
     theater
    0.94
     theaters
    0.89
     theat
    0.88
     Royale
    0.85
     productions
    0.83
     trou
    0.83
    Act Density 0.030%

    No Known Activations