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

    Neuronpedia

    INDEX
    Explanations

    movie or book titles, characters, and locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     customary
    -0.62
     tremend
    -0.61
    Ô
    -0.61
     carbohyd
    -0.60
    Þ
    -0.60
    said
    -0.60
     obligated
    -0.59
    rosc
    -0.58
     nep
    -0.57
     exting
    -0.57
    POSITIVE LOGITS
     Nights
    0.94
     Ridge
    0.83
     Studios
    0.80
     Valley
    0.79
     Inn
    0.79
     Brewery
    0.79
     Heights
    0.78
     Wonderland
    0.74
     Farms
    0.74
     Tavern
    0.74
    Act Density 15.415%

    No Known Activations