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

    Neuronpedia

    INDEX
    Explanations

    references to movie trailers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.83
    urrency
    -0.78
    Ĭ±
    -0.72
    iott
    -0.71
    aido
    -0.70
    tein
    -0.70
    gans
    -0.70
    ternity
    -0.69
    etheless
    -0.69
    reme
    -0.66
    POSITIVE LOGITS
     trailer
    1.16
     trailers
    0.93
     Trailer
    0.85
     teaser
    0.75
     hitch
    0.73
     footage
    0.72
     projector
    0.72
     clips
    0.71
    Studio
    0.69
     clip
    0.68
    Act Density 0.018%

    No Known Activations