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-turbo

    references to movie trailers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reme
    -0.76
    urrency
    -0.75
    ternity
    -0.75
    iments
    -0.70
    ¬¼
    -0.69
    ederation
    -0.68
    Ĭ±
    -0.68
    orius
    -0.67
    theless
    -0.66
    iott
    -0.66
    POSITIVE LOGITS
     trailer
    1.11
     trailers
    0.96
     Trailer
    0.91
    ographer
    0.74
     hitch
    0.72
    nikov
    0.72
    film
    0.68
    ature
    0.68
    ript
    0.67
    ographers
    0.66
    Act Density 0.015%

    No Known Activations