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

    Neuronpedia

    INDEX
    Explanations

    specific day references mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days and nights in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etooth
    -0.70
    ãģ®å
    -0.67
    olate
    -0.67
     Pact
    -0.66
     VIDEOS
    -0.65
    姫
    -0.64
    akia
    -0.63
    ãĤ¼
    -0.63
    Æ
    -0.62
    åij
    -0.62
    POSITIVE LOGITS
    lies
    0.85
    nings
    0.72
     premiere
    0.67
    lights
    0.64
     inception
    0.64
     itself
    0.62
    lings
    0.62
    idates
    0.61
    illo
    0.60
    books
    0.60
    Act Density 0.086%

    No Known Activations