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

    Neuronpedia

    INDEX
    Explanations

    items listed as "following."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "following."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.82
    aus
    -0.77
    abella
    -0.76
    eus
    -0.74
    haw
    -0.73
    utenant
    -0.73
    姫
    -0.72
    uca
    -0.72
    Sport
    -0.71
    raper
    -0.70
    POSITIVE LOGITS
     excerpt
    0.88
     scenario
    0.83
     diagram
    0.83
     paragraphs
    0.83
     subsections
    0.82
     statement
    0.81
     qualities
    0.79
     sections
    0.79
     table
    0.79
     kinds
    0.79
    Act Density 0.037%

    No Known Activations