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

    Neuronpedia

    INDEX
    Explanations

    lines or breaks (such as underscores or ellipses) that suggest a pause or separation in the text

    oai_token-act-pair · gpt-4-turbo

    scenes or breaks in text marked by specific patterns of underscores ('_')

    oai_token-act-pair · gpt-3.5-turbo

    symbols and underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oise
    -0.70
    scl
    -0.70
    outed
    -0.69
    oscope
    -0.66
     Dynamics
    -0.66
    oming
    -0.65
    sis
    -0.65
    aido
    -0.64
    ippi
    -0.63
    ymph
    -0.62
    POSITIVE LOGITS
    SOURCE
    0.89
     ___
    0.85
    kw
    0.77
    !/
    0.71
    KEN
    0.70
    LINE
    0.69
    DIV
    0.69
    quote
    0.69
    ""
    0.68
    ELL
    0.68
    Act Density 0.012%

    No Known Activations