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

    Neuronpedia

    INDEX
    Explanations

    pairs of alphanumeric characters and numbers that go often together and enclosed in symbols such as parentheses

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical data and references related to years and international events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.74
    berman
    -0.74
    ensional
    -0.70
    ndra
    -0.69
    iru
    -0.63
    achus
    -0.62
    ryce
    -0.60
     tantal
    -0.60
    aez
    -0.59
    monton
    -0.59
    POSITIVE LOGITS
    potion
    0.71
     largeDownload
    0.68
    cknowled
    0.68
    USS
    0.65
    ĸļ
    0.64
     Retrieved
    0.64
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.63
    rote
    0.62
    cknow
    0.62
    ATURE
    0.62
    Act Density 0.293%

    No Known Activations