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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing new information or citing sources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "As" indicating introductory phrases or transitions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redits
    -0.69
     incent
    -0.68
    ãĤ©
    -0.67
    âĸº
    -0.63
    LESS
    -0.60
    âĢķ
    -0.60
    aceae
    -0.60
    []
    -0.60
    âĻ¦
    -0.60
    _-_
    -0.59
    POSITIVE LOGITS
    semb
    1.06
    ylum
    1.06
    piring
    1.04
    king
    1.03
    bestos
    0.98
    ahi
    0.97
    weeney
    0.92
    phalt
    0.91
    ymm
    0.88
    semble
    0.88
    Act Density 0.071%

    No Known Activations