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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases expressing personal opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of doubt or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resultant
    -0.64
    .'"
    -0.62
    ,'"
    -0.61
    !'"
    -0.59
     motif
    -0.59
    ',"
    -0.59
    !--
    -0.58
     invention
    -0.57
    '."
    -0.57
    """
    -0.56
    POSITIVE LOGITS
    renheit
    0.70
    Lisa
    0.66
    cler
    0.65
    anamo
    0.63
    HAM
    0.60
    leep
    0.60
    HAEL
    0.60
    wives
    0.60
    Fle
    0.59
     Roads
    0.59
    Act Density 1.341%

    No Known Activations