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

    Neuronpedia

    INDEX
    Explanations

    common phrases or expressions used in various contexts and topics

    oai_token-act-pair · gpt-3.5-turbo

    multiple references to the word "few" and concepts indicating quantity or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ternity
    -0.66
    izont
    -0.60
    estern
    -0.58
    oret
    -0.52
    foreseen
    -0.52
    orously
    -0.49
    itud
    -0.48
    ELY
    -0.47
    zens
    -0.47
    cellaneous
    -0.47
    POSITIVE LOGITS
    .","
    0.87
    .?
    0.87
    .}
    0.87
    .</
    0.85
    .'
    0.84
    .''
    0.83
    ãĢĤ
    0.81
    .:
    0.79
    .",
    0.78
    .#
    0.77
    Act Density 0.969%

    No Known Activations