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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or opposition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Despite."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aird
    -0.69
    lees
    -0.69
    ahime
    -0.68
    SELECT
    -0.65
    ecycle
    -0.63
    ée
    -0.62
    que
    -0.62
    isition
    -0.61
    aby
    -0.61
     contrace
    -0.61
    POSITIVE LOGITS
     acknowledging
    0.83
    math
    0.79
     having
    0.75
    ĸļ
    0.67
     conced
    0.67
     setbacks
    0.67
     knowing
    0.67
     seeming
    0.66
     surviving
    0.65
     lacking
    0.64
    Act Density 0.025%

    No Known Activations