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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments and affirmations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions and evaluations of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Soda
    -0.63
    enter
    -0.61
     ABV
    -0.60
     Nirvana
    -0.59
     Volcano
    -0.59
    oku
    -0.58
     Ecology
    -0.58
     Redmond
    -0.58
     iceberg
    -0.58
     Compliance
    -0.57
    POSITIVE LOGITS
     him
    1.19
     admire
    1.01
     congratulate
    0.96
     vou
    0.94
     compliment
    0.89
     pity
    0.87
     admiration
    0.87
     adore
    0.85
     esteem
    0.85
    ascript
    0.85
    Act Density 0.730%

    No Known Activations