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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gestures or expressions involving thumbs

    oai_token-act-pair · gpt-3.5-turbo

    references to "thumb" or related expressions, indicating approval or disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hammad
    -0.87
    RT
    -0.83
    اÙĦ
    -0.75
    effic
    -0.71
    gow
    -0.71
    اØ
    -0.70
    ÙĦ
    -0.67
    vernment
    -0.65
     rooft
    -0.65
     Occupations
    -0.65
    POSITIVE LOGITS
     thumb
    1.32
     finger
    0.90
    eenth
    0.86
     fingers
    0.80
     thumbs
    0.79
     dexterity
    0.77
     toe
    0.76
     stroke
    0.75
     amput
    0.74
    finger
    0.73
    Act Density 0.006%

    No Known Activations