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

    Neuronpedia

    INDEX
    Explanations

    descriptions or actions related to thumbs

    oai_token-act-pair · gpt-3.5-turbo

    references to "thumb" and "thumbs," particularly in phrases signifying approval or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ments
    -0.70
    gow
    -0.65
    forming
    -0.64
     Invasion
    -0.62
    iona
    -0.62
    ews
    -0.62
    ihad
    -0.61
    igun
    -0.61
    iers
    -0.60
    inite
    -0.60
    POSITIVE LOGITS
     thumb
    4.00
     thumbs
    2.24
     fingers
    1.52
     finger
    1.51
     fingert
    1.34
    finger
    1.28
     thumbnail
    1.27
     fing
    1.26
     wrist
    1.24
     palm
    1.23
    Act Density 0.011%

    No Known Activations