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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical movements or interactions with objects

    oai_token-act-pair · gpt-3.5-turbo

    actions involving extended physical gestures or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLUS
    -0.81
     unemploy
    -0.79
     conformity
    -0.74
     inval
    -0.74
     Frey
    -0.71
    BuyableInstoreAndOnline
    -0.69
     bankruptcy
    -0.69
     Bast
    -0.67
     suites
    -0.67
     veter
    -0.67
    POSITIVE LOGITS
     gently
    1.03
     fingers
    1.02
    tips
    0.98
     paddle
    0.96
     pressed
    0.96
     fingertips
    0.94
     angled
    0.93
    tip
    0.92
    button
    0.90
     finger
    0.90
    Act Density 0.456%

    No Known Activations