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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical gestures and actions

    oai_token-act-pair · gpt-3.5-turbo

    acts of waving or related gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVES
    -0.74
    Ranked
    -0.68
    ocker
    -0.68
    heid
    -0.63
     partnership
    -0.63
    unker
    -0.62
    ateral
    -0.62
    essor
    -0.61
    igne
    -0.59
     Sins
    -0.59
    POSITIVE LOGITS
     waving
    1.19
     waved
    1.09
     goodbye
    0.98
    pole
    0.85
    boat
    0.80
    glers
    0.78
    uay
    0.76
    wheel
    0.75
    bands
    0.75
    uctor
    0.73
    Act Density 0.005%

    No Known Activations