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

    Neuronpedia

    INDEX
    Explanations

    physical actions or movements carried out by individuals

    oai_token-act-pair · gpt-3.5-turbo

    actions or descriptions of physical movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MAT
    -0.80
    é¾įå
    -0.71
    天
    -0.69
    76561
    -0.62
    quality
    -0.62
    enos
    -0.61
    в
    -0.61
    fill
    -0.59
    Administ
    -0.59
     Anonymous
    -0.58
    POSITIVE LOGITS
     sideways
    1.22
     backwards
    1.19
     awkwardly
    1.17
     backward
    1.16
     downwards
    1.11
     downward
    1.08
     upward
    1.05
     violently
    1.03
     horizontally
    1.03
    rily
    1.03
    Act Density 0.196%

    No Known Activations