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

    Neuronpedia

    INDEX
    Explanations

    texts describing hands and arm movements

    oai_token-act-pair · gpt-3.5-turbo

    references to hand positions and gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.82
    undown
    -0.69
     Flavoring
    -0.68
     Pf
    -0.67
    grade
    -0.66
    monary
    -0.63
     Income
    -0.63
     Born
    -0.63
     Pigs
    -0.63
     Beet
    -0.62
    POSITIVE LOGITS
     clasp
    1.18
     grasping
    1.00
     grasped
    0.99
     clenched
    0.99
    stretched
    0.96
     gripping
    0.95
     gripped
    0.92
     towel
    0.88
     palms
    0.88
     dexter
    0.87
    Act Density 0.055%

    No Known Activations