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

    Neuronpedia

    INDEX
    Explanations

    instances of hands being mentioned or used in actions

    oai_token-act-pair · gpt-3.5-turbo

    references to hands, particularly in contexts involving physical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undown
    -0.76
     Atmosp
    -0.74
    eming
    -0.68
    vell
    -0.67
     IPS
    -0.67
     RAND
    -0.66
     Flavoring
    -0.66
     UTC
    -0.66
    ItemTracker
    -0.64
    Trend
    -0.64
    POSITIVE LOGITS
    bag
    1.13
    ker
    0.99
    chair
    0.97
     grasping
    0.94
     clasp
    0.91
    maid
    0.90
    tips
    0.86
     grip
    0.84
     grasped
    0.82
     clutching
    0.82
    Act Density 0.044%

    No Known Activations