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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hands or physical actions involving hands

    oai_token-act-pair · gpt-3.5-turbo

    references to hands and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RAND
    -0.72
    undown
    -0.68
    Sov
    -0.68
     IPS
    -0.65
    actionDate
    -0.65
    ally
    -0.65
     Neigh
    -0.64
    antz
    -0.63
     Born
    -0.61
    burgh
    -0.60
    POSITIVE LOGITS
    bag
    1.29
    ker
    1.21
    maid
    1.09
    bags
    0.98
     grasping
    0.96
     dexter
    0.93
    prints
    0.90
     grips
    0.89
    chair
    0.88
     clasp
    0.88
    Act Density 0.052%

    No Known Activations