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

    Neuronpedia

    INDEX
    Explanations

    references to, or actions involving, the fingers

    oai_token-act-pair · gpt-3.5-turbo

    references to fingers and hands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.75
    ivals
    -0.72
     Wolfe
    -0.71
    Wars
    -0.68
    igslist
    -0.66
    MQ
    -0.65
    nces
    -0.64
     Neigh
    -0.64
    DEM
    -0.64
    Neigh
    -0.63
    POSITIVE LOGITS
     dexter
    1.01
    pring
    0.98
     grasping
    0.95
     numb
    0.93
     dexterity
    0.93
     amput
    0.91
     paws
    0.90
     stroke
    0.89
     fingers
    0.88
     glide
    0.83
    Act Density 0.049%

    No Known Activations