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

    Neuronpedia

    INDEX
    Explanations

    actions related to taking, picking up, or grabbing objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CallOverrides
    -0.58
     defaultstate
    -0.58
     cdti
    -0.52
    LookAnd
    -0.52
     дописавши
    -0.52
    ExtendWith
    -0.51
    交
    -0.50
     fileSize
    -0.50
     Commission
    -0.50
    ensas
    -0.49
    POSITIVE LOGITS
     grab
    1.28
     grabbed
    1.28
     grabs
    1.26
     grabbing
    1.20
     pick
    1.14
     picked
    1.14
    pick
    1.11
     Grab
    1.09
     catches
    1.07
     catch
    1.07
    Act Density 0.248%

    No Known Activations