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

    Neuronpedia

    INDEX
    Explanations

    actions related to grasping or grabbing objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Obed
    -0.65
    Batis
    -0.56
    CloseOperation
    -0.55
    FormTagHelper
    -0.54
    örungen
    -0.54
     Buche
    -0.53
     nakalista
    -0.53
     bower
    -0.52
     Clears
    -0.51
     дописавши
    -0.51
    POSITIVE LOGITS
     grip
    0.89
     grabbed
    0.86
     gripped
    0.86
     hold
    0.85
     grab
    0.84
     saisir
    0.82
    Grab
    0.77
     grips
    0.76
     grasped
    0.76
     gripping
    0.75
    Act Density 0.129%

    No Known Activations