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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to movement or physical processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.66
     Situation
    -0.64
     Memories
    -0.61
     rematch
    -0.60
     cosmetics
    -0.59
     Tournament
    -0.59
     Dialogue
    -0.58
    é¾įå
    -0.58
    ãĥª
    -0.58
     Badge
    -0.58
    POSITIVE LOGITS
     toward
    1.16
     towards
    1.10
     perpend
    1.03
     perpendicular
    0.97
     across
    0.94
     farther
    0.92
     into
    0.92
     overhead
    0.92
     away
    0.92
     north
    0.91
    Act Density 0.168%

    No Known Activations