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

    Neuronpedia

    INDEX
    Explanations

    instances of characters being physically present or in a specific posture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sit
    -0.17
     Sit
    -0.17
     Sitting
    -0.16
    sit
    -0.15
    Sit
    -0.15
     sitting
    -0.15
    acio
    -0.14
     Modal
    -0.14
     sits
    -0.14
    amon
    -0.14
    POSITIVE LOGITS
     motion
    0.28
     Motion
    0.22
    -motion
    0.20
    Motion
    0.20
     next
    0.19
    -stock
    0.19
     perfectly
    0.18
     facing
    0.18
     stock
    0.18
    .motion
    0.18
    Act Density 0.115%

    No Known Activations