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

    Neuronpedia

    INDEX
    Explanations

    the concept of physical body parts or actions associated with them

    oai_token-act-pair · gpt-3.5-turbo

    references to body parts and physical gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arenthood
    -0.71
    VERS
    -0.69
     Rohing
    -0.67
    auri
    -0.65
    naire
    -0.61
     oneself
    -0.61
     Yugoslavia
    -0.60
     Haku
    -0.60
    humane
    -0.59
     Byrne
    -0.59
    POSITIVE LOGITS
     burned
    0.83
     dipped
    0.82
     crossed
    0.80
     smelled
    0.79
     slipped
    0.79
     popped
    0.79
     dyed
    0.79
     stained
    0.77
    butt
    0.75
    picked
    0.74
    Act Density 0.158%

    No Known Activations