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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical movement, such as being dragged or escorted

    oai_token-act-pair · gpt-3.5-turbo

    actions related to physical restraint or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Recomm
    -0.64
    acts
    -0.64
     Effective
    -0.63
     Siber
    -0.62
     collaboration
    -0.62
     collaborations
    -0.62
    ITNESS
    -0.60
     pact
    -0.58
     Inher
    -0.58
    asio
    -0.58
    POSITIVE LOGITS
     away
    1.26
     aside
    1.04
     overboard
    0.98
     awa
    0.95
     ashore
    0.94
     onto
    0.90
    away
    0.90
     unconscious
    0.88
     aback
    0.87
     upstairs
    0.87
    Act Density 0.123%

    No Known Activations