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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement and physical actions

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of physical structures or actions related to movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    climate
    -0.80
    2013
    -0.75
    2016
    -0.73
    2015
    -0.73
    UPDATE
    -0.73
    hack
    -0.73
    Brexit
    -0.72
    2014
    -0.72
    profits
    -0.71
     Worst
    -0.70
    POSITIVE LOGITS
     oneself
    1.09
     preferably
    1.06
     alternating
    1.00
     usually
    0.99
     ceremon
    0.98
     customary
    0.96
    usually
    0.95
     seated
    0.95
     ceremonial
    0.95
     initi
    0.90
    Act Density 0.683%

    No Known Activations