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

    Neuronpedia

    INDEX
    Explanations

    actions related to assembling or connecting objects

    oai_token-act-pair · gpt-3.5-turbo

    technical or mechanical descriptions of objects and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Politics
    -0.78
    Online
    -0.76
    Nation
    -0.73
     memes
    -0.73
    ologne
    -0.73
    humans
    -0.72
    quit
    -0.70
    Ranked
    -0.70
    iots
    -0.69
     Skies
    -0.68
    POSITIVE LOGITS
     protr
    1.49
     perpendicular
    1.17
     attaches
    1.15
     perpend
    1.13
     vertically
    1.09
     weld
    1.08
     adjustable
    1.08
     diameter
    1.08
     retract
    1.07
     horizontally
    1.04
    Act Density 0.419%

    No Known Activations