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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Balo
    -0.60
    berdayakan
    -0.59
     landings
    -0.59
     Sext
    -0.56
     rekord
    -0.54
     Centurion
    -0.54
     KML
    -0.53
     tart
    -0.52
    pand
    -0.51
     ActionResult
    -0.50
    POSITIVE LOGITS
     undergone
    1.05
     process
    1.03
     processes
    1.02
     undergoes
    1.02
     through
    1.00
     undergo
    0.97
     ordeal
    0.96
    through
    0.94
    Through
    0.88
    processes
    0.88
    Act Density 0.150%

    No Known Activations