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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.07
    3:0.09
    4:0.09
    5:0.08
    6:0.07
    7:0.08
    8:0.09
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     Sop
    -2.04
     counter
    -1.66
     Chev
    -1.64
     Tab
    -1.61
     tit
    -1.61
     Bernard
    -1.56
     Hollow
    -1.56
     hash
    -1.56
     tab
    -1.55
     Christy
    -1.53
    POSITIVE LOGITS
    DragonMagazine
    2.41
    omaly
    2.02
    inav
    1.96
    eatures
    1.93
     therap
    1.88
    today
    1.82
    Brow
    1.80
    speech
    1.76
     millenn
    1.75
    aditional
    1.74
    Act Density 0.000%

    No Known Activations