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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "go"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.06
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.09
    10:0.07
    11:0.08
    Negative Logits
    ciating
    -2.03
     Palestin
    -1.94
     Iro
    -1.89
     Elections
    -1.86
     Constitution
    -1.83
     AFB
    -1.83
     Tackle
    -1.77
     ENT
    -1.76
     Bucks
    -1.76
    ousing
    -1.75
    POSITIVE LOGITS
    perse
    2.27
     hindsight
    2.13
    Repl
    2.09
    repl
    2.07
    Sov
    2.06
    REDACTED
    2.01
     replacements
    2.01
     stockp
    1.99
    sav
    1.94
    ゴ
    1.94
    Act Density 0.000%

    No Known Activations