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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their contents in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     U
    -0.63
     R
    -0.63
     H
    -0.59
     W
    -0.58
     O
    -0.57
     S
    -0.56
     E
    -0.56
     T
    -0.55
     Pro
    -0.52
     G
    -0.52
    POSITIVE LOGITS
    "]=
    1.06
    )]=
    1.01
     auroit
    1.00
     inoxydable
    0.99
     ainfi
    0.98
    Билгалдахарш
    0.98
     enfans
    0.97
     purpoſe
    0.96
    >"+
    0.96
     scolaires
    0.95
    Act Density 0.251%

    No Known Activations