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

    Neuronpedia

    INDEX
    Explanations

    references to discussions or descriptions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.54
     Roskov
    -0.50
    drawSprites
    -0.49
     useAppContext
    -0.48
    Tembelea
    -0.47
    stdc
    -0.45
    principalColumn
    -0.44
    :✨
    -0.43
     utafitiHapana
    -0.42
    Lähteet
    -0.41
    POSITIVE LOGITS
     succinctly
    0.75
     explicitly
    0.75
     eloquently
    0.65
     briefly
    0.65
     concise
    0.64
     elsewhere
    0.63
     expli
    0.60
     vividly
    0.59
     ausführ
    0.57
     graphically
    0.57
    Act Density 1.018%

    No Known Activations