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

    Neuronpedia

    INDEX
    Explanations

    opening and closing curly braces in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cente
    -0.07
    /manual
    -0.06
    quete
    -0.06
    antz
    -0.06
    sian
    -0.06
    ftar
    -0.06
    metatable
    -0.06
    aida
    -0.06
    çł²
    -0.06
    chants
    -0.05
    POSITIVE LOGITS
     return
    0.10
    return
    0.09
    	return
    0.09
    .return
    0.07
    -return
    0.07
    è¿ĶåĽŀ
    0.07
    (return
    0.07
    Return
    0.07
     returns
    0.07
     returning
    0.07
    Act Density 0.001%

    No Known Activations