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

    Neuronpedia

    INDEX
    Explanations

    specific variable declarations and function definitions in programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izr
    -0.61
     colspan
    -0.56
    assung
    -0.53
     Wiesen
    -0.51
    ing
    -0.49
    quartered
    -0.49
    ingdon
    -0.49
    copg
    -0.49
    GTCX
    -0.48
    躇
    -0.48
    POSITIVE LOGITS
    ″
    0.91
    a
    0.89
    s
    0.84
    ️⃣
    0.76
    ″]
    0.76
    ′
    0.72
    e
    0.65
     protoimpl
    0.62
    ⃣
    0.60
    b
    0.58
    Act Density 0.502%

    No Known Activations