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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igan
    -0.19
    ÃŁ
    -0.15
    rea
    -0.14
    dea
    -0.14
    andin
    -0.13
    bac
    -0.13
    ÑģÑĤи
    -0.13
    ibel
    -0.13
     especific
    -0.13
    ongo
    -0.13
    POSITIVE LOGITS
     cr
    0.16
     triple
    0.15
    é¼
    0.14
    ëįĶëĭĪ
    0.14
    iffe
    0.14
    Prompt
    0.14
     triples
    0.14
     lean
    0.14
    nonnull
    0.14
     Samp
    0.14
    Act Density 0.022%

    No Known Activations