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

    Neuronpedia

    INDEX
    Explanations

    references to various programming concepts or code-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.76
    es
    -0.70
    tory
    -0.70
    tale
    -0.64
    t
    -0.62
    a
    -0.58
    ture
    -0.57
    tation
    -0.55
    ه
    -0.54
    tative
    -0.53
    POSITIVE LOGITS
    nnnn
    0.84
     незавершена
    0.83
    nnn
    0.80
     kasarigan
    0.78
    RenderAtEndOf
    0.76
    ning
    0.76
     متعلقه
    0.75
    ned
    0.74
     nahilalakip
    0.73
    はじめに
    0.72
    Act Density 0.453%

    No Known Activations