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

    Neuronpedia

    INDEX
    Explanations

    references to variable assignments and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kele
    -0.65
     مرئيه
    -0.64
     parseFrom
    -0.64
     Steiner
    -0.62
    ″]
    -0.62
     Koval
    -0.62
     \{\
    -0.61
     cerr
    -0.60
    اخ
    -0.60
    ]=>
    -0.60
    POSITIVE LOGITS
     p
    1.69
    p
    1.28
    pS
    1.04
    pV
    0.98
    ｐ
    0.97
    pT
    0.92
    frontmatter
    0.90
     nakalista
    0.87
     pimples
    0.85
     р
    0.84
    Act Density 0.156%

    No Known Activations