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

    Neuronpedia

    INDEX
    Explanations

    document structure or metadata markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     —
    -0.52
    ised
    -0.47
    …
    -0.46
    —
    -0.45
    ..
    -0.43
    ...
    -0.43
    zunehmen
    -0.43
    bourn
    -0.42
     here
    -0.42
    (_
    -0.42
    POSITIVE LOGITS
    awtextra
    1.21
     ModelExpression
    1.12
     дописавши
    1.11
     tartalomajánló
    1.11
    InjectAttribute
    1.04
    Datuak
    1.01
    StoreMessageInfo
    1.00
     AssemblyTitle
    1.00
    الحياه
    1.00
    .*")]
    0.96
    Act Density 0.515%

    No Known Activations