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

    Neuronpedia

    INDEX
    Explanations

    references to specific quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.59
    complexContent
    -0.59
     дописавши
    -0.57
    ьаж
    -0.57
     betweenstory
    -0.55
     <=",
    -0.55
     otomatig
    -0.54
    ingabe
    -0.52
     समीक्षक
    -0.52
     miles
    -0.52
    POSITIVE LOGITS
     occafion
    0.65
     whoſe
    0.60
     pleaſure
    0.58
     fhort
    0.57
     Shakspeare
    0.56
     greateſt
    0.56
     Majefty
    0.54
     تانيه
    0.54
     Chriftian
    0.54
     ſhould
    0.53
    Act Density 1.640%

    No Known Activations