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

    Neuronpedia

    INDEX
    Explanations

    code-related terms or references within technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preſent
    -0.73
    IntoConstraints
    -0.70
    |}{}
    -0.69
     дописавши
    -0.66
     tartalomajánló
    -0.66
    >>()
    -0.66
    issau
    -0.66
    PREFERRED
    -0.66
    istani
    -0.65
    énage
    -0.64
    POSITIVE LOGITS
     by
    0.91
     oleh
    0.79
     توسط
    0.58
     przez
    0.54
     pelos
    0.54
     dagli
    0.52
     according
    0.51
     pela
    0.51
     пользователем
    0.50
    by
    0.47
    Act Density 0.548%

    No Known Activations