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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases or signals indicating the start of a new section or thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     West
    -0.56
     unknownFields
    -0.55
     (
    -0.54
     
    -0.54
    **
    -0.54
     s
    -0.54
     K
    -0.54
    ("$.
    -0.52
     re
    -0.52
     J
    -0.50
    POSITIVE LOGITS
     المعيارى
    0.96
     يتيمه
    0.95
     незавершена
    0.89
     مرئيه
    0.83
     صوتيه
    0.82
     متعلقه
    0.81
    expandindo
    0.79
     الحره
    0.77
     كومونز
    0.77
     Waray
    0.75
    Act Density 0.193%

    No Known Activations