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

    Neuronpedia

    INDEX
    Explanations

    comparative conjunctions indicating contrast or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    whereas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.78
     propOrder
    -0.73
     Administrativna
    -0.71
    esModule
    -0.68
     المعيارى
    -0.66
    Mito
    -0.60
    Tikang
    -0.60
     للاسماء
    -0.56
     instr
    -0.55
    Vidite
    -0.55
    POSITIVE LOGITS
    Whereas
    0.59
     whereas
    0.52
    whereas
    0.50
     Whereas
    0.48
    ness
    0.47
    对于
    0.41
     faptul
    0.41
     szcze
    0.41
     deose
    0.40
     dagegen
    0.40
    Act Density 0.011%

    No Known Activations