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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.72
     мәкал
    -0.70
     مشين
    -0.68
    Tikang
    -0.60
    تقاوى
    -0.60
    bootstrapcdn
    -0.59
    postsleuth
    -0.58
    AnchorStyles
    -0.56
    ValueGeneration
    -0.55
    tvguidetime
    -0.54
    POSITIVE LOGITS
    Kilder
    0.42
     słoń
    0.41
     Könige
    0.40
     zdrowia
    0.36
     kobieta
    0.36
     scolaires
    0.36
     Berufung
    0.36
     étoit
    0.36
    It
    0.35
     menangis
    0.35
    Act Density 0.089%

    No Known Activations