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

    Neuronpedia

    INDEX
    Explanations

    intensifying adverbs, particularly the word "very"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seamnă
    -0.63
    paravant
    -0.62
     sauvages
    -0.61
     complètes
    -0.61
     برانيه
    -0.60
     culoare
    -0.60
    تفصیلات
    -0.59
     lenker
    -0.57
     Walkover
    -0.56
     Zjednoc
    -0.55
    POSITIVE LOGITS
     Very
    0.73
     VERY
    0.69
    VERY
    0.68
    very
    0.68
     ***!
    0.68
    Very
    0.67
     surla
    0.66
     very
    0.63
    THING
    0.61
     much
    0.61
    Act Density 0.046%

    No Known Activations