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

    Neuronpedia

    INDEX
    Explanations

    intensifying adverbs that express a high degree of positivity or appeal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -1.03
     transférez
    -0.98
    icoot
    -0.97
    setVerticalGroup
    -0.95
     ModelExpression
    -0.92
    //
    -0.90
    endpush
    -0.87
    TintMode
    -0.85
    UnsafeEnabled
    -0.84
    Хьажоргаш
    -0.82
    POSITIVE LOGITS
     darn
    1.25
     pretty
    1.24
     Pretty
    1.13
    Pretty
    1.09
    pretty
    1.08
     PRET
    0.95
    PRET
    0.88
     damn
    0.86
    ing
    0.83
     good
    0.82
    Act Density 0.048%

    No Known Activations