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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

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

    that + descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.55
    
    -0.50
     Wikimedijinoj
    -0.49
     Roskov
    -0.45
     ویکی‌پدی
    -0.45
     auft
    -0.43
    Архівовано
    -0.43
    iNdEx
    -0.43
     HasFactory
    -0.42
     Carni
    -0.42
    POSITIVE LOGITS
     StatefulWidget
    0.56
     Muito
    0.51
    anskje
    0.51
    Molto
    0.51
    Muito
    0.51
     aika
    0.50
     quite
    0.48
     vähän
    0.48
     Very
    0.48
     very
    0.48
    Act Density 0.014%

    No Known Activations