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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive forms in relation to experiences and emotions

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

    dates and quantities

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical tokens — numbers, dates, ages, durations, and other numeric expressions in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     dieſe
    -0.80
     NSCoder
    -0.79
     ſehr
    -0.78
     ſans
    -0.77
     ſei
    -0.77
     メンテナ
    -0.76
     Dieſe
    -0.75
     fashiola
    -0.75
     ſchon
    -0.75
     erſten
    -0.74
    POSITIVE LOGITS
     hin
    0.22
     ka
    0.19
     cried
    0.19
    ไ
    0.18
     finish
    0.18
     الح
    0.17
     mul
    0.17
     words
    0.17
     Gy
    0.17
     ak
    0.17
    Act Density 0.109%

    No Known Activations