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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their occurrence in the text

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

    t seguido por punto y letra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciudadana
    -0.44
     Masalah
    -0.44
     extranjeros
    -0.41
     existir
    -0.41
     compositeur
    -0.41
     světě
    -0.41
     Sucher
    -0.40
     diputados
    -0.40
     condominio
    -0.40
     parmi
    -0.40
    POSITIVE LOGITS
     T
    1.05
    T
    0.90
    Ｔ
    0.72
    getT
    0.68
     t
    0.68
     Tc
    0.65
     Tl
    0.65
     TJ
    0.64
     TD
    0.63
     TType
    0.63
    Act Density 0.055%

    No Known Activations