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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "à" and variations of special characters or decorations indicating emphasis or formatting

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

    à followed by common French words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.57
     Púb
    -0.56
     Jefus
    -0.54
     fubject
    -0.54
     enfans
    -0.54
     étoient
    -0.53
     nôtre
    -0.53
     travailleurs
    -0.52
     vôtre
    -0.51
     plufieurs
    -0.50
    POSITIVE LOGITS
     à
    1.19
     À
    0.80
    À
    0.75
    à
    0.70
     a
    0.67
     aan
    0.65
     goTo
    0.59
     at
    0.58
     à
    0.57
     zu
    0.57
    Act Density 0.004%

    No Known Activations