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

    Neuronpedia

    INDEX
    Explanations

    variations and references to articles or objects in a document, particularly in French

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

    French and Spanish words, particularly articles and prepositions with high character-level encoding artifacts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    ſelf
    -0.63
    farande
    -0.61
     händer
    -0.59
    ſelves
    -0.59
     pleaſure
    -0.59
    makeText
    -0.58
     Cassius
    -0.58
     Jefus
    -0.57
     barnen
    -0.57
     cheminée
    -0.57
    POSITIVE LOGITS
    toare
    0.41
     nicio
    0.39
     вышла
    0.39
    ține
    0.37
    țele
    0.37
    astă
    0.36
    pă
    0.35
     bune
    0.35
     Haupts
    0.35
    óa
    0.35
    Act Density 0.115%

    No Known Activations