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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and specific counts in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     épaules
    -0.41
    -0.41
     Handeln
    -0.41
    aktur
    -0.38
     Auflösung
    -0.37
     yeux
    -0.36
     âmes
    -0.36
     mères
    -0.35
    equipo
    -0.35
     πως
    -0.35
    POSITIVE LOGITS
     different
    0.65
     consecutive
    0.60
    expandindo
    0.60
     successive
    0.56
    __":
    0.54
     separate
    0.53
     major
    0.50
     wireType
    0.50
     dozen
    0.49
     RIPRODUZIONE
    0.49
    Act Density 0.844%

    No Known Activations