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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating measurements and proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trung
    -0.59
     at
    -0.56
     co
    -0.54
    .
    -0.54
     alone
    -0.51
     in
    -0.49
     of
    -0.49
     Co
    -0.49
     (
    -0.48
     on
    -0.48
    POSITIVE LOGITS
    Personendaten
    1.01
    Datuak
    0.86
     EconPapers
    0.85
     <<<<<<<<<<<<<<
    0.80
    expandindo
    0.79
    Personensuche
    0.77
     مرئيه
    0.76
     Audiodateien
    0.75
    DockStyle
    0.74
    iecie
    0.74
    Act Density 0.559%

    No Known Activations