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

    Neuronpedia

    INDEX
    Explanations

    references to scientific publications and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [{
    -0.61
    StructEnd
    -0.57
    Xna
    -0.47
    Livre
    -0.47
    jock
    -0.47
    Entrega
    -0.46
     prek
    -0.46
     karna
    -0.45
     punish
    -0.45
    prefixer
    -0.44
    POSITIVE LOGITS
    ViewImports
    0.75
    Rüyada
    0.69
     palsu
    0.67
     Beware
    0.63
     disambiguazione
    0.61
     FALSE
    0.61
     bogus
    0.60
    Beware
    0.60
     falsos
    0.58
     fakes
    0.58
    Act Density 0.197%

    No Known Activations