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

    Neuronpedia

    INDEX
    Explanations

    references to numerical characters and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.65
    -0.65
     препратки
    -0.65
    UserScript
    -0.63
     Infórmanos
    -0.61
     PeEnEo
    -0.60
    Personendaten
    -0.59
     дописавши
    -0.57
     kasarigan
    -0.57
    出版年
    -0.57
    POSITIVE LOGITS
     numbers
    0.95
    numbers
    0.85
     Numbers
    0.84
    Numbers
    0.81
     Zahlen
    0.76
     numerals
    0.75
     chiffres
    0.75
     números
    0.75
     NUMBERS
    0.75
     numeri
    0.72
    Act Density 1.043%

    No Known Activations