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

    Neuronpedia

    INDEX
    Explanations

    quantitative references, specifically numbers and their occurrences in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chevalier
    -0.65
     fédé
    -0.63
     Nacionales
    -0.63
    hésite
    -0.61
    StoreMessageInfo
    -0.61
     Zuge
    -0.60
    Tikang
    -0.59
     savages
    -0.57
     diccionario
    -0.57
     magari
    -0.54
    POSITIVE LOGITS
     two
    0.90
     three
    0.84
     dozen
    0.81
     four
    0.79
    two
    0.78
     zwei
    0.74
    zwei
    0.73
    dozen
    0.72
     deux
    0.70
    three
    0.70
    Act Density 0.690%

    No Known Activations