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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.72
     Monfieur
    -0.69
    ſelf
    -0.69
     Theſe
    -0.68
     Efq
    -0.66
     Majefty
    -0.64
     voleva
    -0.60
     chrétien
    -0.59
    ſelves
    -0.59
     Jefus
    -0.59
    POSITIVE LOGITS
     disambiguazione
    0.66
    ConverterFactory
    0.65
    ابراین
    0.64
     so
    0.63
     dAtA
    0.63
     поэтому
    0.62
     nên
    0.62
     hivyo
    0.61
     بنابراین
    0.58
    تقاوى
    0.57
    Act Density 0.243%

    No Known Activations