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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ratios and measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fe
    -0.43
    owie
    -0.41
    ваете
    -0.41
     vidi
    -0.41
    ueta
    -0.40
     Nä
    -0.40
    canal
    -0.40
    ster
    -0.39
    Hid
    -0.39
    feri
    -0.39
    POSITIVE LOGITS
    Diweddarwch
    0.88
    Personensuche
    0.86
     propOrder
    0.75
     Ratios
    0.75
     RATIO
    0.73
    NameInMap
    0.73
     onOptions
    0.73
     ratio
    0.71
     فريبيس
    0.71
     שוליים
    0.70
    Act Density 0.485%

    No Known Activations