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

    Neuronpedia

    INDEX
    Explanations

    terms related to indicators and measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HasIndex
    -0.62
    ArgumentParser
    -0.57
    autique
    -0.57
     spørs
    -0.55
    ]))
    -0.53
     everywhere
    -0.51
     médicaux
    -0.51
    LEZ
    -0.50
    QWidget
    -0.49
     geslacht
    -0.49
    POSITIVE LOGITS
     respectively
    1.51
     respective
    1.35
    respectively
    1.34
     rispet
    1.07
     respectivement
    1.06
    それぞれ
    1.05
     respectivamente
    1.04
     jeweils
    1.00
     masing
    0.99
    各自
    0.94
    Act Density 1.096%

    No Known Activations