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

    Neuronpedia

    INDEX
    Explanations

    questions and interrogative phrases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Verge
    -0.68
    Brooks
    -0.68
    NameInMap
    -0.68
    rawDesc
    -0.68
     Aze
    -0.67
    timbangkan
    -0.66
     reminder
    -0.64
     Tabor
    -0.63
    TestingModule
    -0.63
    ksu
    -0.63
    POSITIVE LOGITS
     what
    1.87
     WHAT
    1.80
    What
    1.79
     What
    1.77
    what
    1.74
    WHAT
    1.73
    Qué
    1.16
    Τι
    1.05
     quelles
    1.04
    Quelles
    1.03
    Act Density 0.789%

    No Known Activations