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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    NotBe
    -0.48
    Be
    -0.47
    fe
    -0.45
    Slides
    -0.45
    ato
    -0.44
     colspan
    -0.44
     Be
    -0.43
     oleh
    -0.43
    смотря
    -0.43
     pozna
    -0.43
    POSITIVE LOGITS
    OGND
    0.88
    )++;
    0.86
    Искәрмәләр
    0.85
     Roskov
    0.81
    RepeatedField
    0.81
    aarrggbb
    0.79
     فريبيس
    0.79
    UnusedPrivate
    0.79
     EconPapers
    0.77
    UnitTesting
    0.77
    Act Density 0.113%

    No Known Activations