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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" in various forms and usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.70
     Hilde
    -0.59
     funcion
    -0.59
     Église
    -0.58
    PyExc
    -0.57
     purpoſe
    -0.57
    chtung
    -0.56
     kaban
    -0.56
     Kina
    -0.55
     Româ
    -0.55
    POSITIVE LOGITS
     are
    1.69
     ARE
    1.56
     Are
    1.50
     were
    1.41
    Are
    1.41
     Were
    1.36
     WERE
    1.34
    Were
    1.26
    were
    1.21
    are
    1.20
    Act Density 0.398%

    No Known Activations