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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOPQRST
    -0.70
     distanciation
    -0.70
     autorytatywna
    -0.67
    DoubleQuotes
    -0.63
    verwijspagina
    -0.62
    ΙΣ
    -0.61
     Oppen
    -0.59
     Mooney
    -0.59
    OLUTION
    -0.59
     ters
    -0.57
    POSITIVE LOGITS
     would
    1.02
     WOULD
    0.98
     Would
    0.97
    would
    0.91
     Will
    0.89
    Would
    0.89
    Will
    0.86
    d
    0.84
     youll
    0.79
    Might
    0.78
    Act Density 0.048%

    No Known Activations