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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "have" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the verb "has" in various contexts.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
     Chriftian
    -0.95
     houſe
    -0.94
     myſelf
    -0.92
     ſtate
    -0.92
     poffible
    -0.89
     againſt
    -0.87
     Jefus
    -0.87
     Monfieur
    -0.86
     ainfi
    -0.83
     perfons
    -0.82
    POSITIVE LOGITS
     been
    1.40
     had
    1.39
     has
    1.25
     have
    1.06
     HAS
    1.05
     Has
    1.04
     a
    1.04
    had
    0.98
     HAD
    0.97
     Had
    0.92
    Act Density 0.421%

    No Known Activations