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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb "have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.97
     Chriftian
    -0.94
     ſche
    -0.92
     houſe
    -0.86
     poffible
    -0.86
     ſtate
    -0.85
     Jefus
    -0.84
     ſch
    -0.82
     againſt
    -0.82
     Monfieur
    -0.82
    POSITIVE LOGITS
     have
    1.50
     been
    1.49
     had
    1.38
     has
    1.35
     Have
    1.08
     HAVE
    1.08
     Has
    1.03
    have
    1.02
     got
    1.01
     HAS
    0.99
    Act Density 0.459%

    No Known Activations