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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.94
     triom
    -0.90
     purpoſe
    -0.85
     ſtate
    -0.85
     pleaſure
    -0.85
     poffible
    -0.83
     Jefus
    -0.81
     ſche
    -0.80
     myſelf
    -0.79
     auffi
    -0.78
    POSITIVE LOGITS
     be
    1.64
     Be
    1.28
    ToBe
    1.27
    Be
    1.25
     être
    1.10
     BE
    1.08
     shouldBe
    1.07
    tobe
    1.07
     able
    1.06
     being
    1.06
    Act Density 0.437%

    No Known Activations