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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chriftian
    -1.02
     pleaſure
    -1.02
     purpoſe
    -1.01
     Jefus
    -0.99
     ſtate
    -0.98
     Theſe
    -0.96
     ſeveral
    -0.95
     myſelf
    -0.95
     Houſe
    -0.95
     houſe
    -0.95
    POSITIVE LOGITS
     not
    1.32
     is
    1.30
     also
    1.15
     always
    1.11
     a
    1.08
     actually
    1.03
     indeed
    1.02
     still
    1.01
     was
    0.99
     are
    0.97
    Act Density 1.342%

    No Known Activations