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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.23
     myſelf
    -1.03
     Jefus
    -1.03
     ftill
    -1.02
     ſtill
    -1.02
     themſelves
    -0.99
     Majefty
    -0.99
     ſche
    -0.98
     ſeveral
    -0.98
     pleaſure
    -0.97
    POSITIVE LOGITS
     able
    1.19
     a
    0.82
     an
    0.75
     seen
    0.74
    friend
    0.70
     the
    0.66
     held
    0.65
     considered
    0.64
     so
    0.63
     made
    0.62
    Act Density 0.385%

    No Known Activations