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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "be" indicating existence or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.70
     myſelf
    -1.63
     ſtate
    -1.55
     purpoſe
    -1.50
     pleaſure
    -1.48
     Jefus
    -1.47
     houſe
    -1.46
     Chriftian
    -1.38
     themſelves
    -1.38
     Monfieur
    -1.37
    POSITIVE LOGITS
     be
    2.10
     Be
    1.58
    Be
    1.36
     a
    1.26
     BE
    1.22
     is
    1.21
    be
    1.19
     been
    1.19
     being
    1.12
     an
    1.09
    Act Density 0.386%

    No Known Activations