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

    Neuronpedia

    INDEX
    Explanations

    statements about existence or the state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the verb "to be" (forms of "are" and "is").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     ſtate
    -1.05
     purpoſe
    -1.00
     itſelf
    -0.98
     myſelf
    -0.94
     uſed
    -0.94
     pleaſure
    -0.93
     raiſ
    -0.91
     Chriftian
    -0.91
     fubject
    -0.90
     poffible
    -0.89
    POSITIVE LOGITS
     is
    1.31
     are
    1.25
     not
    1.22
     a
    1.16
     be
    1.10
     being
    1.09
    ίναι
    1.06
     also
    1.00
     was
    0.99
     were
    0.96
    Act Density 1.464%

    No Known Activations