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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "be"

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

    "Be" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    be + adjective/determiner/participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.40
     Jefus
    -1.36
     pleaſure
    -1.24
     myſelf
    -1.19
     themſelves
    -1.15
     Chriftian
    -1.15
     ſtate
    -1.13
     purpoſe
    -1.11
     houſe
    -1.09
     becauſe
    -1.08
    POSITIVE LOGITS
     be
    1.31
     able
    1.29
     a
    1.19
     an
    1.12
     Be
    0.93
     the
    0.93
     part
    0.90
     very
    0.90
     seen
    0.89
     quite
    0.85
    Act Density 0.369%

    No Known Activations