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

    Neuronpedia

    INDEX
    Explanations

    conjugated forms of the verb "to be."

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

    Follows "be" and precedes adverbs/adjectives

    np_acts-logits-general · gemini-2.0-flash

    future states/actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     egentlig
    -0.60
    stdc
    -0.59
     actually
    -0.53
    থ্য
    -0.50
     eigentlich
    -0.48
     supposed
    -0.47
    Originally
    -0.47
     already
    -0.47
    竟然
    -0.47
     intended
    -0.47
    POSITIVE LOGITS
     prochain
    0.96
     tomorrow
    0.95
    tomorrow
    0.90
     bientôt
    0.87
     soon
    0.83
     forever
    0.82
     demain
    0.81
    plenty
    0.79
    forever
    0.77
    soon
    0.74
    Act Density 0.234%

    No Known Activations