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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

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

    phrases expressing judicial or authoritative opinion using "we are" or similar first-person plural statements of conclusion.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.45
     adquirido
    -0.42
    ########.
    -0.41
    indd
    -0.40
    InstrumentedTest
    -0.40
     dormitórios
    -0.39
    SequentialGroup
    -0.38
    Портали
    -0.38
     bewe
    -0.37
    Abit
    -0.37
    POSITIVE LOGITS
     convinced
    0.65
     aware
    0.61
     interested
    0.61
     confident
    0.60
     willing
    0.60
     unable
    0.55
     Interested
    0.54
    unable
    0.54
    interested
    0.53
     able
    0.52
    Act Density 0.367%

    No Known Activations