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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns, specifically first-person singular pronouns and mentions of the self

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

    "I think" or "I would" statements

    np_acts-logits-general · gemini-2.0-flash

    expressing certainty or doubt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.54
     fossa
    -0.50
    ंदीखरीदारी
    -0.49
     BoxFit
    -0.47
     चीज़ों
    -0.43
    hend
    -0.42
    atoto
    -0.41
    setContentView
    -0.40
     برانيه
    -0.39
    rmtree
    -0.39
    POSITIVE LOGITS
     sure
    1.45
     bet
    1.34
    sure
    1.26
     certeza
    1.22
     doubt
    1.16
     SURE
    1.16
     guarantee
    1.15
     assure
    1.15
     bets
    1.11
     sûr
    1.08
    Act Density 0.189%

    No Known Activations