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

    Neuronpedia

    INDEX
    Explanations

    references to inclusivity and collective recognition of people

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

    "everyone"

    np_acts-logits-general · gemini-2.0-flash

    everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iscri
    -0.50
    y
    -0.50
     Utrecht
    -0.43
     pregi
    -0.42
    立
    -0.41
    kyard
    -0.41
     anmelden
    -0.41
     chain
    -0.39
    llary
    -0.38
    大な
    -0.38
    POSITIVE LOGITS
    everyone
    1.04
     everyone
    0.93
     EVERYONE
    0.91
    everybody
    0.88
    Everyone
    0.87
     perſon
    0.86
    anyone
    0.85
     Everyone
    0.85
     everybody
    0.84
    someone
    0.79
    Act Density 0.089%

    No Known Activations