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

    Neuronpedia

    INDEX
    Explanations

    references to inclusivity and collective experiences

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

    everyone and everybody

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    subpackage
    -0.52
     NSCoder
    -0.41
    ⟬
    -0.41
    setBold
    -0.40
     expériment
    -0.39
     noDo
    -0.39
    [--
    -0.38
     paramString
    -0.37
     itemprop
    -0.36
     dalších
    -0.36
    POSITIVE LOGITS
    Everyone
    1.07
     Everybody
    1.06
     Everyone
    1.05
    Everybody
    1.04
    everyone
    0.82
     EVERYONE
    0.80
    everybody
    0.80
     everybody
    0.78
    Nobody
    0.77
     everyone
    0.75
    Act Density 0.012%

    No Known Activations