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

    Neuronpedia

    INDEX
    Explanations

    claims of entitlement and perceived superiority based on institutional affiliation

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

    preceding or related to "bullshit"

    np_acts-logits-general · gemini-2.0-flash

    meaningless claims and falsehoods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.77
     fevere
    -0.68
    GraphicsUnit
    -0.67
     pleaſure
    -0.67
     fubject
    -0.66
    Occasion
    -0.66
     occaf
    -0.66
     ſtate
    -0.65
     uſe
    -0.64
     occafion
    -0.64
    POSITIVE LOGITS
     nonsense
    1.93
     bullshit
    1.52
     crap
    1.50
     stuff
    1.42
    nonsense
    1.38
     rubbish
    1.32
    Nonsense
    1.28
    onsense
    1.18
     gibber
    1.16
     shit
    1.12
    Act Density 0.420%

    No Known Activations