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

    Neuronpedia

    INDEX
    Explanations

    questions and statements regarding beliefs and skepticism about social issues

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

    people being fooled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.46
    Symmetry
    -0.35
     Symmetric
    -0.35
    Unmount
    -0.35
     Asymmetric
    -0.34
     Docks
    -0.34
    úmeros
    -0.34
    WebElementEntity
    -0.34
     viață
    -0.33
    scribers
    -0.33
    POSITIVE LOGITS
     gul
    1.27
     fooled
    1.19
     naive
    1.12
     unsuspecting
    0.96
     deceived
    0.96
     sucker
    0.96
     naïve
    0.95
     suckers
    0.94
     naï
    0.93
     tricked
    0.92
    Act Density 0.119%

    No Known Activations