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

    Neuronpedia

    INDEX
    Explanations

    instances of satire and its related concepts

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

    satire, satirical, satiety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.60
    JAKARTA
    -0.59
    windowFixed
    -0.52
    IBOutlet
    -0.52
    anganese
    -0.50
    URLConnection
    -0.49
     cherokee
    -0.49
     tiguan
    -0.48
    dagangan
    -0.48
    endregion
    -0.48
    POSITIVE LOGITS
     Sati
    1.55
     sati
    1.48
     satire
    1.38
     satirical
    1.11
     Sat
    0.84
     sat
    0.82
     Saty
    0.81
     SAT
    0.76
    atire
    0.69
    Sat
    0.68
    Act Density 0.012%

    No Known Activations