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

    Neuronpedia

    INDEX
    Explanations

    references to madness and insanity

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

    madness, insanity, and mania

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.56
    -0.42
    ➥
    -0.40
     Administrativna
    -0.40
     Utf
    -0.39
     Sikh
    -0.38
    Carson
    -0.38
    Shir
    -0.38
    etsk
    -0.37
    zeera
    -0.37
    POSITIVE LOGITS
     madness
    1.87
     Madness
    1.76
    Madness
    1.59
     insanity
    1.23
     locura
    1.23
     frenzy
    1.02
     mania
    0.95
     craz
    0.94
     Mania
    0.86
     chaos
    0.85
    Act Density 0.004%

    No Known Activations