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

    Neuronpedia

    INDEX
    Explanations

    elements related to deception and disguise

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

    Acting or appearing as someone/something else

    np_acts-logits-general · gemini-2.0-flash

    pretending to be someone else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.69
    Referencer
    -0.65
     Wiktionnaire
    -0.63
    DeleteBehavior
    -0.60
     '\\;'
    -0.58
    رشف
    -0.57
    reportWebVitals
    -0.56
     fré
    -0.56
    getSeconds
    -0.56
     aapt
    -0.55
    POSITIVE LOGITS
     disguise
    1.86
     disguised
    1.68
     pretending
    1.64
     fake
    1.63
     disgu
    1.63
     pretended
    1.56
     faking
    1.49
     pretends
    1.44
     masquer
    1.43
    fake
    1.42
    Act Density 0.495%

    No Known Activations