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

    Neuronpedia

    INDEX
    Explanations

    instances of fraud and deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    league
    -0.17
    deme
    -0.15
    tring
    -0.14
    á»ħ
    -0.14
    sez
    -0.14
    aggable
    -0.14
    Normalized
    -0.14
    anon
    -0.14
    Iterable
    -0.14
    CTL
    -0.14
    POSITIVE LOGITS
     cogn
    0.18
    /false
    0.17
    hd
    0.16
     false
    0.16
     Pump
    0.15
    ilden
    0.15
    pras
    0.15
    XC
    0.14
     leading
    0.14
    ona
    0.14
    Act Density 0.193%

    No Known Activations