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

    Neuronpedia

    INDEX
    Explanations

    details, interesting information, and specific facts within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to small, intriguing pieces of information or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mileage
    -0.78
     Warfare
    -0.66
    Ĥª
    -0.66
     Pwr
    -0.66
    ħĭ
    -0.65
    dash
    -0.65
     Ferdinand
    -0.65
     contraception
    -0.65
    Ļ½
    -0.64
     breathing
    -0.64
    POSITIVE LOGITS
    estate
    1.09
    aton
    0.95
    kees
    0.91
    uers
    0.89
    eworks
    0.89
    bley
    0.88
    chen
    0.86
    ance
    0.85
    iets
    0.84
    endum
    0.84
    Act Density 0.076%

    No Known Activations