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

    Neuronpedia

    INDEX
    Explanations

    statistics and numerical values mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to the world and its statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.75
    RAW
    -0.73
    INGTON
    -0.70
    SPONSORED
    -0.69
    PLA
    -0.69
    æ³
    -0.64
    imaru
    -0.64
     Zionism
    -0.63
    aciously
    -0.61
    idan
    -0.61
    POSITIVE LOGITS
     heaviest
    1.06
     smallest
    1.01
     country
    0.92
     largest
    0.86
     highest
    0.85
     earliest
    0.85
     nation
    0.84
     slightest
    0.84
     same
    0.83
     wearer
    0.81
    Act Density 0.211%

    No Known Activations