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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with computer hardware components

    oai_token-act-pair · gpt-3.5-turbo

    references to the Windows 8 operating system and its associated features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andise
    -0.77
    é¾įå¥ij士
    -0.75
    ãĥ¼ãĥĨ
    -0.70
    insula
    -0.67
     Lauder
    -0.66
     parach
    -0.66
    iage
    -0.64
     ancest
    -0.63
     railing
    -0.63
    itton
    -0.62
    POSITIVE LOGITS
    192
    1.23
    90
    1.05
    98
    1.04
    989
    1.03
    88
    0.98
    een
    0.97
    79
    0.94
    ecause
    0.94
    58
    0.93
    57
    0.92
    Act Density 0.055%

    No Known Activations