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

    Neuronpedia

    INDEX
    Explanations

    numbers in a specific range

    oai_token-act-pair · gpt-3.5-turbo

    references to the Windows 8 operating system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itton
    -0.81
    ignore
    -0.62
    andise
    -0.62
    rison
    -0.61
    lich
    -0.61
     Lauder
    -0.60
     unpre
    -0.59
     Bride
    -0.59
     parach
    -0.59
     bellig
    -0.58
    POSITIVE LOGITS
    192
    1.15
    een
    1.07
    eenth
    1.06
    989
    0.99
    ecause
    0.96
    90
    0.94
    98
    0.94
    57
    0.90
    58
    0.89
    79
    0.86
    Act Density 0.074%

    No Known Activations