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

    Neuronpedia

    INDEX
    Explanations

    words related to computer operating systems, particularly Windows Vista

    oai_token-act-pair · gpt-3.5-turbo

    terms related to professions or roles associated with people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MENTS
    -0.85
    shaw
    -0.82
    auld
    -0.81
    orough
    -0.80
    ibble
    -0.79
    quartered
    -0.77
    inance
    -0.76
    nel
    -0.76
    lying
    -0.76
    lie
    -0.76
    POSITIVE LOGITS
    uthor
    0.87
     da
    0.83
    perture
    0.77
    ño
    0.76
    BILITY
    0.74
    uto
    0.73
    zzi
    0.73
    ista
    0.72
     Dia
    0.71
    ignt
    0.71
    Act Density 0.019%

    No Known Activations