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

    Neuronpedia

    INDEX
    Explanations

    various URLs and related alphanumeric patterns

    oai_token-act-pair · gpt-3.5-turbo

    the presence of web URLs or references to online content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    t
    -0.85
    dor
    -0.85
    lining
    -0.76
    sburg
    -0.74
    wagon
    -0.74
    met
    -0.73
    rat
    -0.73
    tein
    -0.72
    lus
    -0.71
    mus
    -0.71
    POSITIVE LOGITS
    ecd
    1.16
    usterity
    1.04
    uthor
    1.04
    cean
    1.01
    pport
    0.95
    xt
    0.95
    velength
    0.94
    vern
    0.94
    hei
    0.88
    qi
    0.87
    Act Density 0.114%

    No Known Activations