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

    Neuronpedia

    INDEX
    Explanations

    text related to news reports or official statements

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uty
    -0.77
    wic
    -0.77
    uba
    -0.77
    pell
    -0.72
    rypt
    -0.71
    uel
    -0.71
    uta
    -0.71
    weet
    -0.70
    abul
    -0.69
    obe
    -0.68
    POSITIVE LOGITS
     consequently
    1.08
     thereby
    1.04
     thus
    1.04
     hence
    1.00
     therefore
    1.00
     thence
    0.99
     subsequent
    0.97
     consequ
    0.91
     subsequently
    0.87
    romeda
    0.83
    Act Density 0.444%

    No Known Activations