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

    Neuronpedia

    INDEX
    Explanations

    items listed within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.83
    enance
    -0.75
    ¯
    -0.64
    ff
    -0.62
     Shutterstock
    -0.62
    erers
    -0.61
    edia
    -0.59
    iffs
    -0.59
    ĸļ
    -0.58
     nearby
    -0.57
    POSITIVE LOGITS
     Including
    1.21
     totaling
    1.19
     apiece
    1.08
    including
    1.02
     including
    0.98
     consecut
    0.90
     total
    0.82
    each
    0.81
     tot
    0.78
    ãĥ¯ãĥ³
    0.76
    Act Density 0.468%

    No Known Activations