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

    Neuronpedia

    INDEX
    Explanations

    comparisons and estimates related to resource recovery and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    636
    -0.16
    odo
    -0.15
    irth
    -0.14
    idget
    -0.14
    odos
    -0.14
    gil
    -0.14
    ates
    -0.14
    allest
    -0.14
    throp
    -0.14
     Mil
    -0.14
    POSITIVE LOGITS
     exactly
    0.20
    enz
    0.19
    pter
    0.18
     actual
    0.18
    iets
    0.17
    actual
    0.17
     Äijúng
    0.17
     ÑĦакÑĤи
    0.16
    accuracy
    0.16
     Actual
    0.15
    Act Density 0.199%

    No Known Activations