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

    Neuronpedia

    INDEX
    Explanations

    new features or enhancements

    oai_token-act-pair · gpt-3.5-turbo

    highlighted elements related to software updates and enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Benz
    -0.69
    ieth
    -0.68
    nee
    -0.66
    Ire
    -0.65
    onel
    -0.64
    sis
    -0.63
    prison
    -0.62
    inventoryQuantity
    -0.62
    engeance
    -0.61
    osate
    -0.60
    POSITIVE LOGITS
     including
    1.11
     ranging
    1.06
     includ
    1.00
     such
    0.99
     goodies
    0.93
     besides
    0.92
     pertaining
    0.91
     namely
    0.91
     Included
    0.91
     included
    0.90
    Act Density 0.259%

    No Known Activations