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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of names, places, and titles, especially focusing on individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo

    specific brand or company names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.74
    anwhile
    -0.69
     pleas
    -0.69
     stride
    -0.67
     altogether
    -0.67
     yourselves
    -0.65
     Petraeus
    -0.64
     wise
    -0.64
     root
    -0.62
     Warwick
    -0.61
    POSITIVE LOGITS
    ifles
    1.11
    eworks
    1.10
    istries
    1.08
    astery
    1.03
     Ltd
    0.98
    uctions
    0.97
    ifts
    0.95
    ework
    0.94
    ipel
    0.93
    itars
    0.92
    Act Density 0.307%

    No Known Activations