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

    Neuronpedia

    INDEX
    Explanations

    references to authors and editors

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and their roles or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nicaragua
    -0.67
    Ĥª
    -0.65
    ierrez
    -0.65
    UGE
    -0.62
    EMS
    -0.62
     Bolivia
    -0.62
    xon
    -0.61
    ll
    -0.61
     dancers
    -0.61
    roads
    -0.61
    POSITIVE LOGITS
    itatively
    1.63
    itar
    1.57
    itarian
    1.42
    itative
    1.31
    hip
    1.21
    izations
    1.04
    uscript
    1.01
    sonian
    1.01
    isations
    1.01
    isation
    1.00
    Act Density 0.042%

    No Known Activations