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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of individuals' names

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or institutional classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minecraft
    -0.69
     è£ıè
    -0.69
    anova
    -0.69
    ongyang
    -0.64
    incial
    -0.64
    inational
    -0.63
    yip
    -0.62
    hani
    -0.61
    achev
    -0.61
    ghai
    -0.61
    POSITIVE LOGITS
     Wonderland
    0.74
    isse
    0.68
    enment
    0.68
     Citation
    0.64
     2024
    0.63
     Franch
    0.62
    iencies
    0.62
     Lauder
    0.62
     Gutierrez
    0.61
    Sah
    0.61
    Act Density 0.826%

    No Known Activations