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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific groups or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group or organization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Appears
    -0.75
     Magicka
    -0.69
     Latest
    -0.69
    èª
    -0.64
    cale
    -0.63
    Adv
    -0.63
    shire
    -0.63
    lite
    -0.63
    lvl
    -0.61
     Highest
    -0.59
    POSITIVE LOGITS
    roups
    0.99
     members
    0.94
     group
    0.90
     groups
    0.89
    think
    0.89
    members
    0.86
    atics
    0.86
    naires
    0.85
    arettes
    0.85
     affili
    0.83
    Act Density 0.053%

    No Known Activations