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

    Neuronpedia

    INDEX
    Explanations

    Latin words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols, particularly accented letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.80
    Assembly
    -0.71
    ragon
    -0.70
    aday
    -0.68
     Dragonbound
    -0.67
    Asset
    -0.65
    ifference
    -0.64
     Belt
    -0.64
     Cookies
    -0.64
    aturdays
    -0.63
    POSITIVE LOGITS
    É
    1.27
    Ļ
    1.19
    ¾
    1.18
    Ĵ
    1.18
    ©
    1.17
    ª
    1.17
    Ľ
    1.15
    ´
    1.15
    Ķ
    1.15
    ¡
    1.12
    Act Density 0.013%

    No Known Activations