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

    Neuronpedia

    INDEX
    Explanations

    emojis and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tid
    -0.72
     Fou
    -0.69
     Sle
    -0.69
     Bale
    -0.68
     Abyssal
    -0.65
    EngineDebug
    -0.65
     Glou
    -0.64
    swick
    -0.64
     Kling
    -0.62
     Glas
    -0.61
    POSITIVE LOGITS
    Į
    1.72
    ¥ŀ
    1.68
    Ĵ
    1.66
    ĵ
    1.64
    ĻĤ
    1.61
    İ
    1.59
    ı
    1.53
    Ķ
    1.51
    ļ
    1.51
    į
    1.49
    Act Density 0.009%

    No Known Activations