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

    Neuronpedia

    INDEX
    Explanations

    words that end with the specific Unicode character “Ļ”

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'L' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fascination
    -0.77
     Koen
    -0.70
     Indra
    -0.69
     Argon
    -0.68
     Nau
    -0.68
     Mobil
    -0.66
     Folk
    -0.66
    Topic
    -0.65
     notebooks
    -0.65
     Crusher
    -0.65
    POSITIVE LOGITS
    ufact
    1.06
    ï¸ı
    1.02
    shall
    0.89
    independence
    0.88
    defined
    0.88
    sic
    0.87
    agree
    0.87
    they
    0.85
    actual
    0.85
    accept
    0.85
    Act Density 0.256%

    No Known Activations