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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    repeated punctuation marks and symbols that may signify a pattern or emphasis in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     segreg
    -0.77
     tremend
    -0.71
     Sabha
    -0.70
     dispers
    -0.70
     Cycl
    -0.70
     Mous
    -0.69
     assemb
    -0.68
     sling
    -0.68
     CMS
    -0.68
     Alc
    -0.66
    POSITIVE LOGITS
    ľ
    1.71
    ¬
    1.26
    ¦
    1.22
    Ľ
    1.21
    ł
    1.20
    ¼
    1.15
    Ń
    1.14
    ª
    1.12
    ¡
    1.12
    º
    1.11
    Act Density 0.283%

    No Known Activations