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

    Neuronpedia

    INDEX
    Explanations

    particular symbols or characters in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the symbol pattern "âĢ" indicating formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mous
    -0.90
     shroud
    -0.83
     dispers
    -0.77
     ASC
    -0.73
     assemb
    -0.71
     sled
    -0.71
     Schn
    -0.70
     scrambling
    -0.70
     sling
    -0.69
     Mall
    -0.68
    POSITIVE LOGITS
    ľ
    2.12
    ¡
    1.63
    Ķ
    1.60
    Ŀ
    1.55
    ª
    1.52
    ł
    1.49
    Ł
    1.47
    ļ
    1.45
    Ľ
    1.45
    ¦
    1.44
    Act Density 0.186%

    No Known Activations