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

    Neuronpedia

    INDEX
    Explanations

    strings of characters that might represent technical data or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols that may represent a particular format or context in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rul
    -0.69
     Seym
    -0.69
     glim
    -0.68
     ponies
    -0.67
    okemon
    -0.67
     lipstick
    -0.66
     creeps
    -0.66
     sacrific
    -0.66
    ebin
    -0.65
     idea
    -0.65
    POSITIVE LOGITS
    ï¸ı
    0.89
     Ibid
    0.83
    âĢł
    0.83
    Abstract
    0.82
    âĪ
    0.82
    §
    0.81
    âģ
    0.79
    âĵĺ
    0.78
    ¶
    0.78
    Struct
    0.75
    Act Density 0.546%

    No Known Activations