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

    Neuronpedia

    INDEX
    Explanations

    specific strings of characters that seem to be technical or code-related in nature

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or characters related to identification codes or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dist
    -0.67
     Mall
    -0.65
    mont
    -0.65
     Cass
    -0.64
     Moon
    -0.63
     Swamp
    -0.63
     sea
    -0.62
     Triumph
    -0.61
     land
    -0.60
    mouth
    -0.59
    POSITIVE LOGITS
    ĸ
    4.52
    Ĺ
    2.13
    ķ
    1.75
    Ĭ
    1.72
    ĺ
    1.71
    ļ
    1.71
    ¤
    1.70
    ģ
    1.69
    ¦
    1.69
    Ī
    1.69
    Act Density 0.009%

    No Known Activations