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

    Neuronpedia

    INDEX
    Explanations

    words in a specific format likely related to code snippets or excerpts from text processing tasks

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters used in text, particularly in song lyrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.88
     pione
    -0.88
    Þ
    -0.88
     hemor
    -0.78
     obser
    -0.73
     nomine
    -0.72
     exting
    -0.72
    ą
    -0.72
    Ý
    -0.71
    ö
    -0.71
    POSITIVE LOGITS
    Ŀ
    1.00
    70
    0.70
    470
    0.67
    âĢķ
    0.66
    bat
    0.66
    cham
    0.65
    ther
    0.65
    706
    0.64
    peat
    0.63
    poses
    0.63
    Act Density 0.186%

    No Known Activations