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

    Neuronpedia

    INDEX
    Explanations

    numbers with little context or scattered throughout the text

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers, particularly related to dates and voting results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eners
    -0.76
    reek
    -0.76
    aith
    -0.75
    achu
    -0.75
    aye
    -0.74
    rd
    -0.74
    reen
    -0.72
    ornia
    -0.69
    ensibly
    -0.68
    aeus
    -0.68
    POSITIVE LOGITS
    20439
    1.02
    384
    0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.72
    0100
    0.72
    6666
    0.72
    MHz
    0.72
    İĭ
    0.70
    ïve
    0.68
    tenance
    0.67
    66666666
    0.67
    Act Density 0.071%

    No Known Activations