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

    Neuronpedia

    INDEX
    Explanations

    specific dates and numerical data within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierz
    -0.16
    ALAR
    -0.15
    ãĤ¦ãĥĪ
    -0.15
    pll
    -0.15
    phia
    -0.15
    classnames
    -0.14
    DataURL
    -0.14
    DAQ
    -0.14
    oplayer
    -0.14
    igham
    -0.14
    POSITIVE LOGITS
    th
    0.35
     th
    0.22
    rd
    0.20
    TH
    0.20
    Th
    0.17
    nd
    0.17
    thin
    0.17
    thy
    0.16
     ------
    0.15
    _th
    0.15
    Act Density 0.036%

    No Known Activations