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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and numerical values related to computer processors

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical values or identifiers associated with data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.77
    iple
    -0.75
    owered
    -0.71
    herer
    -0.71
    atis
    -0.70
    ãĥ´ãĤ¡
    -0.67
    utra
    -0.66
    awaru
    -0.66
    herty
    -0.66
    etsk
    -0.65
    POSITIVE LOGITS
    nd
    1.16
    rd
    0.99
    00
    0.82
    ¯¯
    0.74
    een
    0.73
    ald
    0.71
    nces
    0.70
    50
    0.70
    th
    0.69
    lake
    0.69
    Act Density 0.068%

    No Known Activations