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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numeric identifiers or significant years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aith
    -0.81
    aeus
    -0.80
    aye
    -0.79
    reek
    -0.76
    akes
    -0.75
    itta
    -0.70
    rd
    -0.70
    ritten
    -0.69
    ayn
    -0.68
    eday
    -0.67
    POSITIVE LOGITS
    20439
    1.01
    0100
    0.92
    6666
    0.85
    384
    0.81
    tenance
    0.78
    66666666
    0.76
    016
    0.76
    554
    0.75
    MHz
    0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.73
    Act Density 0.058%

    No Known Activations