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

    Neuronpedia

    INDEX
    Explanations

    numbers related to specific months or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and time-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rio
    -0.82
     laun
    -0.70
    ¥µ
    -0.68
    roo
    -0.68
    agi
    -0.67
    ridge
    -0.66
    ighthouse
    -0.65
    hub
    -0.64
    ysis
    -0.64
    google
    -0.63
    POSITIVE LOGITS
    ())
    0.97
     (
    0.95
     (),
    0.90
    ('
    0.88
    (
    0.87
     (?,
    0.85
     ().
    0.83
    (),
    0.80
    ("
    0.79
    ()
    0.78
    Act Density 0.179%

    No Known Activations