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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technological actions or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    instances of attempts and classifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sem
    -0.75
    ey
    -0.71
    nar
    -0.70
    header
    -0.68
    amy
    -0.66
    foot
    -0.64
     Throne
    -0.64
    sey
    -0.62
    pert
    -0.62
    aly
    -0.62
    POSITIVE LOGITS
    Attempts
    3.13
     Countdown
    2.05
    Dist
    1.38
    Charges
    1.26
    Attempt
    1.01
    Late
    0.96
    Trend
    0.94
    GMT
    0.90
    ----------
    0.90
     Attempt
    0.88
    Act Density 0.050%

    No Known Activations