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

    Neuronpedia

    INDEX
    Explanations

    updates or changes in information

    oai_token-act-pair · gpt-3.5-turbo

    repetitive structures and patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ourselves
    -0.70
    uten
    -0.67
     hasht
    -0.67
     attent
    -0.65
     myself
    -0.64
    utan
    -0.64
     Pradesh
    -0.62
    ivably
    -0.61
    ulously
    -0.60
     Hydra
    -0.60
    POSITIVE LOGITS
    Updated
    1.01
    Posted
    0.98
    ALE
    0.79
    agher
    0.77
    ccording
    0.71
    ritz
    0.70
    hello
    0.69
    Published
    0.67
    ¶
    0.67
     Mayo
    0.67
    Act Density 0.153%

    No Known Activations