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

    Neuronpedia

    INDEX
    Explanations

    time-related information such as durations, dates, and sequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or recurrence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CK
    -0.66
     Wikimedia
    -0.64
     Rolls
    -0.61
    "}
    -0.60
    Mech
    -0.59
     Folder
    -0.58
    ufact
    -0.58
     WordPress
    -0.57
    ".[
    -0.57
     sponge
    -0.56
    POSITIVE LOGITS
    姫
    0.85
    Ĭ±
    0.74
    rand
    0.72
    ALSE
    0.71
    whether
    0.68
    ulk
    0.68
    Aust
    0.68
    DERR
    0.66
    omething
    0.64
    president
    0.62
    Act Density 0.394%

    No Known Activations