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

    Neuronpedia

    INDEX
    Explanations

    timestamps or specific times mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time zones and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.94
    ortium
    -0.90
    warts
    -0.86
    ourt
    -0.83
    uthor
    -0.79
    gew
    -0.79
    rim
    -0.77
    riks
    -0.70
    ramid
    -0.69
    rative
    -0.68
    POSITIVE LOGITS
    frames
    1.18
    zone
    0.94
     elapsed
    0.93
    frame
    0.92
    clock
    0.85
     stamps
    0.83
    glass
    0.81
    points
    0.79
    caps
    0.79
     continuum
    0.79
    Act Density 0.068%

    No Known Activations