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

    Neuronpedia

    INDEX
    Explanations

    references to the passage of time and the concept of time itself

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ramid
    -0.94
    ourt
    -0.93
    ortium
    -0.88
    qqa
    -0.87
    riad
    -0.87
    rosis
    -0.85
    warts
    -0.83
    erto
    -0.81
    heses
    -0.80
    doms
    -0.80
    POSITIVE LOGITS
    frames
    1.29
    frame
    1.11
    zone
    1.00
     stamps
    0.90
     Spiral
    0.90
    borne
    0.89
    glass
    0.89
     elapsed
    0.86
     Warner
    0.84
     consuming
    0.83
    Act Density 9.546%

    No Known Activations