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

    Neuronpedia

    INDEX
    Explanations

    events related to specific time spans, particularly months and years

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    inav
    -1.09
     hypocr
    -1.08
    anooga
    -1.07
     Haram
    -1.05
    inburgh
    -1.04
    inite
    -0.98
    duction
    -0.97
    bidden
    -0.96
    ech
    -0.95
     VIDEOS
    -0.92
    POSITIVE LOGITS
     ago
    1.55
    pring
    1.30
     gestation
    1.14
    assetsadobe
    1.14
     Ples
    1.11
     pregnant
    1.06
     Ago
    1.04
    hips
    1.03
     elapsed
    1.02
     Ukrain
    1.01
    Act Density 0.604%

    No Known Activations