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

    Neuronpedia

    INDEX
    Explanations

    references to time, specifically events or conditions in the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CDP
    -0.81
     Sardinia
    -0.79
    Municipio
    -0.77
     Jeanette
    -0.77
     Garibaldi
    -0.76
    aarrggbb
    -0.76
     Mukherjee
    -0.75
     Richelieu
    -0.74
     Kugel
    -0.74
     lighten
    -0.74
    POSITIVE LOGITS
     Past
    1.60
    Past
    1.47
     past
    1.43
    past
    1.34
    PAST
    1.31
     PAST
    1.29
     Pasture
    0.78
     Pas
    0.76
     few
    0.76
     Ago
    0.75
    Act Density 0.037%

    No Known Activations