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

    Neuronpedia

    INDEX
    Explanations

    references to specific months

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months, particularly September and October

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.80
    emort
    -0.79
    anooga
    -0.78
    ioch
    -0.76
    aque
    -0.72
    UTF
    -0.70
    ufficient
    -0.69
    icket
    -0.68
    inburgh
    -0.67
    ortium
    -0.65
    POSITIVE LOGITS
    days
    0.92
    flower
    0.90
    iversary
    0.88
     ago
    0.81
    ruary
    0.81
     Ples
    0.81
     Ago
    0.81
     Ukrain
    0.76
     Fool
    0.74
    nard
    0.73
    Act Density 0.028%

    No Known Activations