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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "month"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.86
    ufficient
    -0.71
    aque
    -0.71
     UID
    -0.70
    unders
    -0.69
    emort
    -0.68
    icket
    -0.68
    akes
    -0.67
    ortium
    -0.67
    itutional
    -0.66
    POSITIVE LOGITS
    iversary
    0.98
    days
    0.91
     Ago
    0.91
    ruary
    0.88
     ago
    0.86
    flower
    0.82
     Fool
    0.80
     Ukrain
    0.78
     Ples
    0.76
     anniversary
    0.75
    Act Density 0.028%

    No Known Activations