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

    Neuronpedia

    INDEX
    Explanations

    mentions of durations of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate durations of time or quantities in excess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":[
    -0.74
     Solution
    -0.68
    Express
    -0.66
     hereafter
    -0.63
    ILY
    -0.62
     Lauder
    -0.62
     Mate
    -0.61
     thence
    -0.60
    Ô
    -0.60
     Bomber
    -0.59
    POSITIVE LOGITS
    drive
    1.04
    tones
    1.00
    hang
    1.00
    whelming
    0.98
    capacity
    0.97
    priced
    0.96
    kill
    0.96
    haul
    0.92
    lander
    0.91
    valued
    0.91
    Act Density 0.049%

    No Known Activations