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

    Neuronpedia

    INDEX
    Explanations

    the word "sooner" appearing in relation to time or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ward
    -0.72
     parap
    -0.66
    prison
    -0.64
    port
    -0.61
    riel
    -0.61
    pit
    -0.60
    square
    -0.58
     Divinity
    -0.58
     Syndicate
    -0.57
     Rain
    -0.56
    POSITIVE LOGITS
    aneously
    1.03
     than
    1.02
    than
    0.97
     arri
    0.81
     Than
    0.78
     "$:/
    0.76
    ened
    0.74
    iatus
    0.74
    nown
    0.73
    mares
    0.73
    Act Density 0.022%

    No Known Activations