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

    Neuronpedia

    INDEX
    Explanations

    instances where the number "100" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, especially those related to quantities or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.91
    eatures
    -0.72
    rift
    -0.67
    isphere
    -0.67
    Leary
    -0.66
    ideon
    -0.65
    interstitial
    -0.65
    ibur
    -0.65
     hither
    -0.65
    gey
    -0.64
    POSITIVE LOGITS
     100
    3.11
     1000
    2.13
     200
    2.04
    100
    2.00
     150
    1.95
     500
    1.90
     300
    1.89
     50
    1.88
     110
    1.86
     10000
    1.85
    Act Density 0.022%

    No Known Activations