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

    Neuronpedia

    INDEX
    Explanations

    products or items with a numerical value of '1' indicating popularity or significance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "1" followed by different contextual values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaru
    -0.73
     Lumpur
    -0.73
    orative
    -0.64
    enges
    -0.61
    anty
    -0.60
    opy
    -0.60
    alus
    -0.59
    espie
    -0.59
     Pompe
    -0.59
    folk
    -0.59
    POSITIVE LOGITS
    Password
    1.27
    st
    1.27
    125
    1.22
    120
    1.20
    ½
    1.06
    128
    1.02
    000000
    0.99
    âģ
    0.99
    123
    0.87
    0000000
    0.86
    Act Density 0.108%

    No Known Activations