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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "users"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of users in various contexts within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hurricanes
    -0.69
     Shore
    -0.68
    FLAG
    -0.68
    western
    -0.67
     Shack
    -0.65
     Baptist
    -0.64
     Scand
    -0.63
     Rib
    -0.62
     Hat
    -0.62
     Caldwell
    -0.62
    POSITIVE LOGITS
    pace
    1.07
    hip
    0.99
    paces
    0.95
    cript
    0.90
     users
    0.87
    mens
    0.83
    wana
    0.83
    ettings
    0.80
     interfaces
    0.80
    hao
    0.79
    Act Density 0.019%

    No Known Activations