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

    Neuronpedia

    INDEX
    Explanations

    references to online content or activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "online."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.79
    ioxide
    -0.76
     Wing
    -0.67
    atories
    -0.64
    geries
    -0.64
    zik
    -0.63
     Zer
    -0.62
     Pod
    -0.61
    ========
    -0.60
    ouf
    -0.60
    POSITIVE LOGITS
    ibaba
    0.95
    culosis
    0.69
     multiplayer
    0.69
     encyclopedia
    0.67
     retailer
    0.67
    ledge
    0.67
     behavi
    0.66
     calcul
    0.66
     marketplace
    0.65
     streaming
    0.65
    Act Density 0.016%

    No Known Activations