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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political themes, especially focusing on specific individuals and events

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "independent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sshd
    -0.93
    ongyang
    -0.88
    ĵĺ
    -0.71
    wagen
    -0.69
    idon
    -0.67
    interstitial
    -0.64
     AVG
    -0.64
    =-=-=-=-=-=-=-=-
    -0.63
    taboola
    -0.62
    =-=-=-=-
    -0.61
    POSITIVE LOGITS
    azeera
    0.87
    aucuses
    0.80
    ixture
    0.71
    oland
    0.71
    apolis
    0.70
    asia
    0.69
    ctr
    0.69
    cest
    0.68
    ogo
    0.68
    ja
    0.67
    Act Density 0.077%

    No Known Activations