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

    Neuronpedia

    INDEX
    Explanations

    phrases related to upcoming events or announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to upcoming events or releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licted
    -0.70
    heit
    -0.70
    entimes
    -0.68
    wrong
    -0.67
    onds
    -0.65
    evidence
    -0.65
    achus
    -0.64
    igion
    -0.63
    abul
    -0.62
    administ
    -0.62
    POSITIVE LOGITS
     updates
    0.97
     launches
    0.93
     release
    0.93
     teaser
    0.92
     releases
    0.91
     announcements
    0.91
     launch
    0.91
     premiere
    0.91
     Xiaomi
    0.90
     update
    0.89
    Act Density 0.991%

    No Known Activations