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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate future events or imminent releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abyrin
    -0.19
    abyrinth
    -0.16
    riz
    -0.15
    inho
    -0.15
    eses
    -0.14
    ÑĥÑĪка
    -0.14
    /DD
    -0.14
     ongoing
    -0.14
    ized
    -0.14
     existing
    -0.14
    POSITIVE LOGITS
    /current
    0.27
    /up
    0.18
    /new
    0.17
    -generation
    0.17
    lassen
    0.16
    ling
    0.15
     generations
    0.15
     retirees
    0.15
    /original
    0.15
    zer
    0.15
    Act Density 0.018%

    No Known Activations