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

    Neuronpedia

    INDEX
    Explanations

    words ending in "-ation"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tsukuyomi
    -0.77
    ADE
    -0.72
    ONSORED
    -0.66
    Rogue
    -0.64
     destro
    -0.62
     Bangl
    -0.61
     forks
    -0.60
     Xie
    -0.60
     Paula
    -0.60
     Choi
    -0.60
    POSITIVE LOGITS
    abase
    1.01
    hetically
    0.97
    istical
    0.96
    rix
    0.94
    hemat
    0.94
    uitous
    0.93
    ting
    0.92
    istics
    0.91
    roph
    0.88
    rice
    0.87
    Act Density 0.023%

    No Known Activations