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

    Neuronpedia

    INDEX
    Explanations

    dates or events of releases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "released."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isma
    -0.79
    stal
    -0.66
    iop
    -0.66
    anan
    -0.66
    pill
    -0.62
    ophe
    -0.62
    enter
    -0.62
     Mé
    -0.60
     imperson
    -0.60
    fine
    -0.59
    POSITIVE LOGITS
    æĸ¹
    0.98
    quished
    0.92
    éĹĺ
    0.91
    released
    0.85
     Seym
    0.80
    lisher
    0.79
     releasing
    0.76
    ãĥ¯
    0.75
    20439
    0.74
     Releases
    0.74
    Act Density 0.035%

    No Known Activations