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

    Neuronpedia

    INDEX
    Explanations

    phrases related to high-quality or top-notch entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to "world-class" status or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.80
    arty
    -0.76
    pty
    -0.73
    YA
    -0.70
    oult
    -0.70
    foreseen
    -0.69
    microsoft
    -0.68
    addon
    -0.66
    HUD
    -0.65
     Grimes
    -0.65
    POSITIVE LOGITS
    ifications
    1.16
    ifiers
    1.13
    ifying
    1.05
    ified
    1.04
    ifier
    0.99
    ification
    0.98
    ifies
    0.93
    ifiable
    0.89
    smanship
    0.88
    ify
    0.87
    Act Density 0.020%

    No Known Activations