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

    Neuronpedia

    INDEX
    Explanations

    words or phrases commonly found at the beginning of a sentence followed by a colon

    oai_token-act-pair · gpt-3.5-turbo

    references to a generic subject or object in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Polk
    -0.71
     Dayton
    -0.69
    hips
    -0.69
    dding
    -0.68
     PUBLIC
    -0.66
     Pearce
    -0.65
     Orn
    -0.65
     Lar
    -0.59
     Skydragon
    -0.58
     Idaho
    -0.58
    POSITIVE LOGITS
    self
    1.20
    unes
    1.00
    ueller
    0.94
    chwitz
    0.94
    zbollah
    0.92
    achi
    0.91
    zik
    0.90
    asca
    0.89
    chy
    0.89
    alian
    0.88
    Act Density 0.133%

    No Known Activations