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

    Neuronpedia

    INDEX
    Explanations

    mentions of blood-related terms

    oai_token-act-pair · gpt-3.5-turbo

    words that contain specific vowel patterns or sounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIL
    -0.78
    è¦ļéĨĴ
    -0.72
    Lago
    -0.70
    Recomm
    -0.70
     brace
    -0.63
     VIDEOS
    -0.62
     Cosponsors
    -0.62
     rapt
    -0.61
     prayers
    -0.61
     Walton
    -0.61
    POSITIVE LOGITS
    hemy
    1.13
    etooth
    0.87
    pedia
    0.75
    lein
    0.74
    Cola
    0.74
    itzer
    0.70
    ois
    0.69
    aith
    0.69
    zinski
    0.69
    imore
    0.69
    Act Density 0.056%

    No Known Activations