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

    Neuronpedia

    INDEX
    Explanations

    words related to computer programming and syntax

    oai_token-act-pair · gpt-3.5-turbo

    references to parsing or the term "ars."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pearce
    -0.61
    states
    -0.60
     coli
    -0.60
     Biden
    -0.60
     Vert
    -0.59
     STATES
    -0.59
     oxid
    -0.58
     Volunteer
    -0.57
     Kiw
    -0.57
     propriet
    -0.55
    POSITIVE LOGITS
    hip
    1.22
    cale
    1.11
    hips
    1.03
    DragonMagazine
    1.03
    imony
    1.01
    ansas
    0.98
    mith
    0.97
    ystem
    0.94
    hod
    0.92
    chall
    0.91
    Act Density 0.042%

    No Known Activations