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

    Neuronpedia

    INDEX
    Explanations

    acronyms related to technology and data communication protocols

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hold
    -0.97
    taboola
    -0.85
    âĸ¬
    -0.85
    Interstitial
    -0.80
    âĸ¬âĸ¬
    -0.78
    nces
    -0.76
    gra
    -0.73
     Liberties
    -0.71
     Sheen
    -0.70
     Antarctic
    -0.70
    POSITIVE LOGITS
    TP
    1.09
    ython
    1.08
    ACK
    1.02
    WD
    1.00
    ocalypse
    1.00
    etition
    0.98
    rint
    0.98
    ractor
    0.95
    olitics
    0.93
    ainted
    0.92
    Act Density 0.007%

    No Known Activations