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

    Neuronpedia

    INDEX
    Explanations

    capitalized acronyms related to organizations or titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.66
     Allaah
    -0.64
    rooms
    -0.64
     surpr
    -0.63
     speedy
    -0.62
    ogene
    -0.62
     clutter
    -0.60
     raise
    -0.59
    thinkable
    -0.59
    Spoiler
    -0.58
    POSITIVE LOGITS
    FU
    1.08
    KA
    1.07
    KI
    1.03
    KT
    1.00
    HY
    0.99
    ZA
    0.95
    KO
    0.95
    HE
    0.94
    OT
    0.93
    JA
    0.93
    Act Density 0.121%

    No Known Activations