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

    Neuronpedia

    INDEX
    Explanations

    phrases related to licensing and compliance terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utherland
    -0.16
    idon
    -0.15
    erti
    -0.15
    oglob
    -0.15
    ukes
    -0.15
    267
    -0.15
    esen
    -0.14
     primitive
    -0.14
    488
    -0.14
    orners
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.18
     Cheat
    0.15
    adel
    0.15
     eskort
    0.14
    ÙĬز
    0.14
     Humph
    0.14
    инов
    0.14
     hóa
    0.13
    OLL
    0.13
     ÐĴи
    0.13
    Act Density 0.001%

    No Known Activations