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

    Neuronpedia

    INDEX
    Explanations

    specific code-related terms and references to documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aria
    -0.16
    bed
    -0.16
    IEL
    -0.15
    itty
    -0.14
    acy
    -0.14
    ¶Ī
    -0.14
    ood
    -0.14
    åī
    -0.14
    slides
    -0.14
    cast
    -0.14
    POSITIVE LOGITS
    linger
    0.16
    ovna
    0.15
     preserve
    0.15
    endas
    0.14
    ellig
    0.14
    eon
    0.14
    argas
    0.14
    Ø·Ùģ
    0.14
    enco
    0.14
    illac
    0.14
    Act Density 0.004%

    No Known Activations