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

    Neuronpedia

    INDEX
    Explanations

    references to hyperlinks or web links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»Ļng
    -0.16
    elon
    -0.15
    281
    -0.15
    dd
    -0.15
    alon
    -0.15
    RAINT
    -0.14
     derivatives
    -0.14
     derivative
    -0.14
    elo
    -0.14
    267
    -0.14
    POSITIVE LOGITS
     links
    0.24
    /link
    0.24
    links
    0.24
     link
    0.23
    (links
    0.22
    link
    0.20
    edin
    0.19
    -link
    0.19
    .link
    0.19
     linking
    0.18
    Act Density 0.032%

    No Known Activations