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

    Neuronpedia

    INDEX
    Explanations

    technical terms, data structures, and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĤº
    -0.17
    angel
    -0.16
    utor
    -0.15
    Ñij
    -0.15
     Sap
    -0.15
    .rdf
    -0.14
    ousse
    -0.14
    ucas
    -0.14
     cancellation
    -0.14
    åĢį
    -0.14
    POSITIVE LOGITS
    -li
    0.15
     paraph
    0.14
     Perr
    0.14
    pekt
    0.14
    elfast
    0.14
     Thornton
    0.14
     alo
    0.13
    209
    0.13
    sta
    0.13
     eing
    0.13
    Act Density 0.126%

    No Known Activations