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

    Neuronpedia

    INDEX
    Explanations

    references to methods or results that are detailed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lix
    -0.17
    677
    -0.16
    aves
    -0.16
    ISTR
    -0.15
    ist
    -0.15
    521
    -0.15
     бок
    -0.15
    orm
    -0.14
    ued
    -0.14
    187
    -0.14
    POSITIVE LOGITS
    ãĥ
    0.17
    idge
    0.14
    oton
    0.14
    нг
    0.14
    Ľå»º
    0.14
    perl
    0.14
    NIL
    0.14
    grese
    0.14
    epam
    0.14
     Interrupt
    0.14
    Act Density 0.123%

    No Known Activations