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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs and their representations in code and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccione
    -0.16
    idunt
    -0.15
    wdx
    -0.14
    abcdefghijkl
    -0.14
    opis
    -0.14
    opoulos
    -0.14
    lsi
    -0.14
    -ни
    -0.14
    ãĥ³ãĥIJ
    -0.14
    bsd
    -0.14
    POSITIVE LOGITS
     \
    0.17
    unk
    0.16
    857
    0.15
    ornings
    0.15
     %
    0.15
    -,
    0.15
     /
    0.15
    aje
    0.14
    iol
    0.14
    aggi
    0.14
    Act Density 0.023%

    No Known Activations