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

    Neuronpedia

    INDEX
    Explanations

    tabular data structures or key-value pair annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lfw
    -0.17
    oras
    -0.15
     ragaz
    -0.15
    inize
    -0.15
    ongyang
    -0.15
     ilan
    -0.15
    MLS
    -0.14
    unas
    -0.14
     бак
    -0.14
    ldr
    -0.14
    POSITIVE LOGITS
    rid
    0.15
    num
    0.15
    볨
    0.14
    tant
    0.14
    ctest
    0.13
    icular
    0.13
     Pregn
    0.13
     dec
    0.13
    alogy
    0.13
     Champagne
    0.13
    Act Density 0.027%

    No Known Activations