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

    Neuronpedia

    INDEX
    Explanations

    logging-related terms in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enburg
    -0.18
    weg
    -0.17
    ibur
    -0.15
    ppe
    -0.14
    ogi
    -0.14
    uais
    -0.14
    ebi
    -0.14
    owering
    -0.14
     cenu
    -0.14
    TERN
    -0.13
    POSITIVE LOGITS
    ONUS
    0.16
     unf
    0.15
     Cold
    0.15
    æĢ§çļĦ
    0.15
    inston
    0.14
    prs
    0.14
    :set
    0.14
    esome
    0.14
    INAL
    0.14
     cold
    0.14
    Act Density 0.001%

    No Known Activations