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

    Neuronpedia

    INDEX
    Explanations

    specific time-related references and periods in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oup
    -0.16
    次
    -0.16
    divider
    -0.15
    egin
    -0.15
    ằ
    -0.15
    orte
    -0.14
    lashes
    -0.14
    iken
    -0.14
    .library
    -0.14
    nev
    -0.14
    POSITIVE LOGITS
     part
    0.29
     half
    0.19
     week
    0.18
     decade
    0.17
    æĹ
    0.17
     of
    0.17
    ráf
    0.16
     full
    0.16
    gence
    0.16
     quarter
    0.16
    Act Density 0.067%

    No Known Activations