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

    Neuronpedia

    INDEX
    Explanations

    temporal references, particularly dates and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Dial
    -0.16
    atism
    -0.15
    itel
    -0.14
    ogui
    -0.14
    atre
    -0.14
     Rica
    -0.14
     hab
    -0.14
    åĮº
    -0.14
    Ð¡Ð¡Ðł
    -0.13
    les
    -0.13
    POSITIVE LOGITS
    utherland
    0.15
     Throne
    0.15
     tow
    0.15
    ohl
    0.15
    atcher
    0.15
    inds
    0.15
    ë
    0.14
    ãĥ³ãĥĩ
    0.14
    ksi
    0.14
    eax
    0.14
    Act Density 0.018%

    No Known Activations