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

    Neuronpedia

    INDEX
    Explanations

    references to New Year's celebrations and associated events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yard
    -0.16
    ernes
    -0.15
     beyond
    -0.14
    .te
    -0.14
    714
    -0.13
    ah
    -0.13
    yard
    -0.13
    жив
    -0.13
    itary
    -0.13
    ortal
    -0.13
    POSITIVE LOGITS
     Eve
    0.26
     eve
    0.23
     EVE
    0.20
     resolutions
    0.20
     Resolution
    0.18
    eve
    0.18
    /start
    0.17
     resolution
    0.17
    -resolution
    0.16
    theless
    0.16
    Act Density 0.006%

    No Known Activations