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

    Neuronpedia

    INDEX
    Explanations

    references to the conclusion of events, particularly phrases that denote the end of a period or timeframe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     early
    -0.19
     Dawn
    -0.18
    igen
    -0.17
     poc
    -0.17
     begin
    -0.16
     throughout
    -0.15
    696
    -0.15
    china
    -0.15
    ie
    -0.15
     beginnings
    -0.15
    POSITIVE LOGITS
     cuent
    0.18
     Ramadan
    0.16
    oyer
    0.16
    /end
    0.16
    elman
    0.16
    veis
    0.15
    ÙĬات
    0.15
    ereço
    0.15
    terior
    0.15
    ÙħØ©
    0.14
    Act Density 0.049%

    No Known Activations