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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" indicating contrast or shifting of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enced
    -0.61
     encyclopedia
    -0.56
     Excellence
    -0.54
     pursu
    -0.52
    æĿ
    -0.52
    naire
    -0.52
     Orient
    -0.51
    ãģ£
    -0.50
     Cycle
    -0.50
     Corps
    -0.50
    POSITIVE LOGITS
    chers
    1.12
    chery
    1.09
    tons
    1.00
    ts
    0.86
    ickets
    0.84
     alas
    0.80
    lers
    0.77
    ters
    0.77
    ler
    0.77
     nevertheless
    0.75
    Act Density 0.152%

    No Known Activations