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

    Neuronpedia

    INDEX
    Explanations

    references to government, economic policies, and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardon
    -0.17
    ORTH
    -0.16
     Stateless
    -0.15
    eya
    -0.15
    ÙĤØ·
    -0.14
    Ïģον
    -0.14
    orth
    -0.14
    okane
    -0.13
    idia
    -0.13
    inston
    -0.13
    POSITIVE LOGITS
     according
    0.45
    according
    0.37
     says
    0.32
     According
    0.32
     selon
    0.32
    According
    0.30
     según
    0.26
     Says
    0.26
    ccording
    0.25
    says
    0.24
    Act Density 0.105%

    No Known Activations