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

    Neuronpedia

    INDEX
    Explanations

    references to financial amounts or limits

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating maximum limits or allowances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mate
    -0.65
    士
    -0.62
     Abyss
    -0.62
     Mistress
    -0.59
     Sev
    -0.56
     Fant
    -0.55
     Wiz
    -0.55
    Ware
    -0.55
     Mole
    -0.54
     Theo
    -0.54
    POSITIVE LOGITS
    votes
    1.06
    regulation
    0.97
    raised
    0.97
    grading
    0.96
    grades
    0.96
    rights
    0.94
    bringing
    0.94
    sized
    0.92
    graded
    0.90
    bring
    0.88
    Act Density 0.046%

    No Known Activations