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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of people and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     profit
    -0.70
     conventions
    -0.68
     similar
    -0.67
     downgrade
    -0.67
     comparable
    -0.66
     depreciation
    -0.66
     effectively
    -0.63
     NYT
    -0.63
     treasury
    -0.63
     divided
    -0.62
    POSITIVE LOGITS
    aldo
    1.04
    ilyn
    1.04
    uko
    1.03
    iane
    1.02
    ija
    1.01
    isha
    1.01
    ena
    1.00
    onda
    1.00
    imar
    0.99
    ona
    0.98
    Act Density 0.547%

    No Known Activations