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

    Neuronpedia

    INDEX
    Explanations

    currencies or monetary values

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gors
    -0.89
     Nare
    -0.84
     Tall
    -0.76
     Bend
    -0.75
     Dare
    -0.72
     Wra
    -0.72
     Entered
    -0.68
     Ital
    -0.67
     Desk
    -0.66
     Freed
    -0.66
    POSITIVE LOGITS
    ultz
    0.88
    100
    0.85
    false
    0.84
    $$
    0.82
    200
    0.81
    130
    0.79
    HOME
    0.79
    iris
    0.78
    300
    0.78
    future
    0.78
    Act Density 0.044%

    No Known Activations