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

    Neuronpedia

    INDEX
    Explanations

    references to units of weight measurement, particularly 'kilogram' and 'kilowatt'

    oai_token-act-pair · gpt-3.5-turbo

    references to quantity or measurements related to kilowatts and kilojoules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fargo
    -0.74
     Advice
    -0.69
     Forbidden
    -0.68
    ãģį
    -0.68
     Flight
    -0.67
     Romance
    -0.67
     Rolls
    -0.64
    Discussion
    -0.64
     Annotations
    -0.64
     Cause
    -0.63
    POSITIVE LOGITS
    oby
    1.21
    oton
    1.07
    kil
    1.02
    mos
    1.00
    ometers
    0.97
    imet
    0.96
    ogram
    0.93
    tern
    0.92
    ometer
    0.92
    ths
    0.92
    Act Density 0.010%

    No Known Activations