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

    Neuronpedia

    INDEX
    Explanations

    quantities measured in gallons

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities of liquid measured in gallons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skelet
    -0.85
    eering
    -0.85
    eer
    -0.70
    spons
    -0.66
     pse
    -0.66
    doms
    -0.66
     Malik
    -0.65
    hra
    -0.64
     Fram
    -0.63
     Oversight
    -0.63
    POSITIVE LOGITS
     gallons
    1.05
     gallon
    0.95
     litres
    0.94
     spilled
    0.82
     jug
    0.82
    cake
    0.81
     bottles
    0.80
    oline
    0.80
    assing
    0.79
     barrels
    0.79
    Act Density 0.017%

    No Known Activations