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

    Neuronpedia

    INDEX
    Explanations

    references to specific monetary amounts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to pricing and costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rarily
    -0.67
    ilipp
    -0.65
    jer
    -0.63
    limits
    -0.63
    FORE
    -0.62
    ECA
    -0.61
    hess
    -0.60
    behind
    -0.59
    iron
    -0.58
    acid
    -0.56
    POSITIVE LOGITS
     hour
    0.98
     month
    0.97
     pound
    0.91
     gallon
    0.87
     ounce
    0.86
     kil
    0.84
     kWh
    0.82
     capita
    0.81
     acre
    0.79
     semester
    0.79
    Act Density 0.050%

    No Known Activations