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

    Neuronpedia

    INDEX
    Explanations

    large numerical figures indicating quantity

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly large quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiz
    -0.74
     manag
    -0.59
    itory
    -0.58
    oward
    -0.57
    liction
    -0.54
    aryl
    -0.53
     pairing
    -0.52
    bara
    -0.52
    rigan
    -0.51
    ainer
    -0.51
    POSITIVE LOGITS
     SHARES
    0.92
     Shares
    0.79
     acres
    0.78
     tonnes
    0.78
     hectares
    0.76
     volts
    0.76
    mAh
    0.75
     litres
    0.75
     miles
    0.73
     calories
    0.72
    Act Density 0.153%

    No Known Activations