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

    Neuronpedia

    INDEX
    Explanations

    instances where a specific amount is mentioned in a context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.89
    ĸļ
    -0.84
    endants
    -0.74
    most
    -0.73
    Ń·
    -0.73
     Cosponsors
    -0.72
    stal
    -0.70
    Names
    -0.66
    ands
    -0.66
    reys
    -0.66
    POSITIVE LOGITS
     money
    1.05
     firepower
    0.98
     information
    0.93
     mileage
    0.91
     time
    0.89
     manpower
    0.89
     autonomy
    0.87
     resources
    0.87
     material
    0.83
     effort
    0.81
    Act Density 0.098%

    No Known Activations