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

    Neuronpedia

    INDEX
    Explanations

    the word "of" occurring frequently in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.00
    ħĭ
    -0.84
    find
    -0.72
     Cosponsors
    -0.71
    Ń·
    -0.69
    aroo
    -0.69
    \\\\\\\\
    -0.69
    reys
    -0.68
    ials
    -0.67
    ales
    -0.66
    POSITIVE LOGITS
     money
    1.05
     firepower
    0.93
     effort
    0.88
     information
    0.88
     mileage
    0.87
     time
    0.87
     energy
    0.87
     autonomy
    0.83
     attention
    0.83
     ammunition
    0.81
    Act Density 0.065%

    No Known Activations