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

    Neuronpedia

    INDEX
    Explanations

    large numbers (likely represented in a monetary context)

    oai_token-act-pair · gpt-3.5-turbo

    various numerical data points or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fault
    -0.67
     biography
    -0.62
    ucci
    -0.61
     organized
    -0.61
     joke
    -0.60
     Sheet
    -0.60
     blame
    -0.60
    ña
    -0.59
     jokes
    -0.58
     vested
    -0.58
    POSITIVE LOGITS
    10
    3.14
    12
    2.22
    11
    2.21
    20
    2.06
    15
    2.05
    13
    1.96
    30
    1.93
    14
    1.92
    40
    1.88
    25
    1.87
    Act Density 0.024%

    No Known Activations