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

    Neuronpedia

    INDEX
    Explanations

    numerical values and fractions

    oai_token-act-pair · gpt-3.5-turbo

    percentages and numerical data related to demographics or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.83
    Claim
    -0.81
    Apps
    -0.79
     Projects
    -0.76
     Sites
    -0.76
    Products
    -0.76
     ALWAYS
    -0.75
    Sym
    -0.75
    ï¸
    -0.72
    Cause
    -0.72
    POSITIVE LOGITS
     white
    0.91
     suburban
    0.90
     African
    0.89
     black
    0.85
     wom
    0.84
     blue
    0.83
     female
    0.83
     juvenile
    0.83
     Hispanic
    0.82
     gay
    0.82
    Act Density 0.463%

    No Known Activations