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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to statistics, figures, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.55
    abwe
    -0.55
     mathemat
    -0.53
    bart
    -0.52
    anders
    -0.51
     Conclusion
    -0.51
    etheless
    -0.51
     resemb
    -0.50
     è£ıè
    -0.50
     Beyond
    -0.49
    POSITIVE LOGITS
     to
    0.98
    to
    0.70
     onwards
    0.62
     yesterday
    0.61
     [+
    0.60
     Mbps
    0.59
    efer
    0.58
    To
    0.57
     earlier
    0.57
    pm
    0.56
    Act Density 0.079%

    No Known Activations