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

    Neuronpedia

    INDEX
    Explanations

    mentions of acknowledgments or credits

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Courtesy" or similar acknowledgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akia
    -0.77
    powers
    -0.76
    merce
    -0.74
    thin
    -0.74
    oshenko
    -0.71
    ild
    -0.66
    ago
    -0.66
    prime
    -0.66
    acea
    -0.66
    ties
    -0.64
    POSITIVE LOGITS
     Courtesy
    1.31
    tesy
    1.18
    Courtesy
    1.11
     courtesy
    0.91
     Provided
    0.82
     VIDEOS
    0.81
     Via
    0.81
    Credit
    0.80
     Credit
    0.79
    heses
    0.77
    Act Density 0.005%

    No Known Activations