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

    Neuronpedia

    INDEX
    Explanations

    percentage values mentioned in survey results

    oai_token-act-pair · gpt-3.5-turbo

    statistical percentages related to opinions and approval ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manifold
    -0.72
     condensed
    -0.65
     exile
    -0.62
     besie
    -0.61
     savior
    -0.60
     spor
    -0.59
     superhuman
    -0.59
     saga
    -0.58
     bount
    -0.58
     itiner
    -0.58
    POSITIVE LOGITS
    %
    1.43
     percent
    1.39
    %;
    1.34
    %,
    1.30
    %-
    1.28
    %)
    1.26
    %);
    1.22
    %),
    1.21
    %.
    1.21
    %).
    1.17
    Act Density 0.188%

    No Known Activations