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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    percentages and demographic statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.72
     Bod
    -0.68
    BO
    -0.65
    arf
    -0.65
    ebook
    -0.63
    zos
    -0.63
     Dos
    -0.62
    fire
    -0.62
     retri
    -0.62
    flash
    -0.62
    POSITIVE LOGITS
    %:
    1.51
    %)
    1.48
    %).
    1.44
    %
    1.43
    %,
    1.42
    %-
    1.40
    %;
    1.39
    %.
    1.35
    %),
    1.30
     percent
    1.24
    Act Density 0.108%

    No Known Activations