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

    Neuronpedia

    INDEX
    Explanations

    references to percentages and statistics in text

    oai_token-act-pair · gpt-3.5-turbo

    percentage statistics related to various topics or demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     short
    -0.77
    rael
    -0.70
     mathemat
    -0.68
     compan
    -0.68
     princ
    -0.66
     nurs
    -0.66
     restruct
    -0.60
     lett
    -0.60
    changes
    -0.60
     hall
    -0.60
    POSITIVE LOGITS
    %)
    1.05
    %).
    0.94
    %),
    0.93
    %);
    0.84
    \<
    0.84
    ONSORED
    0.82
    +)
    0.81
    %;
    0.80
    %,
    0.80
    ecided
    0.80
    Act Density 0.008%

    No Known Activations