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

    Neuronpedia

    INDEX
    Explanations

    keywords related to leaked information and revelations

    oai_token-act-pair · gpt-3.5-turbo

    instances of disclosure or revelation of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ç¥ŀ
    -0.87
    aver
    -0.80
    acea
    -0.78
    ona
    -0.77
    brance
    -0.69
    thood
    -0.68
    lear
    -0.67
    oka
    -0.66
    ometer
    -0.65
    izu
    -0.65
    POSITIVE LOGITS
     firsthand
    1.11
     harrowing
    1.09
     widespread
    1.01
     rampant
    1.00
     abuses
    0.99
     irregularities
    0.95
     allegations
    0.94
     revelations
    0.93
     discrepancies
    0.93
     shocking
    0.90
    Act Density 0.341%

    No Known Activations