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

    Neuronpedia

    INDEX
    Explanations

    references to reports, studies, and official documents

    oai_token-act-pair · gpt-3.5-turbo

    references to classified or leaked information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecause
    -0.73
     tho
    -0.62
    trak
    -0.60
    ousy
    -0.59
    wcs
    -0.58
     Gors
    -0.57
    ardless
    -0.57
    MSN
    -0.56
     TAMADRA
    -0.55
    anyahu
    -0.55
    POSITIVE LOGITS
    published
    0.62
    >.
    0.62
     unearthed
    0.62
     watchdog
    0.59
    `.
    0.58
    .�
    0.58
    ILA
    0.56
    $.
    0.56
    .''
    0.55
    ]."
    0.55
    Act Density 0.530%

    No Known Activations