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

    Neuronpedia

    INDEX
    Explanations

    references to philosophical concepts and historical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лон
    -0.15
     Nazi
    -0.15
    rava
    -0.15
    asz
    -0.15
    lush
    -0.15
    inox
    -0.15
     ÄIJiá»ĩn
    -0.14
     Scalars
    -0.14
    .lt
    -0.14
    chluss
    -0.14
    POSITIVE LOGITS
     bourgeois
    0.15
    ICC
    0.15
    venir
    0.15
    184
    0.14
     Moses
    0.14
     historical
    0.14
     spor
    0.14
     Fate
    0.13
    beam
    0.13
    aseline
    0.13
    Act Density 0.004%

    No Known Activations