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

    Neuronpedia

    INDEX
    Explanations

    terms related to mystery and investigative themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     integrados
    -0.39
     deportivos
    -0.38
     desierto
    -0.38
     Fry
    -0.36
     koos
    -0.36
     crédit
    -0.36
    Override
    -0.35
     grades
    -0.33
     склада
    -0.33
     dedi
    -0.33
    POSITIVE LOGITS
     mystery
    0.85
    endregion
    0.81
    parsedMessage
    0.81
    GEBURTSDATUM
    0.80
     dat
    0.79
    mystery
    0.78
    Mystery
    0.75
    RegressionTest
    0.74
     Mystery
    0.70
    uxxxx
    0.69
    Act Density 0.434%

    No Known Activations