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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate adequacy, meaning, effectiveness, and credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inerja
    -0.48
    кота
    -0.47
    ikin
    -0.46
    AddField
    -0.46
     sorg
    -0.44
    aky
    -0.44
     따
    -0.44
     Sum
    -0.43
     stark
    -0.43
    arean
    -0.43
    POSITIVE LOGITS
     decent
    0.99
     Decent
    0.95
    ItemBackground
    0.92
     adequate
    0.89
    Decent
    0.85
     reliable
    0.84
     decently
    0.80
     credible
    0.80
     adequately
    0.79
     meaningful
    0.78
    Act Density 0.951%

    No Known Activations