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

    Neuronpedia

    INDEX
    Explanations

    newsletter subscriptions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Lam
    -0.90
     Ludwig
    -0.76
     Hussain
    -0.74
    ORN
    -0.72
    eur
    -0.71
     Wah
    -0.71
     Jinn
    -0.71
    bolt
    -0.70
    ugal
    -0.69
    reme
    -0.69
    POSITIVE LOGITS
    isode
    0.86
    farious
    0.83
    padding
    0.79
    Skip
    0.78
    EngineDebug
    0.77
     externalToEVAOnly
    0.75
    VERTISEMENT
    0.74
    ispers
    0.74
     actionGroup
    0.74
     inbox
    0.73
    Act Density 0.153%

    No Known Activations