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

    Neuronpedia

    INDEX
    Explanations

    non-English characters and special symbols

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.85
     ethic
    -0.80
    swick
    -0.75
     testim
    -0.74
    etheless
    -0.72
    enhagen
    -0.70
     swaps
    -0.69
    iqueness
    -0.67
     differential
    -0.65
    urses
    -0.64
    POSITIVE LOGITS
    ÃįÃį
    1.11
    ãĤĭ
    0.94
    aurus
    0.92
    ource
    0.92
    ÑĮ
    0.91
    е
    0.88
    Ĩ
    0.88
    à¸
    0.87
    TER
    0.87
    к
    0.86
    Act Density 0.014%

    No Known Activations