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

    Neuronpedia

    INDEX
    Explanations

    references to technical specifications or data points

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivities
    -0.88
    ivity
    -0.83
    ãĤ¤ãĥĪ
    -0.81
    ional
    -0.72
    ICLE
    -0.70
    achu
    -0.69
    ique
    -0.68
    rophe
    -0.68
    icles
    -0.68
    lier
    -0.68
    POSITIVE LOGITS
     externalToEVAOnly
    1.06
    98
    0.87
    mph
    0.86
    80
    0.86
    987
    0.85
    989
    0.81
    57
    0.81
    78
    0.79
    58
    0.79
    68
    0.78
    Act Density 0.074%

    No Known Activations