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

    Neuronpedia

    INDEX
    Explanations

    words related to architectural and construction details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukong
    -0.81
    renheit
    -0.73
    ENN
    -0.72
    \\\\\\\\
    -0.71
    axies
    -0.70
    ivities
    -0.69
    itans
    -0.69
    ivated
    -0.68
    imil
    -0.67
    rongh
    -0.66
    POSITIVE LOGITS
     thereof
    0.86
    âĶĢ
    0.77
     borne
    0.77
    ttes
    0.76
    ishly
    0.74
     containing
    0.74
     wherein
    0.72
     ridden
    0.71
     gland
    0.67
     clad
    0.66
    Act Density 0.302%

    No Known Activations