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

    Neuronpedia

    INDEX
    Explanations

    quotes or messages written on signs in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ucket
    -0.31
    roo
    -0.22
    ño
    -0.20
    imate
    -0.20
    ihu
    -0.19
    udi
    -0.19
    alks
    -0.19
    utorial
    -0.19
    ierrez
    -0.18
    ibo
    -0.18
    POSITIVE LOGITS
    SAN
    0.19
     [+
    0.19
    units
    0.19
    stocks
    0.19
     unemploy
    0.18
    caps
    0.18
    MAT
    0.18
     SPI
    0.18
    CENT
    0.18
     caps
    0.18
    Act Density 0.446%

    No Known Activations