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

    Neuronpedia

    INDEX
    Explanations

    references to locations and organizations in Detroit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avad
    -0.17
    olute
    -0.16
    .CreateInstance
    -0.15
     Vader
    -0.15
    859
    -0.15
    iaux
    -0.15
    avour
    -0.15
    chy
    -0.14
     Waterloo
    -0.14
    OLT
    -0.14
    POSITIVE LOGITS
     DET
    0.27
     Detroit
    0.27
    Detroit
    0.25
     det
    0.24
    DET
    0.23
    (det
    0.22
    _det
    0.22
    det
    0.21
     Det
    0.21
    etroit
    0.21
    Act Density 0.055%

    No Known Activations