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

    Neuronpedia

    INDEX
    Explanations

    references to distances and measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yates
    -0.17
     Dawson
    -0.17
     higher
    -0.15
     highest
    -0.14
    porte
    -0.13
     Higher
    -0.13
    793
    -0.13
    974
    -0.13
     Chocolate
    -0.13
    ternal
    -0.13
    POSITIVE LOGITS
     distance
    1.11
     Distance
    1.00
    distance
    0.96
     distances
    0.96
    Distance
    0.91
    -distance
    0.80
    .distance
    0.75
    è·Ŀ离
    0.75
    _distance
    0.75
     distancia
    0.75
    Act Density 0.219%

    No Known Activations