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

    Neuronpedia

    INDEX
    Explanations

    references to motion or movement, such as cameras, sensors, or physical actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.48
    شهاد
    -0.45
     iniqu
    -0.44
    Cambridge
    -0.42
     Cambridge
    -0.41
    柿
    -0.41
    猾
    -0.40
    Jub
    -0.40
     незавершена
    -0.40
    Lus
    -0.40
    POSITIVE LOGITS
     motion
    1.26
    motion
    1.15
     Motion
    1.14
     MOTION
    1.10
     motions
    1.10
    Motion
    1.06
     Motions
    0.92
    MOTION
    0.86
    motions
    0.85
     uncin
    0.70
    Act Density 0.082%

    No Known Activations