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

    Neuronpedia

    INDEX
    Explanations

    phrases related to training and preparation for tasks, particularly in a military or tactical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lw
    -0.15
     suff
    -0.15
     barren
    -0.15
    ziej
    -0.14
    pite
    -0.14
    uff
    -0.14
    iken
    -0.14
    deniz
    -0.14
    /cs
    -0.14
    pulse
    -0.14
    POSITIVE LOGITS
     physical
    0.26
     Physical
    0.26
    physical
    0.25
    Physical
    0.23
     exercise
    0.19
     phys
    0.19
    exercise
    0.18
     exercises
    0.17
     physically
    0.17
     ÑĦиз
    0.17
    Act Density 0.057%

    No Known Activations