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

    Neuronpedia

    INDEX
    Explanations

    phrases related to frequency and spacing of elements or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubo
    -0.17
    ertia
    -0.16
    .appspot
    -0.15
    егоÑĢ
    -0.15
    Axes
    -0.14
     inertia
    -0.14
    _least
    -0.14
    abox
    -0.14
    urga
    -0.14
    sher
    -0.14
    POSITIVE LOGITS
     interval
    0.44
     intervals
    0.44
     spacing
    0.41
     Interval
    0.39
     spaced
    0.39
    interval
    0.37
    Spacing
    0.34
    Interval
    0.34
    .interval
    0.33
    -spacing
    0.33
    Act Density 0.196%

    No Known Activations