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

    Neuronpedia

    INDEX
    Explanations

    themes related to division and grouping of people or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldt
    -0.15
    onica
    -0.15
    ULK
    -0.15
    uentes
    -0.14
    amble
    -0.13
     bail
    -0.13
    oux
    -0.13
    rana
    -0.13
    .pix
    -0.13
    iminal
    -0.13
    POSITIVE LOGITS
     distribution
    0.26
     assignment
    0.26
     assignments
    0.25
     Distribution
    0.23
     assigning
    0.23
    distribution
    0.23
    assignment
    0.22
    assignments
    0.22
     partition
    0.22
     assign
    0.22
    Act Density 0.358%

    No Known Activations