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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate structure or hierarchy within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bethlehem
    -0.16
    .bias
    -0.16
    bolt
    -0.16
     bail
    -0.15
    bib
    -0.15
    arov
    -0.14
    .blob
    -0.14
    à¥įतव
    -0.14
    bil
    -0.14
    bias
    -0.14
    POSITIVE LOGITS
     Br
    1.30
     br
    1.24
    Br
    1.20
    br
    1.16
    -br
    1.06
    _br
    1.02
     BR
    1.00
    .Br
    0.98
    BR
    0.95
    (br
    0.95
    Act Density 0.613%

    No Known Activations