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

    Neuronpedia

    INDEX
    Explanations

    references to programming variables and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Evet
    -0.07
    iri
    -0.06
    lh
    -0.06
    yb
    -0.06
    責
    -0.05
     respect
    -0.05
     either
    -0.05
    adder
    -0.05
    ceb
    -0.05
    eler
    -0.05
    POSITIVE LOGITS
     range
    0.11
    range
    0.10
     RANGE
    0.10
    -range
    0.10
     Range
    0.10
     ranges
    0.09
    (range
    0.09
    Range
    0.09
    .range
    0.09
     xrange
    0.09
    Act Density 0.008%

    No Known Activations