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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe common situations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thren
    -0.16
    anton
    -0.15
    lio
    -0.15
    ingleton
    -0.14
    ntity
    -0.14
    bjerg
    -0.14
     Advantage
    -0.14
    essler
    -0.14
     Matters
    -0.14
     advantage
    -0.14
    POSITIVE LOGITS
     xuyên
    0.27
     occurrence
    0.26
    -place
    0.23
     among
    0.21
     amongst
    0.20
     encountered
    0.20
     occurring
    0.20
    /pop
    0.19
    -found
    0.19
     occ
    0.19
    Act Density 0.072%

    No Known Activations