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

    Neuronpedia

    INDEX
    Explanations

    terms related to categories, classifications, and measures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     selection
    -0.15
    odic
    -0.14
    Selection
    -0.14
    yun
    -0.14
    selection
    -0.14
     Bender
    -0.14
    ayan
    -0.13
     Eg
    -0.13
    ummer
    -0.13
     Selection
    -0.13
    POSITIVE LOGITS
     è©
    0.18
    _AI
    0.16
    hall
    0.15
    pts
    0.15
    airs
    0.14
    eh
    0.14
    _blend
    0.14
    elm
    0.14
     Trie
    0.14
    Hall
    0.14
    Act Density 0.249%

    No Known Activations