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

    Neuronpedia

    INDEX
    Explanations

    references to alternative options and comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.15
    گاÙĨÛĮ
    -0.15
    baum
    -0.14
    両
    -0.14
    essen
    -0.14
     unspecified
    -0.14
     ============================================================================↵
    -0.13
    Ïģιά
    -0.13
    plen
    -0.13
     Hansen
    -0.13
    POSITIVE LOGITS
    ouro
    0.16
    uster
    0.15
    аÑĢÑĸ
    0.14
    USTER
    0.14
    taire
    0.14
    inch
    0.14
    ollo
    0.14
    rescia
    0.14
    irket
    0.14
    errat
    0.13
    Act Density 0.270%

    No Known Activations