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

    Neuronpedia

    INDEX
    Explanations

    references to weight and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urette
    -0.20
    edith
    -0.19
    ubbo
    -0.17
    ninger
    -0.17
    imen
    -0.16
     Cummings
    -0.15
    itag
    -0.15
    enberg
    -0.15
    -circle
    -0.14
    enery
    -0.14
    POSITIVE LOGITS
     upon
    0.19
     Upon
    0.15
    tec
    0.14
     Lug
    0.14
    upon
    0.14
    ãģĺãĤĥãģªãģĦ
    0.14
    acting
    0.14
    _iterator
    0.14
    ÄĽ
    0.14
     ÐĴолод
    0.13
    Act Density 0.133%

    No Known Activations