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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate observation or sight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anga
    -0.16
    edy
    -0.15
    usra
    -0.15
     Cec
    -0.15
    缤
    -0.15
    amon
    -0.14
    è·Ŀ
    -0.14
    nbsp
    -0.14
    ocks
    -0.14
     Naj
    -0.14
    POSITIVE LOGITS
    alytics
    0.17
     Zah
    0.16
    hn
    0.15
    imits
    0.15
    owie
    0.15
    ulton
    0.15
     Preference
    0.15
    KHR
    0.15
    ÏĢή
    0.14
     Anton
    0.14
    Act Density 0.000%

    No Known Activations