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

    Neuronpedia

    INDEX
    Explanations

    references to wisdom and wise individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsi
    -0.17
    icari
    -0.17
    ergus
    -0.16
    eters
    -0.15
    gaard
    -0.15
    Wnd
    -0.15
    manship
    -0.15
    plain
    -0.14
    uzzi
    -0.14
    ož
    -0.14
    POSITIVE LOGITS
    fully
    0.19
     Archer
    0.15
    oi
    0.15
     wisdom
    0.15
    rana
    0.15
    wis
    0.14
    ought
    0.14
     rede
    0.14
    ầu
    0.14
    Ģ
    0.13
    Act Density 0.034%

    No Known Activations