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

    Neuronpedia

    INDEX
    Explanations

    phrases related to professional roles and career progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anki
    -0.17
    alama
    -0.16
    олом
    -0.15
    kor
    -0.15
    .Axis
    -0.14
    rana
    -0.14
    kv
    -0.14
    /Foundation
    -0.14
    Ä°Åŀ
    -0.14
    frei
    -0.14
    POSITIVE LOGITS
    ets
    0.15
     broader
    0.15
    å·§
    0.15
    II
    0.14
    irectory
    0.14
    æ©ĭ
    0.14
    ież
    0.14
    apolis
    0.13
    opis
    0.13
     Knight
    0.13
    Act Density 0.018%

    No Known Activations