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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' job titles and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gew
    -0.78
    ikkert
    -0.75
     Jank
    -0.70
    SafeAreaView
    -0.69
     Lep
    -0.66
    ꜱ
    -0.65
    ANNELS
    -0.64
     банк
    -0.63
     Kenn
    -0.63
     Hab
    -0.63
    POSITIVE LOGITS
     directors
    1.60
     director
    1.45
     Directors
    1.43
    director
    1.40
     DIRECTOR
    1.39
    Directors
    1.33
     Director
    1.31
    DIRECTOR
    1.26
    directors
    1.26
    Director
    1.23
    Act Density 0.063%

    No Known Activations