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

    Neuronpedia

    INDEX
    Explanations

    terms related to labor unions and work-related negotiations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     makro
    -0.60
    Mä
    -0.54
     gero
    -0.51
     stoff
    -0.51
     bera
    -0.50
     maske
    -0.49
    Kön
    -0.49
     fars
    -0.48
     lü
    -0.48
     alkoh
    -0.47
    POSITIVE LOGITS
     union
    1.28
     Union
    1.26
    Union
    1.21
     unions
    1.14
    union
    1.13
     UNION
    1.09
     Unions
    1.08
    UNION
    1.06
     Unión
    0.82
     unión
    0.63
    Act Density 0.075%

    No Known Activations