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

    Neuronpedia

    INDEX
    Explanations

    differences in wages and benefits between union and non-union workers in different states

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     far
    -0.56
     im
    -0.53
     fast
    -0.52
     Ed
    -0.52
    名称
    -0.51
    saida
    -0.51
     da
    -0.51
     er
    -0.50
     Dan
    -0.50
     Da
    -0.50
    POSITIVE LOGITS
     increa
    1.66
     effe
    1.61
     emphat
    1.61
     mef
    1.59
     desir
    1.57
     guarante
    1.56
     maneu
    1.52
     suspic
    1.52
     stockholm
    1.51
     pessi
    1.50
    Act Density 0.282%

    No Known Activations