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

    Neuronpedia

    INDEX
    Explanations

    mentions of job titles and roles within various organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reft
    -0.77
     tranf
    -0.75
     ACKNOWLEDGMENTS
    -0.70
     nutella
    -0.67
     :—
    -0.65
    hastly
    -0.64
     lefs
    -0.63
     unce
    -0.62
     thut
    -0.61
     foon
    -0.61
    POSITIVE LOGITS
     clients
    0.79
     Áng
    0.76
     Barcelone
    0.65
     Berlín
    0.65
     Jardín
    0.63
     Vaticano
    0.60
    clients
    0.60
     Bahía
    0.60
     Jérusalem
    0.59
     ModelExpression
    0.59
    Act Density 0.412%

    No Known Activations