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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "working"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.47
     wikipagina
    -0.46
     mijne
    -0.45
     mierda
    -0.43
     vaksinasi
    -0.42
    Rohy
    -0.42
     freilich
    -0.41
     Geschw
    -0.41
     przód
    -0.40
     anuales
    -0.40
    POSITIVE LOGITS
     working
    4.19
     Working
    3.77
    Working
    3.72
    working
    3.69
     WORKING
    3.50
    WORKING
    3.22
     trabajando
    2.14
     trabalhando
    1.96
     trabajar
    1.75
     workings
    1.73
    Act Density 0.100%

    No Known Activations