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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "work" used in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     radikal
    -0.54
     zyn
    -0.53
     sonder
    -0.52
     minimalis
    -0.52
     krab
    -0.51
     akade
    -0.49
     ideolog
    -0.47
     Reiz
    -0.47
     rü
    -0.46
     kosme
    -0.46
    POSITIVE LOGITS
     Work
    1.05
    Work
    1.04
     work
    1.02
    work
    1.01
     WORK
    1.01
    WORK
    0.93
     Worked
    0.86
     pixar
    0.85
     workday
    0.84
     hairc
    0.81
    Act Density 0.123%

    No Known Activations