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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "work" and related variations in contexts related to tasks and job-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paravant
    -1.01
    quelize
    -1.00
    Datuak
    -0.97
    zbęd
    -0.97
     CTP
    -0.91
     GIPHY
    -0.90
     unmute
    -0.88
     cref
    -0.87
     Nadel
    -0.84
     Selig
    -0.83
    POSITIVE LOGITS
     work
    1.79
    Work
    1.64
     Work
    1.63
    work
    1.61
     works
    1.61
     WORK
    1.58
    WORK
    1.50
     Works
    1.43
    works
    1.39
    Works
    1.37
    Act Density 0.106%

    No Known Activations