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

    Neuronpedia

    INDEX
    Explanations

    words related to setting limits and testing boundaries in a parenting context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brag
    -0.50
     erad
    -0.49
     implor
    -0.47
     Maw
    -0.46
    brig
    -0.46
     Kuh
    -0.46
     excu
    -0.46
     Davi
    -0.44
     pamph
    -0.44
     OGS
    -0.44
    POSITIVE LOGITS
     testing
    0.94
     Testing
    0.90
     TESTING
    0.89
    Testing
    0.86
     tested
    0.85
     tests
    0.82
    testing
    0.81
     TESTS
    0.81
     test
    0.80
     testers
    0.80
    Act Density 0.137%

    No Known Activations