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

    Neuronpedia

    INDEX
    Explanations

    text related to software development, documentation, and programming

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to software documentation and community contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahu
    -0.68
    drug
    -0.67
     Coulter
    -0.62
    olitics
    -0.60
    mother
    -0.59
    resa
    -0.58
     Ronald
    -0.58
    Donald
    -0.57
     1974
    -0.57
    president
    -0.57
    POSITIVE LOGITS
     workflow
    0.94
     sandbox
    0.91
     tutorials
    0.91
     iter
    0.90
     optimizing
    0.88
     backend
    0.86
     debugging
    0.85
     devs
    0.84
     automate
    0.84
     demos
    0.83
    Act Density 1.312%

    No Known Activations