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

    Neuronpedia

    INDEX
    Explanations

    terms related to rookie or beginner status in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecap
    -0.57
    stdafx
    -0.56
    stris
    -0.56
    printLine
    -0.54
    Diwedd
    -0.53
    MENAFN
    -0.53
    ipedi
    -0.53
    nsis
    -0.53
    ModelState
    -0.52
    RequestMapping
    -0.51
    POSITIVE LOGITS
     poffe
    0.97
     whoſe
    0.91
     himſelf
    0.88
     Jefus
    0.88
     whofe
    0.87
     themſelves
    0.86
     Efq
    0.86
     myſelf
    0.85
     ftate
    0.84
     Chriftian
    0.81
    Act Density 0.273%

    No Known Activations