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

    Neuronpedia

    INDEX
    Explanations

    words related to irrelevance and disruptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to levels or measurements of various concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jindal
    -0.76
    ternal
    -0.68
     foremost
    -0.67
     nomine
    -0.65
     illum
    -0.61
    è¦ļéĨĴ
    -0.61
    Cmd
    -0.61
     sar
    -0.60
    dot
    -0.59
     Trou
    -0.59
    POSITIVE LOGITS
    iced
    0.85
    ibles
    0.81
    ance
    0.80
    encers
    0.75
    actory
    0.73
    ests
    0.73
    ications
    0.72
    icultural
    0.72
    encing
    0.71
    acular
    0.71
    Act Density 0.100%

    No Known Activations