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

    Neuronpedia

    INDEX
    Explanations

    keywords associated with toxicity and environmental contamination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.72
    runApp
    -0.68
     Trit
    -0.68
     Pozn
    -0.67
     Савезне
    -0.67
     surla
    -0.67
     Guarantee
    -0.67
     Majefty
    -0.67
    BeginContext
    -0.66
     guarante
    -0.65
    POSITIVE LOGITS
     Thi
    0.63
     stuck
    0.56
     Lang
    0.56
     thi
    0.56
     tid
    0.55
     sud
    0.55
     Toxic
    0.54
     lệ
    0.54
    Thi
    0.54
     thief
    0.54
    Act Density 2.966%

    No Known Activations