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

    Neuronpedia

    INDEX
    Explanations

    references to armor and defensive attributes in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ابع
    -0.16
    sko
    -0.15
     Olympus
    -0.15
    ppy
    -0.14
    æŁ±
    -0.14
    683
    -0.14
    浦
    -0.14
    alog
    -0.14
    171
    -0.13
    552
    -0.13
    POSITIVE LOGITS
     mail
    0.31
     cu
    0.30
     plate
    0.29
    plate
    0.29
     armor
    0.28
    mail
    0.27
     chain
    0.26
    Plate
    0.26
     helm
    0.26
     Mail
    0.26
    Act Density 0.031%

    No Known Activations