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

    Neuronpedia

    INDEX
    Explanations

    words indicating strong opinions or obvious conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrat
    -0.17
    WA
    -0.15
     recent
    -0.15
     yesterday
    -0.15
     ðŁ
    -0.14
    canonical
    -0.14
     livest
    -0.14
     wherever
    -0.14
    recent
    -0.14
     Bren
    -0.13
    POSITIVE LOGITS
     cave
    0.17
     prisoner
    0.17
    represent
    0.16
    代表
    0.15
    ceb
    0.15
     Prison
    0.15
     Cave
    0.15
     perce
    0.15
     represent
    0.15
     perceived
    0.15
    Act Density 0.000%

    No Known Activations