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

    Neuronpedia

    INDEX
    Explanations

    references to popular book or movie series and their characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erior
    -0.17
    鬼
    -0.15
    culo
    -0.15
    pong
    -0.15
    otel
    -0.15
    inkle
    -0.15
    ongan
    -0.14
     serg
    -0.14
    ardi
    -0.14
    keh
    -0.14
    POSITIVE LOGITS
     Kat
    0.35
     District
    0.33
    District
    0.33
     districts
    0.32
     Mock
    0.32
    Kat
    0.31
     district
    0.30
    district
    0.29
     Hunger
    0.28
     trib
    0.27
    Act Density 0.030%

    No Known Activations