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

    Neuronpedia

    INDEX
    Explanations

    references to historical architecture and fortifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aight
    -0.16
    RITE
    -0.14
    /GPL
    -0.14
    اÙħÛĮÙĨ
    -0.14
    iad
    -0.14
    .navigationBar
    -0.14
     Wrath
    -0.14
    dna
    -0.13
     Andres
    -0.13
     cabinet
    -0.13
    POSITIVE LOGITS
     fort
    0.34
     walls
    0.30
     defenses
    0.29
     Walls
    0.28
     defensive
    0.28
     fortified
    0.28
     forts
    0.28
     defended
    0.28
     castle
    0.27
     defense
    0.26
    Act Density 0.157%

    No Known Activations