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

    Neuronpedia

    INDEX
    Explanations

    geographical names and references to locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hind
    -0.15
    zier
    -0.14
     Dong
    -0.14
    agini
    -0.13
    æ²
    -0.13
     пад
    -0.13
    elper
    -0.13
     Demir
    -0.13
    uela
    -0.13
    iets
    -0.13
    POSITIVE LOGITS
     Ann
    0.21
    ANN
    0.20
     ANN
    0.18
     Rack
    0.17
     ann
    0.16
     Wolver
    0.16
    Ann
    0.16
    ults
    0.16
    apiro
    0.16
     Wolverine
    0.15
    Act Density 0.013%

    No Known Activations