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

    Neuronpedia

    INDEX
    Explanations

    references to legal terminology and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neighbor
    -0.20
     afterward
    -0.20
    favor
    -0.19
     neighborhoods
    -0.18
     neighborhood
    -0.18
    Neighbor
    -0.18
     neighboring
    -0.17
    chter
    -0.17
     traveler
    -0.17
     favorable
    -0.17
    POSITIVE LOGITS
     Malays
    0.20
     Malaysian
    0.20
     Bench
    0.18
     Kuala
    0.16
     Malaysia
    0.16
     Malay
    0.16
     Dat
    0.16
     UM
    0.15
     MIC
    0.15
     Seks
    0.15
    Act Density 0.001%

    No Known Activations