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

    Neuronpedia

    INDEX
    Explanations

    references to Paris and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orca
    -0.16
    IPS
    -0.16
    tir
    -0.15
    tor
    -0.15
    dong
    -0.15
    "display
    -0.15
    адки
    -0.15
    eview
    -0.15
    tors
    -0.15
     Markup
    -0.15
    POSITIVE LOGITS
    ian
    0.34
    ians
    0.24
    ienne
    0.23
     Hilton
    0.21
    IAN
    0.20
    ien
    0.19
    ous
    0.18
    iens
    0.17
    anship
    0.17
    nger
    0.16
    Act Density 0.009%

    No Known Activations