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

    Neuronpedia

    INDEX
    Explanations

    references to buildings or architectural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sights
    -0.16
    æĭ©
    -0.14
    اÙĦÛĮ
    -0.14
    eck
    -0.14
     franca
    -0.14
    istrovstvÃŃ
    -0.14
    vais
    -0.13
    à¹Ī
    -0.13
     конеÑĩно
    -0.13
    ICON
    -0.13
    POSITIVE LOGITS
     Univers
    0.18
     univers
    0.15
    arm
    0.15
    /wiki
    0.15
    Univers
    0.15
    agrams
    0.15
     anc
    0.15
    ence
    0.15
    anc
    0.14
    /backend
    0.14
    Act Density 0.020%

    No Known Activations