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

    Neuronpedia

    INDEX
    Explanations

    references to construction projects and related details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doorway
    -0.17
    ruba
    -0.16
    _NR
    -0.16
    еÑĪ
    -0.16
    ingham
    -0.15
    inou
    -0.15
    rana
    -0.15
    ë¹
    -0.15
     booth
    -0.14
    broken
    -0.14
    POSITIVE LOGITS
     wings
    0.20
     building
    0.19
     buildings
    0.18
     structure
    0.18
    structure
    0.17
     complex
    0.16
     pods
    0.16
    γη
    0.15
    æ£
    0.15
     wing
    0.15
    Act Density 0.179%

    No Known Activations