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

    Neuronpedia

    INDEX
    Explanations

    references to tall buildings and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĿ¢ç©į
    -0.16
    erland
    -0.16
    ften
    -0.15
    aroo
    -0.15
     patch
    -0.15
    vely
    -0.15
    osen
    -0.14
    aliz
    -0.14
    tgl
    -0.14
    ardin
    -0.14
    POSITIVE LOGITS
     tower
    0.18
    tower
    0.17
     towers
    0.16
     tallest
    0.15
     heights
    0.15
    -height
    0.15
    åĩĮ
    0.14
    etail
    0.14
    hotel
    0.14
    Tower
    0.14
    Act Density 0.050%

    No Known Activations