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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tall structures like towers

    oai_token-act-pair · gpt-3.5-turbo

    references to towering structures, specifically buildings and skyscrapers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LAB
    -0.80
     clipboard
    -0.67
    urg
    -0.65
    order
    -0.65
    TN
    -0.64
     amend
    -0.64
    REG
    -0.64
     procedure
    -0.63
    rieving
    -0.63
     fermentation
    -0.63
    POSITIVE LOGITS
     Towers
    3.20
     towers
    2.32
     Bridges
    1.29
     WTC
    1.21
     Tale
    1.17
     Kore
    1.15
    911
    1.08
    uras
    1.07
    osaurs
    1.05
     Architects
    0.98
    Act Density 0.047%

    No Known Activations