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

    Neuronpedia

    INDEX
    Explanations

    references to skyscrapers and skylines

    oai_token-act-pair · gpt-3.5-turbo

    terms related to skyscrapers and high-rise buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.84
    iotic
    -0.81
     Recomm
    -0.80
    onom
    -0.76
    ña
    -0.72
    ELY
    -0.71
    ño
    -0.68
    laus
    -0.68
    gas
    -0.67
    nia
    -0.67
    POSITIVE LOGITS
     skysc
    1.39
     skyline
    1.28
    raper
    1.27
     towers
    1.08
     tallest
    0.95
    itect
    0.88
     tower
    0.82
     Towers
    0.82
    scape
    0.81
     heights
    0.80
    Act Density 0.020%

    No Known Activations