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

    Neuronpedia

    INDEX
    Explanations

    keywords related to famous towers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of towers, specifically associated with notable landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dyl
    -0.78
     oxy
    -0.72
     lubric
    -0.70
     latex
    -0.66
     Bernie
    -0.65
    BIP
    -0.64
    employment
    -0.64
     narc
    -0.63
     occ
    -0.63
     nep
    -0.62
    POSITIVE LOGITS
     Tower
    4.03
     tower
    2.49
     Towers
    2.30
    tower
    2.15
     towers
    1.95
     Shard
    1.41
     Plaza
    1.34
     Castle
    1.24
     Pyramid
    1.17
     skysc
    1.16
    Act Density 0.009%

    No Known Activations