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

    Neuronpedia

    INDEX
    Explanations

    References to structures or objects related to towers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of towers, particularly in a gaming or architectural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ±
    -0.78
    é»Ĵ
    -0.78
    dit
    -0.78
     Lives
    -0.72
    iotic
    -0.70
    furt
    -0.67
    âĸ¬âĸ¬
    -0.67
     Taste
    -0.66
     Luther
    -0.66
    vous
    -0.65
    POSITIVE LOGITS
     towers
    1.02
     tower
    1.02
     skysc
    0.95
    tower
    0.94
     Towers
    0.91
     erected
    0.91
     heights
    0.90
     blocks
    0.87
     crane
    0.86
    itect
    0.79
    Act Density 0.035%

    No Known Activations