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

    Neuronpedia

    INDEX
    Explanations

    words related to towers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĤ±
    -0.77
    dit
    -0.76
    iotic
    -0.72
    é»Ĵ
    -0.70
    DIT
    -0.70
    orie
    -0.67
    nesia
    -0.66
    vous
    -0.65
    sweet
    -0.64
    ez
    -0.64
    POSITIVE LOGITS
     towers
    1.26
     tower
    1.17
     skysc
    1.10
     Towers
    1.08
    tower
    1.06
     erected
    1.01
     blocks
    1.00
     heights
    0.99
    raper
    0.96
     crane
    0.95
    Act Density 0.028%

    No Known Activations