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

    Neuronpedia

    INDEX
    Explanations

    structures or forms related to towers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phosa
    -0.77
     propOrder
    -0.72
     biais
    -0.71
     BioLib
    -0.70
    esgue
    -0.68
     McKinnon
    -0.64
    awakeFromNib
    -0.63
     dục
    -0.63
    Vidite
    -0.63
    ptonshire
    -0.63
    POSITIVE LOGITS
     tower
    3.27
     Tower
    3.22
     TOWER
    2.98
    Tower
    2.98
     towers
    2.92
    tower
    2.88
     Towers
    2.60
    towers
    2.36
     torre
    2.03
    タワー
    1.75
    Act Density 0.069%

    No Known Activations