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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Unicode
    -0.63
     Tai
    -0.63
    awei
    -0.62
    ãĥ¯
    -0.62
    ãĥ¥
    -0.61
    bush
    -0.61
    ãĥ¢
    -0.58
    olphins
    -0.58
     intercepted
    -0.58
    asio
    -0.57
    POSITIVE LOGITS
     Waste
    0.74
    schild
    0.74
    ï¸
    0.62
    overty
    0.62
     cheaply
    0.59
    thus
    0.59
    Ãĥ
    0.58
    oles
    0.57
    ummer
    0.57
    ented
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.