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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ⏳
    0.88
    🚬
    0.86
    🔞
    0.85
     இரத்த
    0.84
    porn
    0.84
    🩸
    0.83
     pornography
    0.82
    ♏
    0.82
    🔪
    0.80
    ⛓
    0.80
    POSITIVE LOGITS
     whimsical
    1.72
     comical
    1.59
     cartoon
    1.58
     aventuras
    1.56
     Adventures
    1.51
     Cartoon
    1.51
     adventures
    1.50
     fairytale
    1.50
     mischievous
    1.46
     adorable
    1.44
    Act Density 0.908%

    No Known Activations