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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    substring
    1.11
    𝑘
    1.06
    thirsty
    1.05
    트
    1.03
    kil
    1.03
    𝑟
    1.03
    yun
    1.01
    КТ
    1.00
    éma
    0.99
    𝐶
    0.99
    POSITIVE LOGITS
    ₤
    0.92
     tillage
    0.91
     monies
    0.91
     detach
    0.91
     foal
    0.91
     copolymers
    0.90
     recoveries
    0.88
     joints
    0.88
     conserve
    0.87
     nudity
    0.86
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.