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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hf
    -0.08
     demonstration
    -0.08
    _nom
    -0.08
    .Summary
    -0.07
    .Question
    -0.07
    _session
    -0.07
    �
    -0.07
     race
    -0.06
    罾
    -0.06
     Neo
    -0.06
    POSITIVE LOGITS
    的魅力
    0.07
    nextInt
    0.06
    atted
    0.06
    سعيد
    0.06
    (percent
    0.06
    募集
    0.06
    巧妙
    0.06
    可愛い
    0.06
     prostit
    0.06
     Garcia
    0.06
    Act Density 0.053%

    No Known Activations