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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     قد
    -0.07
     سوف
    -0.06
    福音
    -0.06
    _scalar
    -0.06
    _seen
    -0.06
    (conv
    -0.06
     Volunteers
    -0.06
    객
    -0.06
     użytk
    -0.06
    הז
    -0.06
    POSITIVE LOGITS
    (ph
    0.07
    changes
    0.07
    (mode
    0.07
     chats
    0.07
     %-
    0.07
    interpreter
    0.07
    人们
    0.07
     MPG
    0.06
     Gmail
    0.06
    的热情
    0.06
    Act Density 0.090%

    No Known Activations