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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    itore
    -0.07
     sen
    -0.07
     Including
    -0.07
     pun
    -0.07
    苧
    -0.07
    ⏶
    -0.06
    Aug
    -0.06
    .Comment
    -0.06
    Pat
    -0.06
    Bot
    -0.06
    POSITIVE LOGITS
    _methods
    0.07
     יהודה
    0.07
     가장
    0.07
    =os
    0.06
     toutes
    0.06
     너무
    0.06
    вяз
    0.06
    依然是
    0.06
    تعامل
    0.06
    封闭
    0.06
    Act Density 0.035%

    No Known Activations