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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Amazing
    -0.07
    .deltaTime
    -0.07
     Womens
    -0.07
    Dick
    -0.07
    Entre
    -0.07
    冷笑
    -0.07
     בשנת
    -0.07
    짚
    -0.07
     Eig
    -0.07
    矜
    -0.06
    POSITIVE LOGITS
    ()]);↵
    0.07
     geb
    0.07
     husbands
    0.07
    BEL
    0.07
    팼
    0.06
     bm
    0.06
    צבא
    0.06
    כה
    0.06
    ?>>
    0.06
     haircut
    0.06
    Act Density 0.011%

    No Known Activations