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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pledges
    -0.07
     detect
    -0.07
     эконом
    -0.07
    avings
    -0.06
     prefs
    -0.06
    奋斗目标
    -0.06
    听过
    -0.06
    put
    -0.06
     deem
    -0.06
    Ident
    -0.06
    POSITIVE LOGITS
     במי
    0.07
    戴着
    0.07
    eteria
    0.07
     сфере
    0.07
    .break
    0.07
    RESS
    0.07
    悲
    0.07
    光线
    0.07
    𐤏
    0.07
    蜿
    0.07
    Act Density 0.000%

    No Known Activations