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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     amph
    -0.07
     dang
    -0.07
    RATE
    -0.07
    퐝
    -0.07
    омер
    -0.07
    Փ
    -0.07
    棼
    -0.07
    𝘗
    -0.07
    amazon
    -0.07
     paran
    -0.07
    POSITIVE LOGITS
     diets
    0.08
     �
    0.07
    	exports
    0.07
     HM
    0.07
     yet
    0.07
     �
    0.07
     Callback
    0.07
    渔业
    0.07
     assistant
    0.07
    iostream
    0.07
    Act Density 0.012%

    No Known Activations