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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ctrl
    -0.07
    alance
    -0.07
    唱片
    -0.07
    〜
    -0.07
    变更
    -0.07
    _less
    -0.07
     risk
    -0.07
    歌唱
    -0.07
     signs
    -0.07
    倌
    -0.07
    POSITIVE LOGITS
    -hole
    0.08
     vår
    0.07
     interpol
    0.07
     divisions
    0.07
    قوان
    0.07
     ==(
    0.07
    כולנו
    0.07
    ",[
    0.07
    !↵
    0.06
     stripslashes
    0.06
    Act Density 0.000%

    No Known Activations