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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    __,
    -0.08
    -men
    -0.07
    _Location
    -0.07
    _beh
    -0.07
    beck
    -0.07
     drills
    -0.07
    Pear
    -0.06
     writings
    -0.06
     Frozen
    -0.06
    ikers
    -0.06
    POSITIVE LOGITS
    罱
    0.07
    好吗
    0.07
     genitals
    0.07
    ⊨
    0.06
    כי
    0.06
    叔
    0.06
    ']/
    0.06
    吱
    0.06
     carrots
    0.06
     המלא
    0.06
    Act Density 0.078%

    No Known Activations