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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lbrace
    -0.08
     relic
    -0.07
     inf
    -0.07
     Turing
    -0.07
     shortest
    -0.07
     Ada
    -0.07
     snag
    -0.07
     VA
    -0.07
     briefing
    -0.07
     thrift
    -0.07
    POSITIVE LOGITS
    ǥ
    0.07
    <(),
    0.07
    עורר
    0.07
    (mouse
    0.07
    ¾
    0.07
     cautioned
    0.06
    ㎗
    0.06
    丐
    0.06
    -edit
    0.06
    (entity
    0.06
    Act Density 0.002%

    No Known Activations