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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     neighbourhood
    -0.07
     Administrator
    -0.07
     compassionate
    -0.07
    "As
    -0.07
     dismissing
    -0.07
     greet
    -0.07
    _BS
    -0.07
    ถาม
    -0.07
     Bu
    -0.06
     watches
    -0.06
    POSITIVE LOGITS
    🚉
    0.07
     latency
    0.07
    .tar
    0.07
     tries
    0.07
    مطل
    0.07
    adero
    0.07
    𬶏
    0.07
    ꦇ
    0.07
    🥃
    0.06
    ................................
    0.06
    Act Density 0.009%

    No Known Activations