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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    forum
    -0.10
    (Frame
    -0.08
    oes
    -0.08
     outf
    -0.07
    都知道
    -0.07
    _OBJ
    -0.07
    esso
    -0.07
    ?f
    -0.07
    chos
    -0.07
    既
    -0.07
    POSITIVE LOGITS
    ˩
    0.07
    _api
    0.07
     writers
    0.07
    הלך
    0.07
    短视频
    0.07
    談
    0.07
    ⑅
    0.07
    뼝
    0.06
    ಐ
    0.06
    内阁
    0.06
    Act Density 0.001%

    No Known Activations