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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    寞
    -0.07
    ❪
    -0.07
    //'
    -0.07
    CONNECT
    -0.07
    📥
    -0.07
    /she
    -0.07
    anya
    -0.06
     IsValid
    -0.06
    noon
    -0.06
     установлен
    -0.06
    POSITIVE LOGITS
     Trainer
    0.07
    用手
    0.07
    Ordinal
    0.07
     Sick
    0.06
     synaptic
    0.06
    .outer
    0.06
     braking
    0.06
    -free
    0.06
     flower
    0.06
     cał
    0.06
    Act Density 0.004%

    No Known Activations