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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    remium
    -0.08
     brave
    -0.08
    稍微
    -0.08
    систем
    -0.07
    맠
    -0.07
    Aff
    -0.07
    avor
    -0.07
    -esteem
    -0.07
    .onChange
    -0.07
    esteem
    -0.07
    POSITIVE LOGITS
     RD
    0.08
     Т
    0.07
    {k
    0.06
    _NO
    0.06
     nov
    0.06
     pérdida
    0.06
    _plots
    0.06
    一直到
    0.06
     borrowed
    0.06
    (hours
    0.06
    Act Density 0.006%

    No Known Activations