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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isActive
    -0.07
    .experimental
    -0.07
     messing
    -0.07
    .sec
    -0.07
     kissing
    -0.06
    ежду
    -0.06
    Î
    -0.06
     astronomy
    -0.06
    needle
    -0.06
    𝐣
    -0.06
    POSITIVE LOGITS
     special
    0.08
     Variation
    0.08
    教育培训
    0.07
     saturation
    0.07
     Corruption
    0.07
     _|
    0.07
    tività
    0.07
    今日は
    0.07
    找回
    0.07
    百
    0.07
    Act Density 0.001%

    No Known Activations