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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    洗干净
    -0.10
    Resize
    -0.07
     plea
    -0.07
    obel
    -0.07
    𝖊
    -0.07
     Relief
    -0.07
    .say
    -0.07
     Pain
    -0.06
    ipel
    -0.06
     click
    -0.06
    POSITIVE LOGITS
     örg
    0.08
     Driver
    0.07
    WithDuration
    0.07
     effect
    0.07
    ceptions
    0.07
    大师
    0.07
    kategori
    0.07
    trad
    0.07
    但从
    0.07
    _sk
    0.07
    Act Density 0.038%

    No Known Activations