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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    dif
    -0.07
     tỷ
    -0.07
    \Dependency
    -0.07
    .Inv
    -0.07
    Filed
    -0.06
    ﯨ
    -0.06
     assist
    -0.06
     ADDR
    -0.06
    Mrs
    -0.06
    ᥙ
    -0.06
    POSITIVE LOGITS
    readOnly
    0.08
    コーヒ
    0.08
    .social
    0.08
     healed
    0.07
     gorgeous
    0.07
     פתוח
    0.07
    .cos
    0.07
     חבר
    0.07
     сахар
    0.07
    agged
    0.07
    Act Density 0.004%

    No Known Activations