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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    shift
    -0.07
    SV
    -0.07
    [train
    -0.07
     BP
    -0.07
     Jimmy
    -0.07
    PIN
    -0.07
     Serbian
    -0.07
    竭
    -0.07
    汲取
    -0.06
    جام
    -0.06
    POSITIVE LOGITS
    咣
    0.08
    ('/:
    0.08
    /***/
    0.07
    ↦
    0.07
    ㊚
    0.07
     blogger
    0.07
    🎡
    0.07
    �
    0.07
    两三
    0.07
    팜
    0.07
    Act Density 0.497%

    No Known Activations