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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Seems
    -0.08
    Problem
    -0.07
     matches
    -0.07
     Result
    -0.07
     х
    -0.07
    咉
    -0.07
     Witch
    -0.07
    ↵		↵
    -0.06
    _matches
    -0.06
    ↵			↵
    -0.06
    POSITIVE LOGITS
     legislation
    0.08
    bpp
    0.08
    顶层设计
    0.07
     Validators
    0.07
    ‾
    0.07
    -ag
    0.07
    _eff
    0.07
    쾨
    0.07
     Mozilla
    0.07
    激光
    0.07
    Act Density 0.005%

    No Known Activations