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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ween
    -0.27
     princ
    -0.27
    apers
    -0.26
    achen
    -0.25
    ocity
    -0.25
    ymax
    -0.25
    utorials
    -0.25
     Posts
    -0.24
     hills
    -0.24
    arat
    -0.24
    POSITIVE LOGITS
    lient
    0.31
    IFS
    0.27
     allowed
    0.26
     vs
    0.25
    è¾ħåĬ©
    0.25
    eos
    0.25
    IES
    0.25
    @protocol
    0.25
    æ¯ı
    0.24
    ÑĤеÑĢ
    0.24
    Act Density 1.457%

    No Known Activations

    This feature has no known activations.