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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    medium
    -0.08
    🌩
    -0.08
    Polygon
    -0.07
     Logged
    -0.07
     Seamless
    -0.07
    �
    -0.07
     Painter
    -0.07
     Welsh
    -0.07
    hound
    -0.07
     près
    -0.07
    POSITIVE LOGITS
     countered
    0.07
     substitutions
    0.07
    /co
    0.07
    lpVtbl
    0.07
    каз
    0.07
     actresses
    0.07
     blackmail
    0.07
    OP
    0.07
     trolls
    0.07
    tn
    0.06
    Act Density 0.002%

    No Known Activations