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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Melt
    -0.76
    lt
    -0.67
    =$
    -0.61
     Synd
    -0.60
     Riy
    -0.59
     Lavrov
    -0.59
     Falk
    -0.59
    jured
    -0.59
     AUD
    -0.59
     Bullets
    -0.59
    POSITIVE LOGITS
    aukee
    0.94
    baugh
    0.75
    ħĭ
    0.74
    olson
    0.74
    OOL
    0.70
    Ùĩ
    0.66
    auder
    0.66
    esian
    0.66
    ãĥ³ãĤ¸
    0.65
     perce
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.