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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    manship
    -0.86
     CARE
    -0.75
     Dialogue
    -0.72
     JJ
    -0.69
    aeda
    -0.67
    Sphere
    -0.65
     Sequence
    -0.64
     Feedback
    -0.64
     Adapt
    -0.63
     Consent
    -0.63
    POSITIVE LOGITS
    ibaba
    0.73
     lav
    0.69
     grapes
    0.68
     tul
    0.67
    ated
    0.65
     gall
    0.64
     pancakes
    0.64
    alsh
    0.63
    æ©Ł
    0.63
    è¦ļéĨĴ
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.