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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.77
     pond
    -0.77
    IENT
    -0.76
     mock
    -0.71
     Frozen
    -0.67
    aneously
    -0.66
    rily
    -0.63
     kan
    -0.63
    IFIC
    -0.63
     STL
    -0.61
    POSITIVE LOGITS
     Kemp
    0.82
     Ezek
    0.73
    ogl
    0.72
    xa
    0.71
    ae
    0.70
    encers
    0.70
    ulton
    0.68
    onom
    0.68
    ĪĴ
    0.68
    oser
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.