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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Efq
    -1.14
     Houſe
    -1.13
     myſelf
    -1.12
     Theſe
    -1.11
     Jefus
    -1.11
     raiſ
    -1.11
     itſelf
    -1.10
     againſt
    -1.09
     fubject
    -1.07
     poffible
    -1.07
    POSITIVE LOGITS
     also
    0.40
     later
    0.40
     own
    0.39
     potentially
    0.39
    als
    0.35
    ines
    0.34
     at
    0.33
     first
    0.33
     factor
    0.33
     then
    0.32
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.