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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    akespeare
    -0.75
    Õ
    -0.68
     Engineering
    -0.65
     Gothic
    -0.65
     Architecture
    -0.64
     Reviews
    -0.64
     Upgrade
    -0.61
     Architect
    -0.61
    igsaw
    -0.60
    inity
    -0.60
    POSITIVE LOGITS
    BOOK
    0.75
    KING
    0.72
    ĪĴ
    0.70
    kef
    0.70
    wik
    0.70
    uffed
    0.68
    agents
    0.64
     ruler
    0.64
    saf
    0.63
    WB
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.