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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    git
    -0.77
    toe
    -0.73
    tta
    -0.71
    ttes
    -0.67
     Kry
    -0.67
    uten
    -0.66
    aml
    -0.63
    tto
    -0.63
    added
    -0.63
    aber
    -0.63
    POSITIVE LOGITS
    actionDate
    0.82
     Archdemon
    0.77
    IRD
    0.73
    avorite
    0.69
    SPONSORED
    0.69
    GGGGGGGG
    0.66
     Lear
    0.64
     glim
    0.64
    ESE
    0.64
     enriched
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.