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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     redhead
    -0.20
    odos
    -0.16
    åIJĪ
    -0.16
    pector
    -0.15
     redd
    -0.15
     orange
    -0.15
    une
    -0.15
    oden
    -0.15
    ÙģاÙĦ
    -0.15
    illard
    -0.15
    POSITIVE LOGITS
    ened
    0.39
    smith
    0.38
    ening
    0.34
    mailer
    0.28
    listed
    0.28
    berry
    0.28
    curr
    0.27
    berries
    0.26
    adder
    0.25
    listing
    0.25
    Act Density 0.037%

    No Known Activations