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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    resh
    -0.70
    artisan
    -0.69
    Recomm
    -0.64
    urn
    -0.64
    ibilities
    -0.62
     chall
    -0.62
    rack
    -0.62
     nep
    -0.61
    ensical
    -0.61
    ä¹
    -0.61
    POSITIVE LOGITS
     Virgin
    0.82
    Virgin
    0.77
    estamp
    0.76
    \\\\\\\\
    0.73
     Flavoring
    0.72
     Toad
    0.71
     Patron
    0.69
     Lionel
    0.67
     Fiorina
    0.67
     Taco
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.