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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.81
    Reviewed
    -0.75
     tasted
    -0.68
    \\\\
    -0.67
    IENCE
    -0.66
    erves
    -0.65
    ufact
    -0.65
    ellen
    -0.64
    reetings
    -0.64
     resil
    -0.63
    POSITIVE LOGITS
    opia
    0.75
     Supplementary
    0.63
    tera
    0.62
    glass
    0.61
    oglu
    0.61
     gray
    0.60
    opian
    0.60
    vernment
    0.59
    ama
    0.59
    tiny
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.