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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    abouts
    -0.90
    dies
    -0.70
    gans
    -0.69
    leness
    -0.69
    loe
    -0.69
    paces
    -0.67
    glers
    -0.66
    cellent
    -0.65
     <@
    -0.64
    ophone
    -0.64
    POSITIVE LOGITS
     diplomacy
    0.65
    potion
    0.61
     epidem
    0.59
    xi
    0.59
    CT
    0.59
     loc
    0.59
    olulu
    0.58
    reci
    0.58
    ida
    0.58
    vernight
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.