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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sails
    -0.71
     toget
    -0.70
     campaign
    -0.67
     prose
    -0.66
     rewrite
    -0.63
     bombardment
    -0.59
     triangle
    -0.58
     halves
    -0.58
    agement
    -0.58
    EngineDebug
    -0.58
    POSITIVE LOGITS
     Brist
    0.81
     lif
    0.78
    gob
    0.66
    »Ĵ
    0.64
    stal
    0.64
    ayne
    0.62
     Dull
    0.61
    aughlin
    0.60
    alter
    0.60
     Cust
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.