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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ombs
    -0.89
    stocks
    -0.80
    urized
    -0.76
    asts
    -0.74
    oaded
    -0.73
    itives
    -0.73
    terday
    -0.72
    ortunately
    -0.70
    rand
    -0.69
    bind
    -0.68
    POSITIVE LOGITS
    croft
    0.75
     dich
    0.66
     nature
    0.65
     ze
    0.64
    fell
    0.63
    ischer
    0.62
    Ń·
    0.62
    tenance
    0.61
     disse
    0.60
     fal
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.