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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    geist
    -0.72
     mistaken
    -0.70
     misinformation
    -0.67
     con
    -0.64
     PowerPoint
    -0.62
     Hurricanes
    -0.61
     click
    -0.60
     Shoot
    -0.59
     Hollywood
    -0.59
     Scient
    -0.59
    POSITIVE LOGITS
    anchester
    0.95
    trak
    0.80
    interstitial
    0.79
    doms
    0.77
    maxwell
    0.76
    wark
    0.76
    ð
    0.74
    oln
    0.74
    stairs
    0.73
    orthy
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.