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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    afety
    -0.76
     VIDEOS
    -0.71
    Ent
    -0.69
    anity
    -0.64
     Mutual
    -0.64
    ofi
    -0.64
     Springer
    -0.63
     Videos
    -0.62
    cms
    -0.61
     Awesome
    -0.61
    POSITIVE LOGITS
     referen
    0.72
     estimating
    0.71
    ¶æ
    0.71
     athlet
    0.70
    paio
    0.69
     disadvant
    0.68
    thren
    0.67
     coerc
    0.66
     "$:/
    0.66
     determination
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.