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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    olson
    -0.70
    xus
    -0.70
    pson
    -0.70
    olini
    -0.63
     analys
    -0.61
    irds
    -0.61
    olics
    -0.61
    sterdam
    -0.61
     LIVE
    -0.59
    emo
    -0.59
    POSITIVE LOGITS
    eah
    0.72
     guiActive
    0.63
    jah
    0.63
    fired
    0.62
    Ïī
    0.62
    rpm
    0.62
    án
    0.60
     pil
    0.58
     externalToEVAOnly
    0.58
    Ñı
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.