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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    olor
    -0.75
    uctor
    -0.74
    thumbnails
    -0.73
    olas
    -0.71
    alos
    -0.65
    rez
    -0.65
    iating
    -0.64
     Renaissance
    -0.64
     Manz
    -0.64
    ,...
    -0.64
    POSITIVE LOGITS
    ERROR
    0.73
    Admin
    0.69
     SUPPORT
    0.68
     Nug
    0.65
     Commando
    0.65
    ãĤĵ
    0.64
     Administ
    0.63
    Administ
    0.62
    ursday
    0.62
    PDATE
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.