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

    Neuronpedia

    INDEX
    Explanations

    connections between family names and genealogical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rând
    -0.56
     vectorielles
    -0.54
     himſelf
    -0.54
     itſelf
    -0.53
     Monfieur
    -0.51
     pleaſure
    -0.51
     congrès
    -0.49
     Theſe
    -0.49
     înc
    -0.48
     noires
    -0.48
    POSITIVE LOGITS
     family
    0.79
     FAMILY
    0.66
     Familienname
    0.65
    family
    0.63
     Family
    0.63
    exitRule
    0.60
    homonymie
    0.60
     CURIAM
    0.59
    GetBytes
    0.58
    Family
    0.58
    Act Density 0.214%

    No Known Activations