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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of society

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    mal
    -0.64
    Luk
    -0.63
    inar
    -0.62
    un
    -0.61
     kvar
    -0.61
    cur
    -0.60
     fla
    -0.60
    therin
    -0.60
    fla
    -0.59
     Prin
    -0.59
    POSITIVE LOGITS
     Societies
    1.74
     SOCIETY
    1.65
     Society
    1.62
    Society
    1.61
     societies
    1.55
     society
    1.45
    society
    1.44
     sociedades
    1.13
     sociedad
    1.11
     Gesellschaft
    1.11
    Act Density 0.014%

    No Known Activations