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

    Neuronpedia

    INDEX
    Explanations

    references to society or societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    𝓸
    -0.64
    𝓪
    -0.64
    cur
    -0.64
     Prat
    -0.61
     kvar
    -0.61
    un
    -0.61
    mal
    -0.61
     GRAN
    -0.60
    ind
    -0.60
    ル
    -0.59
    POSITIVE LOGITS
     society
    2.43
     Society
    2.34
     SOCIETY
    2.30
    Society
    2.27
    society
    2.24
     societies
    2.23
     Societies
    2.16
     sociedad
    1.66
    SOCI
    1.60
     Gesellschaft
    1.55
    Act Density 0.046%

    No Known Activations