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

    Neuronpedia

    INDEX
    Explanations

    terms and discussions related to societal concepts and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mal
    -0.69
    ر
    -0.67
    un
    -0.66
    р
    -0.66
    𝓪
    -0.64
    cur
    -0.64
     kvar
    -0.64
     ros
    -0.64
    𝓸
    -0.63
     Clin
    -0.63
    POSITIVE LOGITS
     Societies
    1.59
     societies
    1.54
     SOCIETY
    1.51
     Society
    1.50
     society
    1.49
    Society
    1.43
    society
    1.37
    ciety
    1.14
     SOCI
    1.11
     Soci
    1.10
    Act Density 0.059%

    No Known Activations