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

    Neuronpedia

    INDEX
    Explanations

    references to society and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    on
    -0.57
    р
    -0.57
    tral
    -0.56
    𝓸
    -0.56
    un
    -0.55
    ر
    -0.54
    ########.
    -0.54
    ck
    -0.54
    𝓪
    -0.53
     Prat
    -0.53
    POSITIVE LOGITS
     society
    3.92
    society
    3.52
    Society
    3.45
     Society
    3.42
     SOCIETY
    3.36
     societies
    3.08
     Societies
    2.76
     sociedad
    2.51
     sociedade
    2.41
    SOCI
    2.30
    Act Density 0.047%

    No Known Activations