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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social issues and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _social
    -0.25
     Social
    -0.23
     social
    -0.20
     socialism
    -0.18
    社ä¼ļ
    -0.18
    Social
    -0.18
     SOCIAL
    -0.18
     sociale
    -0.17
    社æľĥ
    -0.17
     sociales
    -0.17
    POSITIVE LOGITS
    /pol
    0.21
    -economic
    0.21
    -pol
    0.20
    -cultural
    0.20
     cle
    0.20
     fabric
    0.19
    istic
    0.19
     engineering
    0.19
    -ps
    0.18
    /e
    0.18
    Act Density 0.028%

    No Known Activations