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

    Neuronpedia

    INDEX
    Explanations

    references to social topics or concepts related to community and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Turquía
    -0.35
     EEUU
    -0.35
     Nachfolger
    -0.33
     sengaja
    -0.32
     Darüber
    -0.32
    ujących
    -0.31
     Inglaterra
    -0.31
    ujące
    -0.30
    Deutschland
    -0.30
     Herausgeber
    -0.30
    POSITIVE LOGITS
     social
    1.19
     socio
    1.13
     Socio
    1.06
     Social
    1.05
     socioeconomic
    1.02
    social
    1.02
    Social
    0.96
    socio
    0.95
    Socio
    0.93
     SOCIAL
    0.88
    Act Density 0.090%

    No Known Activations