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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates and historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    191
    -0.17
    vell
    -0.16
     derec
    -0.15
    lus
    -0.15
     crus
    -0.14
     Bened
    -0.14
    ruz
    -0.14
    uru
    -0.14
     Caj
    -0.14
    immel
    -0.14
    POSITIVE LOGITS
     socialist
    0.34
     Socialist
    0.30
     socialism
    0.28
     Soviet
    0.28
     communist
    0.27
     USSR
    0.25
     Stalin
    0.24
     Cuba
    0.23
     Communist
    0.23
    197
    0.23
    Act Density 0.054%

    No Known Activations