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

    Neuronpedia

    INDEX
    Explanations

    references to specific years or historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opp
    -0.16
     crus
    -0.16
     laisse
    -0.15
     Flem
    -0.15
    obar
    -0.14
    sh
    -0.14
    .tmp
    -0.14
    uru
    -0.14
     Shelby
    -0.14
    ruz
    -0.14
    POSITIVE LOGITS
     Soviet
    0.28
     socialist
    0.28
     Stalin
    0.28
     Lenin
    0.27
     Communist
    0.26
     Cuba
    0.25
     Socialist
    0.25
     socialism
    0.24
     communist
    0.24
     Party
    0.24
    Act Density 0.185%

    No Known Activations