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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    references to something identified as "former."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otle
    -0.92
    andise
    -0.86
    atown
    -0.85
    antics
    -0.82
    achus
    -0.79
    anguage
    -0.77
    ammy
    -0.76
    anders
    -0.75
    ourced
    -0.72
    onso
    -0.72
    POSITIVE LOGITS
     Yugoslav
    1.11
     Yugoslavia
    1.10
     Soviet
    0.85
     convict
    0.77
     smoker
    0.73
     communist
    0.71
     dictator
    0.71
     occupant
    0.71
     Confederacy
    0.70
     president
    0.69
    Act Density 0.029%

    No Known Activations