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

    Neuronpedia

    INDEX
    Explanations

    references to voters and the general public in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.61
    ándolos
    -0.53
     Einer
    -0.53
    Personendaten
    -0.52
    UnsafeEnabled
    -0.52
    ____
    -0.51
    こともあります
    -0.50
    ilyen
    -0.50
     propi
    -0.50
     verhält
    -0.49
    POSITIVE LOGITS
     themſelves
    0.98
     voters
    0.97
     residents
    0.93
     Efq
    0.92
     fans
    0.91
     shoppers
    0.89
     myſelf
    0.89
     readers
    0.87
     commuters
    0.84
     motorists
    0.83
    Act Density 0.424%

    No Known Activations