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

    Neuronpedia

    INDEX
    Explanations

    political statements and expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Located
    -0.73
    population
    -0.62
     harvest
    -0.62
     Printing
    -0.60
     Agric
    -0.59
    cause
    -0.59
     Harvest
    -0.58
     Mandatory
    -0.57
    aughtered
    -0.57
     Regist
    -0.57
    POSITIVE LOGITS
     upbeat
    0.98
     angrily
    0.96
     sarcast
    0.94
     scathing
    0.93
     apologizing
    0.90
     reiterate
    0.88
     remarks
    0.87
    lique
    0.86
     reiterated
    0.85
     apolog
    0.85
    Act Density 0.405%

    No Known Activations