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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating political criticism and issues related to governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Alert
    -0.73
     besides
    -0.72
    nb
    -0.69
    TION
    -0.67
    tracking
    -0.67
    ¶
    -0.66
    poke
    -0.66
    LOD
    -0.66
    icably
    -0.65
    veland
    -0.65
    POSITIVE LOGITS
     slightest
    1.13
    ocracy
    1.10
     nation
    1.08
    ocratic
    1.08
     greatest
    1.00
     masses
    0.99
     wealthiest
    0.97
     world
    0.95
    ocrats
    0.95
     realities
    0.94
    Act Density 0.455%

    No Known Activations