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

    Neuronpedia

    INDEX
    Explanations

    references to various political figures and their actions in the context of politics and criticism

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tml
    -0.72
    mble
    -0.70
    lehem
    -0.64
     Mehran
    -0.61
    aughtered
    -0.60
    ãĥĩãĤ£
    -0.58
     ILCS
    -0.58
    Berry
    -0.57
    ranged
    -0.56
    emed
    -0.56
    POSITIVE LOGITS
    's
    1.01
    ÃŃs
    0.86
     inaction
    0.82
     interfering
    0.81
     wanting
    0.79
     behaving
    0.78
     meddling
    0.76
     shortcomings
    0.76
     policies
    0.74
     losing
    0.74
    Act Density 0.397%

    No Known Activations