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

    Neuronpedia

    INDEX
    Explanations

    references to political discourse and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allenge
    -0.15
    agn
    -0.15
    nnen
    -0.15
    sko
    -0.15
     Demir
    -0.14
    izons
    -0.14
    oser
    -0.14
    oot
    -0.14
     Nose
    -0.13
     Hubb
    -0.13
    POSITIVE LOGITS
     talk
    0.17
    -talk
    0.16
     Claims
    0.16
     headlines
    0.15
     lately
    0.15
     discussions
    0.15
    talk
    0.15
     discussion
    0.14
    Talk
    0.14
     Talk
    0.14
    Act Density 0.289%

    No Known Activations