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

    Neuronpedia

    INDEX
    Explanations

    references to news agencies like the Associated Press

    oai_token-act-pair · gpt-3.5-turbo

    references to the Associated Press

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gone
    -0.76
     Luthor
    -0.75
     capitalists
    -0.69
    ouses
    -0.67
    istically
    -0.66
    warts
    -0.64
    table
    -0.62
    Reloaded
    -0.61
     capitalist
    -0.61
     dracon
    -0.61
    POSITIVE LOGITS
     Agency
    0.89
    orters
    0.85
    wire
    0.84
    PLIED
    0.81
     Release
    0.76
     Correspond
    0.76
    sburg
    0.75
     Coverage
    0.75
     Corpus
    0.74
     Newsp
    0.72
    Act Density 0.021%

    No Known Activations