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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent media outlets or news stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CFL
    -0.57
     glim
    -0.50
     Commonwealth
    -0.50
    rollers
    -0.48
    usterity
    -0.48
    ylum
    -0.47
     football
    -0.47
     nonprofits
    -0.47
    wealth
    -0.47
    bernatorial
    -0.47
    POSITIVE LOGITS
    )).
    0.87
     respectively
    0.81
    .</
    0.81
     '.
    0.79
     [/
    0.78
    .[
    0.77
     ".
    0.76
     "âĢ¦
    0.76
    .(
    0.75
    `.
    0.73
    Act Density 1.185%

    No Known Activations