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

    Neuronpedia

    INDEX
    Explanations

    keywords related to politics, media commentary, and public figures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal events and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rown
    -0.61
    azines
    -0.61
    ickets
    -0.61
     substantive
    -0.60
     ILCS
    -0.57
    urry
    -0.56
     certific
    -0.56
    rament
    -0.55
     nominal
    -0.55
    MHz
    -0.55
    POSITIVE LOGITS
    :"
    0.87
    undrum
    0.83
     succinct
    0.78
    :[
    0.78
     saying
    0.78
     sarcast
    0.76
     noting
    0.76
    :]
    0.76
    terday
    0.75
     thanking
    0.72
    Act Density 0.691%

    No Known Activations