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

    Neuronpedia

    INDEX
    Explanations

    quotations or statements attributed to individuals in news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in a statement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Offline
    -0.80
    TRY
    -0.78
    ience
    -0.77
    Cover
    -0.74
    Throw
    -0.73
    Origin
    -0.70
    dayName
    -0.70
    yt
    -0.70
    SL
    -0.70
    Includes
    -0.69
    POSITIVE LOGITS
     spokesperson
    0.79
     however
    0.76
     spokes
    0.75
     spokeswoman
    0.75
     dated
    0.72
     responding
    0.72
     citing
    0.71
    said
    0.70
     though
    0.69
     Berm
    0.68
    Act Density 0.155%

    No Known Activations