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

    Neuronpedia

    INDEX
    Explanations

    numerical figures and measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nai
    -0.71
    BRE
    -0.67
    dayName
    -0.67
    soDeliveryDate
    -0.65
    Shut
    -0.63
    bart
    -0.61
    hai
    -0.61
    ONSORED
    -0.60
    orc
    -0.60
     )))
    -0.59
    POSITIVE LOGITS
     none
    0.79
     namely
    0.77
     including
    0.74
     unsurprisingly
    0.72
    there
    0.68
    etheus
    0.65
    avorite
    0.65
     notably
    0.64
     fewer
    0.64
     one
    0.60
    Act Density 0.098%

    No Known Activations