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

    Neuronpedia

    INDEX
    Explanations

    dates and locations associated with individual profiles

    oai_token-act-pair · gpt-3.5-turbo

    profile information related to social media accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dfx
    -0.79
     showc
    -0.76
    rists
    -0.75
    soDeliveryDate
    -0.70
    riet
    -0.68
    faced
    -0.68
    sts
    -0.66
    avorite
    -0.66
    ths
    -0.65
    eways
    -0.64
    POSITIVE LOGITS
     Belg
    1.03
     Netherlands
    1.02
     Bis
    0.98
     Posts
    0.95
     Philippines
    0.95
     United
    0.93
     Austria
    0.91
     Germany
    0.89
     Bulgaria
    0.87
     Slovakia
    0.86
    Act Density 0.013%

    No Known Activations