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

    Neuronpedia

    INDEX
    Explanations

    special characters that may indicate programming or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    references to digital content sharing and collaboration platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Norm
    -0.69
     tram
    -0.63
     bom
    -0.62
     unsc
    -0.60
    esta
    -0.59
     Nig
    -0.58
    arie
    -0.58
     swirl
    -0.58
     hay
    -0.57
     Bob
    -0.57
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.96
    thumbnails
    0.77
    taboola
    0.76
    Israeli
    0.76
    iHUD
    0.75
    Python
    0.74
    http
    0.73
    books
    0.73
    SCP
    0.72
    archive
    0.72
    Act Density 0.080%

    No Known Activations