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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific names and locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or names related to the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.76
    arching
    -0.74
    eways
    -0.70
    ickr
    -0.69
    ocobo
    -0.69
    via
    -0.68
    notice
    -0.68
    pg
    -0.68
    Hispanic
    -0.68
    wcs
    -0.67
    POSITIVE LOGITS
     Benson
    1.17
    hurst
    0.92
    ModLoader
    0.88
    sterdam
    0.86
     Bag
    0.78
     Briggs
    0.75
     Henderson
    0.70
    ua
    0.70
     Lamb
    0.68
     offic
    0.67
    Act Density 0.009%

    No Known Activations