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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seas
    -0.72
    £ı
    -0.70
    OSP
    -0.67
     Labour
    -0.62
    FINE
    -0.62
     Seas
    -0.62
     Rothschild
    -0.61
     Berks
    -0.61
     Rih
    -0.60
     Lanc
    -0.59
    POSITIVE LOGITS
    ources
    1.14
    ourced
    1.10
    aturated
    1.01
    ourcing
    1.01
    wered
    1.01
    olutions
    0.95
    olving
    0.95
    atellite
    0.94
    pecially
    0.92
    hip
    0.91
    Act Density 0.149%

    No Known Activations