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

    Neuronpedia

    INDEX
    Explanations

    references to the word "the," which is primarily used to identify and focus on specific objects, concepts, or entities within a text

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     The
    -0.88
     
    -0.77
     so
    -0.75
     '
    -0.73
     "
    -0.73
     in
    -0.70
     che
    -0.69
     part
    -0.68
     sub
    -0.68
     …
    -0.68
    POSITIVE LOGITS
     Majefty
    1.38
     raiſ
    1.30
     Monfieur
    1.29
     ſever
    1.25
     myſelf
    1.25
     purpoſe
    1.24
     themſelves
    1.23
     poffible
    1.20
     avoient
    1.19
     Efq
    1.19
    Act Density 0.367%

    No Known Activations