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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" following certain prepositions, adjectives, or conjunctions.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ALSE
    -0.07
    undan
    -0.07
    ardin
    -0.07
    are
    -0.06
    either
    -0.06
    ungan
    -0.06
     either
    -0.06
    Ïĥμα
    -0.06
    loh
    -0.06
    anken
    -0.06
    POSITIVE LOGITS
     seemingly
    0.08
     smallest
    0.07
     staunch
    0.07
     modest
    0.06
     very
    0.06
    quez
    0.06
     Ñģами
    0.06
     though
    0.06
     even
    0.06
     Ñģамого
    0.06
    Act Density 0.029%

    No Known Activations