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

    occurrences of the word "Tu" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.75
    âĸ¬
    -0.73
    rawdownloadcloneembedreportprint
    -0.73
    ãĤ®
    -0.72
     Frie
    -0.70
    å°Ĩ
    -0.70
     constants
    -0.67
    éĹĺ
    -0.66
     SPD
    -0.66
     Rebirth
    -0.66
    POSITIVE LOGITS
    fts
    1.16
    ples
    1.10
    culosis
    1.05
    Tu
    1.01
    pper
    0.97
    esta
    0.94
    itton
    0.93
    pping
    0.92
    ipers
    0.92
     Klux
    0.92
    Act Density 0.013%

    No Known Activations