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

    repeated occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     besides
    -0.77
    ãĤ´ãĥ³
    -0.76
    olt
    -0.73
    provided
    -0.72
    agree
    -0.72
    pots
    -0.69
    arettes
    -0.69
    ca
    -0.69
    furt
    -0.68
    verage
    -0.68
    POSITIVE LOGITS
     venerable
    0.99
     Department
    0.97
     United
    0.97
     feds
    0.95
     Associated
    0.94
     Ministry
    0.92
     FBI
    0.91
     Supreme
    0.90
     legislature
    0.90
     Bureau
    0.89
    Act Density 0.267%

    No Known Activations