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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "i" that are part of a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Down
    -0.74
     Territ
    -0.73
    ãĥ¼ãĥĨ
    -0.73
    rique
    -0.72
     Territories
    -0.72
     Rebels
    -0.69
     Reef
    -0.66
    lain
    -0.66
     Everett
    -0.65
     Valkyrie
    -0.64
    POSITIVE LOGITS
    pec
    1.15
    ibo
    1.10
    ota
    1.08
    GPU
    1.03
    wi
    1.00
    ordan
    0.97
    omm
    0.95
    wb
    0.93
    ulia
    0.92
    'm
    0.90
    Act Density 0.034%

    No Known Activations