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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the name "Pir."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tra
    -0.74
    ocrine
    -0.72
     Gemini
    -0.68
    ories
    -0.66
    gaard
    -0.65
     DIRECT
    -0.65
    BOOK
    -0.61
    Charge
    -0.61
    flame
    -0.61
    change
    -0.60
    POSITIVE LOGITS
     Pir
    1.12
     pir
    1.04
     mathemat
    1.03
    acles
    1.00
    acy
    0.96
     piracy
    0.88
    aband
    0.88
    Pir
    0.86
     lapt
    0.85
    iform
    0.84
    Act Density 0.005%

    No Known Activations