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

    Neuronpedia

    INDEX
    Explanations

    the word "those" followed by a numerical value, such as "9" or "10"

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases focused on the word "those."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.80
    ILY
    -0.77
    kamp
    -0.76
    ob
    -0.76
    ario
    -0.70
    onis
    -0.69
    shapeshifter
    -0.68
     Shutterstock
    -0.65
    orate
    -0.64
     Ness
    -0.63
    POSITIVE LOGITS
     pesky
    1.15
     kinds
    1.04
     sorts
    0.93
     same
    0.78
     fateful
    0.78
     types
    0.77
     thoughts
    0.76
     facts
    0.75
     sights
    0.75
     feelings
    0.73
    Act Density 0.067%

    No Known Activations