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

    Neuronpedia

    INDEX
    Explanations

    references to entities named "Smith."

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the name "Smith."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tou
    -0.72
    HO
    -0.65
     Okinawa
    -0.65
    gencies
    -0.64
    CU
    -0.63
    Tokens
    -0.63
    oup
    -0.61
    Interstitial
    -0.61
     ambul
    -0.61
    merga
    -0.60
    POSITIVE LOGITS
     Smith
    3.65
    Smith
    3.22
    smith
    1.58
     Jones
    1.38
     Simmons
    1.35
     Johnson
    1.27
     Thompson
    1.26
     Skinner
    1.24
     Roberts
    1.24
     Harris
    1.24
    Act Density 0.028%

    No Known Activations