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

    Neuronpedia

    INDEX
    Explanations

    SQL queries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "Q" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.77
    wagen
    -0.70
     Dortmund
    -0.65
    ufact
    -0.65
     afore
    -0.64
     Abram
    -0.62
     Lauder
    -0.60
     Ashton
    -0.59
     fullest
    -0.59
     Pra
    -0.58
    POSITIVE LOGITS
    UE
    1.47
    ues
    1.10
    uez
    1.06
    iao
    1.03
    ued
    1.02
    atar
    1.02
    WER
    1.00
    DN
    0.99
    UES
    0.95
    ubes
    0.94
    Act Density 0.026%

    No Known Activations