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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspic
    -0.77
     includ
    -0.66
     targ
    -0.65
     NETWORK
    -0.64
    ccording
    -0.64
     SYSTEM
    -0.64
     referen
    -0.62
     destro
    -0.62
     behav
    -0.60
     XCOM
    -0.60
    POSITIVE LOGITS
     alike
    1.03
    eele
    0.91
    axter
    0.88
    esson
    0.86
    ilda
    0.85
    oliath
    0.79
    meier
    0.77
    bur
    0.75
    Ru
    0.74
    soDeliveryDate
    0.74
    Act Density 0.253%

    No Known Activations