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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology and equipment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "death."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pes
    -0.70
     overnight
    -0.69
     equivalent
    -0.67
     territory
    -0.65
     leaflets
    -0.60
     concession
    -0.60
     µ
    -0.60
     Ev
    -0.59
     suc
    -0.58
     label
    -0.58
    POSITIVE LOGITS
    arth
    5.29
    orth
    1.07
    arya
    1.05
    anan
    1.04
    alach
    1.03
    atts
    1.02
    atar
    1.01
    arcity
    0.99
    arthy
    0.97
    arty
    0.96
    Act Density 0.018%

    No Known Activations