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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities or controversies

    oai_token-act-pair · gpt-3.5-turbo

    words associated with significant events or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertain
    -0.60
    ibaba
    -0.60
    nosis
    -0.57
    phas
    -0.56
    erent
    -0.56
     proble
    -0.55
    eree
    -0.55
     wills
    -0.53
     uniqueness
    -0.50
     deserts
    -0.50
    POSITIVE LOGITS
     shortly
    1.10
     yesterday
    1.03
    ,[
    1.00
     last
    0.96
     earlier
    0.89
     Wednesday
    0.88
     Monday
    0.87
     Tuesday
    0.87
     after
    0.86
     Thursday
    0.86
    Act Density 0.663%

    No Known Activations