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

    Neuronpedia

    INDEX
    Explanations

    phrases related to challenges or struggles

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases and structures relating to time and progression in life experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quin
    -0.66
    ear
    -0.62
     Penal
    -0.60
    oller
    -0.60
    ove
    -0.60
     owns
    -0.57
     superv
    -0.57
     installs
    -0.57
     prosecuting
    -0.56
     corpus
    -0.56
    POSITIVE LOGITS
     been
    1.35
     gotten
    1.10
     begun
    1.08
     grown
    1.06
     undergone
    1.05
     deteriorated
    1.05
     fallen
    1.05
     risen
    1.04
    been
    1.02
     matured
    1.00
    Act Density 0.150%

    No Known Activations