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

    Neuronpedia

    INDEX
    Explanations

    statements describing personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal experiences or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leck
    -0.67
    ayer
    -0.63
     2020
    -0.63
     Gutenberg
    -0.62
    eus
    -0.61
     Contents
    -0.60
    ANK
    -0.59
    ember
    -0.58
     TMZ
    -0.57
     Utilities
    -0.57
    POSITIVE LOGITS
     myself
    1.28
     personally
    0.85
     anecd
    0.82
     experien
    0.80
     encount
    0.79
     firsthand
    0.75
     fond
    0.73
     my
    0.72
     fortunate
    0.72
     cowork
    0.71
    Act Density 0.477%

    No Known Activations