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

    Neuronpedia

    INDEX
    Explanations

    originally mentioned things or facts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "originally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rom
    -0.88
    masters
    -0.80
    wal
    -0.80
    =-=-=-=-=-=-=-=-
    -0.74
     Vish
    -0.73
    laws
    -0.72
    eer
    -0.72
    rist
    -0.71
    eers
    -0.67
    bara
    -0.66
    POSITIVE LOGITS
     conceived
    0.90
     intended
    0.88
     planned
    0.73
     coined
    0.73
     posted
    0.73
     estab
    0.72
     planted
    0.71
     slated
    0.71
     belonged
    0.71
     designed
    0.71
    Act Density 0.015%

    No Known Activations