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

    Neuronpedia

    INDEX
    Explanations

    words related to the original or initial state of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "originally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rom
    -0.83
    wal
    -0.75
    lov
    -0.72
    eer
    -0.71
    eers
    -0.70
    rist
    -0.69
    =-=-=-=-=-=-=-=-
    -0.69
    vich
    -0.69
    masters
    -0.69
     Vish
    -0.68
    POSITIVE LOGITS
     intended
    0.89
     conceived
    0.87
     planned
    0.73
     estab
    0.72
     posted
    0.72
     coined
    0.72
     Posted
    0.69
     designed
    0.69
     planted
    0.69
     assigned
    0.68
    Act Density 0.014%

    No Known Activations