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

    Neuronpedia

    INDEX
    Explanations

    words related to characteristics or properties

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "nature" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rom
    -0.79
    itone
    -0.77
    ogun
    -0.75
    oning
    -0.74
    agher
    -0.72
    visor
    -0.71
     Sutherland
    -0.71
    visors
    -0.70
    ordable
    -0.69
    ron
    -0.69
    POSITIVE LOGITS
     incarn
    0.73
     nature
    0.72
    uality
    0.70
     preserves
    0.70
     occurrences
    0.68
     advers
    0.64
    DragonMagazine
    0.63
     intertwined
    0.63
     Deity
    0.63
    entially
    0.63
    Act Density 0.014%

    No Known Activations