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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating reduction or limitation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reducing or minimizing quantities or sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awn
    -0.81
    mir
    -0.75
    llo
    -0.68
    ren
    -0.68
    ris
    -0.64
    ear
    -0.64
    acha
    -0.64
    oris
    -0.63
    ath
    -0.63
    ADD
    -0.62
    POSITIVE LOGITS
     rubble
    1.08
     obscurity
    1.04
     ashes
    1.03
     zero
    0.95
     basics
    0.92
     earth
    0.92
     scraps
    0.90
     lowest
    0.89
     mere
    0.89
     negligible
    0.88
    Act Density 0.146%

    No Known Activations