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

    Neuronpedia

    INDEX
    Explanations

    terms related to the action of discarding or eliminating something

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of discarding or canceling plans and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icipated
    -0.71
    VERTIS
    -0.68
     FISA
    -0.65
     Origins
    -0.62
     Inquisitor
    -0.62
     Augusta
    -0.60
    iquid
    -0.60
     Admir
    -0.60
     Editorial
    -0.59
     districts
    -0.59
    POSITIVE LOGITS
     scra
    1.44
    pling
    1.12
    pping
    1.05
    ppy
    1.04
     scrap
    1.01
    ppers
    0.97
    ãĤ©
    0.94
    ppings
    0.90
     scrapped
    0.89
    ãĤ§
    0.89
    Act Density 0.005%

    No Known Activations