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

    Neuronpedia

    INDEX
    Explanations

    words related to shorthand or abbreviations, especially with emphasis on the token "SHORT"

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and short forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marcos
    -0.78
    anship
    -0.75
    ADS
    -0.75
    bryce
    -0.71
     Epstein
    -0.70
    rium
    -0.70
    ugi
    -0.70
    paio
    -0.70
     DRAG
    -0.69
    ILA
    -0.68
    POSITIVE LOGITS
    ly
    1.29
    ness
    1.20
    LY
    1.10
    nesses
    0.94
    hearted
    0.94
    heartedly
    0.91
    bodied
    0.89
    entimes
    0.87
    body
    0.87
    est
    0.86
    Act Density 0.188%

    No Known Activations