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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    words or suffixes related to "ion" indicating processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herty
    -0.82
    ĻĤ
    -0.72
     gobl
    -0.71
     tradem
    -0.70
     citiz
    -0.69
     behav
    -0.68
     unbeliev
    -0.68
     sonic
    -0.66
    ramid
    -0.66
     Tanz
    -0.66
    POSITIVE LOGITS
    naire
    1.57
    naires
    1.31
    ettes
    1.04
    ality
    1.04
    aries
    1.00
    ary
    1.00
    SHIP
    0.92
    arium
    0.92
    aires
    0.90
    ette
    0.86
    Act Density 0.034%

    No Known Activations