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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riba
    -0.17
    naire
    -0.16
    thon
    -0.16
    ption
    -0.16
    compress
    -0.15
    oppins
    -0.15
    abbit
    -0.15
    mente
    -0.14
    pliers
    -0.14
    oleon
    -0.14
    POSITIVE LOGITS
     sure
    0.20
    arded
    0.16
    ings
    0.16
    eline
    0.16
     Sure
    0.15
    ardless
    0.15
    ets
    0.15
     merc
    0.15
    een
    0.15
    zier
    0.15
    Act Density 0.095%

    No Known Activations