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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ger
    -0.14
    bote
    -0.14
    OUNCE
    -0.14
    oved
    -0.14
    mil
    -0.14
     Gem
    -0.13
    èĿ
    -0.13
    586
    -0.13
    nen
    -0.13
    ounge
    -0.13
    POSITIVE LOGITS
    abet
    0.16
    atile
    0.16
    rette
    0.16
    icina
    0.15
    erre
    0.15
    WEEN
    0.14
     Ange
    0.14
    ë¦
    0.14
    ëĵľë¦¬
    0.14
    Disposition
    0.13
    Act Density 0.187%

    No Known Activations