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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate possession or ownership, particularly with the word "our."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.17
    asty
    -0.16
    eno
    -0.16
    aters
    -0.16
    ons
    -0.15
    ải
    -0.15
    holds
    -0.15
    rics
    -0.15
    OE
    -0.14
    orous
    -0.14
    POSITIVE LOGITS
    anos
    0.21
    anou
    0.17
    tesy
    0.17
    uguay
    0.16
    SEL
    0.16
    imei
    0.16
    iginal
    0.15
     own
    0.15
    /my
    0.15
     mutual
    0.15
    Act Density 0.170%

    No Known Activations