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

    Neuronpedia

    INDEX
    Explanations

    pronouns and phrases that indicate possession or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Passenger
    -0.16
     пÑĥ
    -0.15
    utt
    -0.15
    volatile
    -0.14
    ASC
    -0.14
    æ¿Ł
    -0.14
    _modes
    -0.14
    flow
    -0.13
    _CRC
    -0.13
    RATION
    -0.13
    POSITIVE LOGITS
    buz
    0.17
    istr
    0.16
    anki
    0.15
    gap
    0.15
    ntl
    0.15
    suite
    0.15
    rof
    0.14
     Cust
    0.14
    oti
    0.14
    sap
    0.14
    Act Density 0.001%

    No Known Activations