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

    Neuronpedia

    INDEX
    Explanations

    references to events, speakers, and presentations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATRIX
    -0.16
    è¨Ī
    -0.15
    822
    -0.15
    िवस
    -0.15
     tow
    -0.15
    itr
    -0.15
    èªĮ
    -0.14
     Nos
    -0.14
    osen
    -0.14
     Rear
    -0.14
    POSITIVE LOGITS
     booking
    0.24
     Speaker
    0.22
     speaker
    0.22
     Booking
    0.22
     Fee
    0.21
    Spe
    0.21
    Booking
    0.21
     bookings
    0.20
    fee
    0.20
     fee
    0.19
    Act Density 0.001%

    No Known Activations