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

    Neuronpedia

    INDEX
    Explanations

    references to insulated products and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arih
    -0.16
    æ²¹
    -0.16
    è¡£
    -0.15
     æķħ
    -0.15
    tar
    -0.15
    avn
    -0.14
    apan
    -0.14
    roe
    -0.14
     Hust
    -0.14
     Salon
    -0.14
    POSITIVE LOGITS
     straw
    0.26
     tum
    0.24
     drinking
    0.24
     insulated
    0.24
     sip
    0.23
     leak
    0.23
     Pitch
    0.23
     drink
    0.23
     Leak
    0.23
     Drinking
    0.22
    Act Density 0.017%

    No Known Activations