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

    Neuronpedia

    INDEX
    Explanations

    Latin characters and potentially math symbols, although the meaning is not clear from the provided examples

    oai_token-act-pair · gpt-3.5-turbo

    emphasis on key questions or points of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©
    -0.76
    OUNT
    -0.71
    edia
    -0.71
    ruct
    -0.70
    anto
    -0.70
    quickShipAvailable
    -0.70
    æĸ¹
    -0.69
    ãĤ·
    -0.69
    ãĤ´ãĥ³
    -0.68
     Cosponsors
    -0.68
    POSITIVE LOGITS
     luck
    0.76
    ppers
    0.70
     dreaming
    0.61
     linem
    0.60
    luck
    0.60
    berry
    0.58
     topping
    0.58
    zynski
    0.58
     unicorn
    0.57
    ieu
    0.57
    Act Density 0.000%

    No Known Activations