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

    Neuronpedia

    INDEX
    Explanations

    words related to prime numbers and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Donuts
    -0.51
    igas
    -0.50
    arning
    -0.49
     Socks
    -0.49
     sure
    -0.49
    joi
    -0.48
    MockBean
    -0.47
    licky
    -0.47
     referenties
    -0.47
     geführt
    -0.47
    POSITIVE LOGITS
    aca
    1.02
    +#+#
    0.87
    ACA
    0.83
     propOrder
    0.82
    __":
    0.68
    __":
    0.68
    -------------</
    0.66
    cycle
    0.66
    Carriera
    0.65
    ji
    0.64
    Act Density 0.132%

    No Known Activations