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

    Neuronpedia

    INDEX
    Explanations

    phrases ending with 'by'

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "by."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forces
    -0.57
     percept
    -0.57
     MSG
    -0.56
     charm
    -0.56
     liv
    -0.55
     significance
    -0.53
     arts
    -0.53
     involved
    -0.53
    ï¸ı
    -0.52
     cord
    -0.51
    POSITIVE LOGITS
    by
    4.13
    bys
    2.42
    BY
    2.29
    bye
    1.66
    By
    1.53
    bey
    1.40
    bee
    1.32
    bie
    1.31
    byn
    1.29
    bery
    1.28
    Act Density 0.015%

    No Known Activations