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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legislative or formal announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ò
    -0.73
     elsewhere
    -0.72
    —-
    -0.71
    SPONSORED
    -0.71
     thereby
    -0.71
     beforehand
    -0.70
    ––
    -0.69
     theirs
    -0.69
     without
    -0.69
     regardless
    -0.69
    POSITIVE LOGITS
    resa
    1.51
    odore
    1.41
    orem
    1.28
    oret
    1.27
    ories
    1.22
    atre
    1.18
     Basics
    1.02
     Latest
    0.94
    ory
    0.94
    sis
    0.92
    Act Density 0.317%

    No Known Activations