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

    Neuronpedia

    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or large entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gently
    -0.79
     Jinn
    -0.73
    cers
    -0.64
     Leone
    -0.64
     Kenobi
    -0.63
     Keller
    -0.62
     Elise
    -0.61
    ĪĴ
    -0.60
    Kind
    -0.59
     Assassins
    -0.59
    POSITIVE LOGITS
     (>
    1.14
     conglomer
    0.77
     undertaking
    0.68
    occup
    0.67
    scale
    0.66
    ————
    0.66
    ãĤ¼ãĤ¦ãĤ¹
    0.66
     multinational
    0.65
    SHA
    0.65
    ortment
    0.64
    Act Density 0.515%

    No Known Activations