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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hierarchy or ranking

    oai_token-act-pair · gpt-3.5-turbo

    references to "second-class" status or treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vez
    -0.78
    kee
    -0.72
    tti
    -0.64
    ãĤĭ
    -0.64
    gerald
    -0.64
    ihil
    -0.63
    velt
    -0.62
    bleacher
    -0.61
    enegger
    -0.61
    ¶ħ
    -0.60
    POSITIVE LOGITS
    hand
    1.27
    arily
    1.12
     baseman
    1.06
    aries
    1.03
     guessing
    0.92
     glance
    0.90
    ary
    0.86
    chance
    0.83
     glances
    0.82
     halves
    0.80
    Act Density 0.050%

    No Known Activations