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

    Neuronpedia

    INDEX
    Explanations

    references to groups or collectives within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igua
    -0.18
    baum
    -0.18
    廳
    -0.16
    aries
    -0.16
    uet
    -0.15
    chl
    -0.15
    eri
    -0.15
    ister
    -0.15
    lea
    -0.15
    cy
    -0.15
    POSITIVE LOGITS
    ings
    0.20
    think
    0.18
    sWith
    0.17
    -unstyled
    0.17
    sta
    0.17
    spell
    0.16
    sters
    0.16
    ENCHMARK
    0.15
    /team
    0.15
    wide
    0.15
    Act Density 0.071%

    No Known Activations