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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    426
    -0.16
    391
    -0.15
     Gri
    -0.14
    389
    -0.14
    eut
    -0.14
    aqu
    -0.13
    ivant
    -0.13
     this
    -0.13
    umb
    -0.13
    olla
    -0.13
    POSITIVE LOGITS
     hã
    0.14
    AccessException
    0.14
    мм
    0.14
    eldo
    0.13
    Ã¤ÃŁ
    0.13
     Skinner
    0.13
    aggio
    0.13
    eneric
    0.13
    ัศ
    0.13
    pent
    0.13
    Act Density 0.112%

    No Known Activations