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

    Neuronpedia

    INDEX
    Explanations

    mentions of discounts and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BindView
    -0.51
    andExpect
    -0.48
     possib
    -0.47
     wom
    -0.47
     viol
    -0.45
     Largo
    -0.45
     send
    -0.45
     frans
    -0.44
     fon
    -0.44
     ful
    -0.44
    POSITIVE LOGITS
    OrNil
    0.57
    pid
    0.54
    ViewFeatures
    0.50
     silêncio
    0.49
     cadeira
    0.49
     acús
    0.49
     redacción
    0.49
     ***!
    0.48
     econômica
    0.48
     irmã
    0.48
    Act Density 0.323%

    No Known Activations