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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experience and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alem
    -0.65
    uvres
    -0.63
    cester
    -0.63
     Stoppers
    -0.62
    chitz
    -0.60
    writeFieldEnd
    -0.60
     gallop
    -0.59
     cleanse
    -0.59
     Rask
    -0.58
    nthesis
    -0.58
    POSITIVE LOGITS
     وتسجيلات
    0.46
     Italijani
    0.45
    disposing
    0.43
     frequent
    0.40
     helst
    0.39
     beant
    0.39
     спе
    0.39
    İstinadlar
    0.39
    amili
    0.38
    Dys
    0.37
    Act Density 0.339%

    No Known Activations