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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters used in written language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ings
    -0.15
     meisten
    -0.15
    ations
    -0.14
    och
    -0.14
    wing
    -0.14
    lett
    -0.14
    igu
    -0.14
    ables
    -0.13
    enburg
    -0.13
    uar
    -0.13
    POSITIVE LOGITS
    ska
    0.16
    sian
    0.16
    ãĥĭãĥ¡
    0.16
    ed
    0.16
    odyn
    0.16
    å£°éŁ³
    0.15
    nbsp
    0.15
     licensors
    0.15
    amp
    0.15
    vise
    0.15
    Act Density 0.221%

    No Known Activations