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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and expressions indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.55
    otho
    -0.53
    washer
    -0.52
    principalTable
    -0.52
     parseFrom
    -0.51
    PhysRev
    -0.50
     gleichen
    -0.50
    ïti
    -0.50
    webElement
    -0.50
    кових
    -0.49
    POSITIVE LOGITS
    又不是
    0.57
     tartalomajánló
    0.56
    pakah
    0.54
    romolecules
    0.51
    lankton
    0.50
     становника
    0.50
    ftagPool
    0.48
    reportWebVitals
    0.48
     समीक्षाएं
    0.47
    DrawerToggle
    0.47
    Act Density 0.176%

    No Known Activations