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

    Neuronpedia

    INDEX
    Explanations

    instances of technical jargon or abbreviations in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </thead>
    -0.49
    xsi
    -0.46
     atto
    -0.46
     pot
    -0.43
     arche
    -0.41
     pole
    -0.40
     Tens
    -0.39
    ه
    -0.39
     off
    -0.39
    scope
    -0.39
    POSITIVE LOGITS
     dezelve
    0.79
     desmotivaciones
    0.78
     systematically
    0.67
     systematic
    0.67
     parachoque
    0.66
     maternidade
    0.63
     Bewußt
    0.63
     mijne
    0.62
     nothwendig
    0.61
     plufieurs
    0.61
    Act Density 0.234%

    No Known Activations