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

    Neuronpedia

    INDEX
    Explanations

    names of researchers or authors in academic citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     in
    -0.50
    مین
    -0.49
     for
    -0.48
    '
    -0.47
    <eos>
    -0.46
     
    -0.46
     or
    -0.46
    ↘
    -0.45
    么
    -0.45
     a
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.97
    oredCriteria
    0.90
     الحره
    0.84
     Мексичка
    0.83
    ंदीखरीदारी
    0.81
     esternos
    0.79
    ſelf
    0.76
    RTSC
    0.75
    IndentedString
    0.74
    Хьажоргаш
    0.73
    Act Density 0.047%

    No Known Activations