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

    Neuronpedia

    INDEX
    Explanations

    code structures related to network or data communication protocols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <eos>
    -0.53
    тті
    -0.49
    werb
    -0.42
    lami
    -0.41
     .
    -0.40
    ane
    -0.40
     
    -0.40
    ila
    -0.38
     floor
    -0.38
     nume
    -0.37
    POSITIVE LOGITS
     myſelf
    1.01
     الحره
    0.97
     Monfieur
    0.87
    fromnode
    0.84
    Билгалдахарш
    0.84
    adaptiveStyles
    0.81
    ſelf
    0.81
     الدولى
    0.81
     itſelf
    0.81
     ſtate
    0.79
    Act Density 0.024%

    No Known Activations