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

    Neuronpedia

    INDEX
    Explanations

    exact numerical values and percentages related to statistical results in scientific research

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    /
    -0.44
    جع
    -0.43
     pro
    -0.43
     n
    -0.42
    -
    -0.41
    <eos>
    -0.39
     
    -0.39
    i
    -0.39
    מוש
    -0.38
     komen
    -0.37
    POSITIVE LOGITS
     Monfieur
    0.98
     Efq
    0.94
     myſelf
    0.94
     itſelf
    0.89
     Jefus
    0.83
     purpoſe
    0.82
    ^(@)
    0.81
     Houſe
    0.81
     Shakspeare
    0.81
     themſelves
    0.80
    Act Density 0.017%

    No Known Activations