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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific data, measurements, or results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ↵
    -0.48
     '
    -0.46
    <eos>
    -0.46
      
    -0.45
    dą
    -0.42
     «
    -0.42
    Bit
    -0.41
    2
    -0.41
     ma
    -0.40
     
    -0.40
    POSITIVE LOGITS
     myſelf
    0.99
    RegressionTest
    0.97
     raiſ
    0.93
     '\\;'
    0.92
     itſelf
    0.91
     ―――――
    0.89
    addPreferredGap
    0.88
    ^(@)
    0.87
     ſeveral
    0.87
     themſelves
    0.86
    Act Density 0.957%

    No Known Activations