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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions related to electronic components and circuits

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
      
    -0.54
     “
    -0.50
    gabe
    -0.50
    <eos>
    -0.48
       
    -0.46
     "
    -0.45
     h
    -0.45
    gaben
    -0.42
    ’
    -0.42
    ↵
    -0.42
    POSITIVE LOGITS
     autorytatywna
    1.05
    abestanden
    1.00
     ―――――
    0.99
    bewerken
    0.97
    RegressionTest
    0.97
    GEBURTSDATUM
    0.97
    новништво
    0.95
     ſche
    0.92
    IsMutable
    0.92
    SharedCtor
    0.91
    Act Density 0.447%

    No Known Activations