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

    Neuronpedia

    INDEX
    Explanations

    names and references related to academic publications and studies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ball
    -0.47
     she
    -0.46
     Mag
    -0.44
     a
    -0.44
     m
    -0.42
     mag
    -0.42
    if
    -0.42
     
    -0.42
     Rock
    -0.42
    そうで
    -0.42
    POSITIVE LOGITS
    CodedInputStream
    1.00
     estimés
    0.93
    Geplaatst
    0.90
    IsMutable
    0.90
     referenties
    0.88
    出版年
    0.88
     ब्रेकडाउन
    0.86
    abestanden
    0.84
    Хьажоргаш
    0.82
    ValueStyle
    0.79
    Act Density 0.024%

    No Known Activations