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

    Neuronpedia

    INDEX
    Explanations

    references to data structures in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorité
    -0.59
    -0.53
     avoient
    -0.53
     jugement
    -0.50
     Scalars
    -0.48
     المعيارى
    -0.48
    Diwedd
    -0.47
    retudo
    -0.47
     विश्वसनीयता
    -0.47
    ніципалі
    -0.47
    POSITIVE LOGITS
    ds
    1.38
     DS
    1.32
    DS
    1.30
     ds
    1.29
     Ds
    0.93
    Ds
    0.90
    ads
    0.75
    ADS
    0.73
     emission
    0.70
    DSA
    0.65
    Act Density 0.333%

    No Known Activations