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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons or relationships in data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.85
    Geplaatst
    -0.74
    tvguidetime
    -0.72
    Viited
    -0.72
    ագրություններ
    -0.69
     متعلقه
    -0.66
    Espèce
    -0.65
    uvre
    -0.61
     ligiloj
    -0.61
    istoitu
    -0.60
    POSITIVE LOGITS
     the
    0.60
    setVerticalGroup
    0.59
     her
    0.54
     a
    0.52
    copyWith
    0.50
     these
    0.47
    transQ
    0.47
     an
    0.46
     our
    0.46
    ()));
    0.46
    Act Density 0.274%

    No Known Activations