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

    Neuronpedia

    INDEX
    Explanations

    references to scientific models and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     collaborateurs
    -0.28
     colleagues
    -0.26
    '
    -0.25
     de
    -0.25
    shadowOpacity
    -0.25
     collègues
    -0.24
    ब्द
    -0.23
     visual
    -0.23
     pilas
    -0.23
     palavras
    -0.23
    POSITIVE LOGITS
    principalColumn
    0.85
    <unused52>
    0.77
    <pad>
    0.77
    <unused79>
    0.76
    <unused68>
    0.76
    <unused28>
    0.76
    <unused3>
    0.76
    <unused14>
    0.76
    <unused8>
    0.76
    [@BOS@]
    0.76
    Act Density 1.432%

    No Known Activations