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

    Neuronpedia

    INDEX
    Explanations

    beginning of sentences or sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.47
     brasileño
    -0.45
     mío
    -0.43
     múltiple
    -0.43
     Administrativna
    -0.41
     temprano
    -0.40
     Jehová
    -0.40
     Constitucional
    -0.39
     Contactez
    -0.38
     vôtre
    -0.38
    POSITIVE LOGITS
     FontWeight
    0.88
    ⪜
    0.78
    <unused42>
    0.77
    <unused14>
    0.77
    <unused79>
    0.77
    <unused74>
    0.77
    <unused8>
    0.77
    <unused41>
    0.77
    <unused28>
    0.77
    [@BOS@]
    0.77
    Act Density 0.382%

    No Known Activations