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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of prohibition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '{@
    -0.56
    amaño
    -0.56
    berdayakan
    -0.56
    ämmer
    -0.54
     Partager
    -0.52
    Partager
    -0.51
    Enregistrer
    -0.51
    róleo
    -0.49
    Mə
    -0.49
    ambung
    -0.49
    POSITIVE LOGITS
    MigrationBuilder
    0.92
    Beware
    0.79
    Avoid
    0.78
    avoid
    0.78
     Beware
    0.77
    msgTypes
    0.74
     beware
    0.74
     avoid
    0.74
     Avoid
    0.73
     Caution
    0.72
    Act Density 0.155%

    No Known Activations