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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical context and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     humanas
    -0.45
     vieta
    -0.44
     igjen
    -0.42
    stęp
    -0.42
    gesetzt
    -0.41
     again
    -0.41
    tahui
    -0.41
    varer
    -0.40
     сожалению
    -0.40
    idad
    -0.40
    POSITIVE LOGITS
     hitherto
    0.97
     lenker
    0.94
     heretofore
    0.92
     previously
    0.89
     traditionally
    0.85
    MigrationBuilder
    0.78
     Traditionally
    0.78
    previously
    0.76
     Previously
    0.76
     formerly
    0.75
    Act Density 0.544%

    No Known Activations