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

    Neuronpedia

    INDEX
    Explanations

    instances where people express opinions or preferences about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.85
    Autoritní
    -0.77
     виправивши
    -0.74
     termica
    -0.73
     TextAppearance
    -0.73
     tartalomajánló
    -0.72
     MaterialApp
    -0.69
     scattata
    -0.69
     leçons
    -0.68
     vœux
    -0.68
    POSITIVE LOGITS
     even
    0.86
     some
    0.80
    Some
    0.74
     sometimes
    0.74
    有些人
    0.73
     incluso
    0.72
     Some
    0.72
    even
    0.71
     may
    0.71
     manche
    0.70
    Act Density 0.262%

    No Known Activations