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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating doubts or contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    past tense negative contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.46
     onders
    -0.41
     ainfi
    -0.40
     spørs
    -0.40
    ectious
    -0.40
    躇
    -0.40
    iffance
    -0.39
    makin
    -0.39
     plufieurs
    -0.39
     privées
    -0.39
    POSITIVE LOGITS
     Fiction
    0.52
     fiction
    0.48
    GEBURTSDATUM
    0.45
    énario
    0.45
    Fiction
    0.45
     fictional
    0.45
    MigrationBuilder
    0.45
    
    0.44
     stories
    0.43
     story
    0.42
    Act Density 0.126%

    No Known Activations