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

    Neuronpedia

    INDEX
    Explanations

    references to indoctrination and manipulation of beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoField
    -0.51
     Meksiku
    -0.49
    rungsseite
    -0.46
    Билгалдахарш
    -0.46
     ब्रेकडाउन
    -0.46
    insics
    -0.46
    offsetof
    -0.44
    modelBuilder
    -0.44
    balleur
    -0.43
    Controllo
    -0.43
    POSITIVE LOGITS
     impression
    0.53
     propaganda
    0.50
     impressions
    0.49
    impression
    0.48
     indoctr
    0.48
     insegna
    0.47
     Propaganda
    0.47
     vermittelt
    0.47
     messaggio
    0.46
     InputDecoration
    0.46
    Act Density 0.310%

    No Known Activations