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

    Neuronpedia

    INDEX
    Explanations

    assertive statements about truths or verifiable information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andra
    -0.55
    خرى
    -0.50
    kring
    -0.50
     weer
    -0.49
     wieder
    -0.49
    mpe
    -0.48
     mélanger
    -0.48
    wnicy
    -0.47
    рант
    -0.47
     dragen
    -0.47
    POSITIVE LOGITS
     even
    1.07
     sogar
    1.02
     actually
    0.92
    Bahkan
    0.91
     Bahkan
    0.91
     zelfs
    0.90
    むしろ
    0.85
     anzi
    0.84
     Incluso
    0.83
    Actually
    0.80
    Act Density 0.153%

    No Known Activations