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

    Neuronpedia

    INDEX
    Explanations

    terms related to non-specific or non-standard classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imprimée
    -0.84
     ainfi
    -0.79
     duquel
    -0.76
    brainly
    -0.76
     vectorielle
    -0.75
     italienne
    -0.75
     Vikipedi
    -0.73
     particulières
    -0.73
     scuro
    -0.72
     ulang
    -0.70
    POSITIVE LOGITS
     non
    1.37
     Non
    1.34
    Non
    1.26
     NON
    1.26
    non
    1.17
    非
    1.12
     Nong
    1.06
    NON
    1.04
     nong
    1.00
     nons
    0.99
    Act Density 0.114%

    No Known Activations