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

    Neuronpedia

    INDEX
    Explanations

    negative affirmations or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chargés
    -0.47
    umą
    -0.43
     guerres
    -0.42
    mew
    -0.42
    нале
    -0.40
    níků
    -0.40
     peuples
    -0.40
     popoli
    -0.40
     nationaux
    -0.40
     souverain
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.94
     مرئيه
    0.85
     صوتيه
    0.83
     ostavi
    0.83
    UrlEncoded
    0.81
     betweenstory
    0.79
     referenties
    0.77
     الحره
    0.77
    expandindo
    0.76
    rungsseite
    0.75
    Act Density 0.254%

    No Known Activations