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

    Neuronpedia

    INDEX
    Explanations

    references to written documentation or written agreements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Koss
    -0.64
     bağlantılar
    -0.64
     Argus
    -0.63
     errand
    -0.63
    UVWXYZ
    -0.62
     Samir
    -0.62
    ładka
    -0.61
     beginnetje
    -0.61
    homonymie
    -0.60
    Вопрос
    -0.60
    POSITIVE LOGITS
    CAPT
    0.63
    ]='\
    0.59
     entren
    0.58
    })`
    0.57
    IsContent
    0.56
     `;
    0.56
     Audiodateien
    0.55
    ized
    0.54
     wirk
    0.52
     الحره
    0.52
    Act Density 0.005%

    No Known Activations