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

    Neuronpedia

    INDEX
    Explanations

    instances where specific actions or choices were made and their justifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.62
    ChildScrollView
    -0.60
    ymce
    -0.59
    setVerticalGroup
    -0.59
    IBU
    -0.55
    moiselle
    -0.54
    GLenum
    -0.54
    wäh
    -0.54
    ukone
    -0.54
    rzost
    -0.51
    POSITIVE LOGITS
     because
    1.14
    because
    0.95
    Because
    0.85
     karena
    0.85
     fordi
    0.84
     Because
    0.83
     omdat
    0.82
     porque
    0.81
     BECAUSE
    0.80
     perché
    0.79
    Act Density 0.257%

    No Known Activations