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

    Neuronpedia

    INDEX
    Explanations

    references to regulations or directives related to governance and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theid
    -0.17
     سÙĨت
    -0.14
    jas
    -0.14
    illas
    -0.14
    isodes
    -0.14
     åıĤ
    -0.13
    OTE
    -0.13
     Charm
    -0.13
    à¥ĩय
    -0.13
     اÙĦشر
    -0.13
    POSITIVE LOGITS
    iras
    0.17
     maz
    0.15
     Cage
    0.15
     New
    0.14
    μμα
    0.14
    nam
    0.14
    KA
    0.14
     Fir
    0.14
     Pie
    0.13
     do
    0.13
    Act Density 0.951%

    No Known Activations