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

    Neuronpedia

    INDEX
    Explanations

    terms related to separating or distinguishing between different elements or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    separate the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.56
    دانشنامهٔ
    -0.52
     مرئيه
    -0.52
    хьтан
    -0.51
    ymce
    -0.47
    قایناق‌لار
    -0.47
    原始内容存档于
    -0.46
    Referências
    -0.45
    UserScript
    -0.45
    حوالہ
    -0.44
    POSITIVE LOGITS
     separating
    1.42
     separation
    1.34
     Separation
    1.32
     Separ
    1.27
     separates
    1.24
     separated
    1.23
     separar
    1.20
    separation
    1.20
     separa
    1.20
    Separation
    1.20
    Act Density 0.047%

    No Known Activations