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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships involving variables and constants

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

    mathematical symbols and equations, particularly those involving Greek letters and mathematical notation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    This neuron detects mathematical expressions and equations, particularly focusing on equality symbols and mathematical conclusions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     estekak
    -0.75
    ⤹
    -0.73
    Хьажоргаш
    -0.68
     فريبيس
    -0.66
     Exacts
    -0.65
     للمعارف
    -0.63
    原始内容存档于
    -0.63
    tvguidetime
    -0.63
     &___
    -0.63
    MemoryWarning
    -0.62
    POSITIVE LOGITS
     therefore
    0.45
     hence
    0.45
     dermed
    0.41
     Gestión
    0.40
     ejus
    0.39
     emperador
    0.38
     bestemt
    0.38
    Therefore
    0.37
     agrav
    0.37
     inmun
    0.37
    Act Density 0.340%

    No Known Activations