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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash

    structured arguments and formal writing characteristics in essays.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron selectively activates on words that appear at the start of sentences or document sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Dll
    -0.07
     downtown
    -0.07
     Going
    -0.06
     slain
    -0.06
     journalist
    -0.06
     Walt
    -0.06
     broadcaster
    -0.06
    Thread
    -0.06
    unge
    -0.06
     wood
    -0.06
    POSITIVE LOGITS
    itori
    0.07
     thereby
    0.07
     попыт
    0.06
    ijd
    0.06
    rowave
    0.06
    MEDIA
    0.06
    -if
    0.06
    knife
    0.06
    这样
    0.06
     momentos
    0.06
    Act Density 0.071%

    No Known Activations