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

    Neuronpedia

    INDEX
    Explanations

    expressing opinions/arguments

    np_max-act · gemini-2.0-flash

    discussions about economic hardship and labor conditions.

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

    The neuron activates on evaluative or opinion-laden modifiers and adjectives (e.g. “incredibly,” “important,” “public,” “bad”) that signal subjective commentary.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -links
    -0.07
    id
    -0.06
    Quit
    -0.06
    -letter
    -0.06
    .enumer
    -0.06
    775
    -0.06
     Ward
    -0.06
     flew
    -0.06
    _SELECTION
    -0.06
     случаев
    -0.06
    POSITIVE LOGITS
     totalPrice
    0.06
    _hist
    0.06
    aría
    0.06
    ریق
    0.06
    linkplain
    0.06
     činnost
    0.06
    љ
    0.06
    ulta
    0.06
    Categoria
    0.06
    _rgb
    0.06
    Act Density 0.056%

    No Known Activations