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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash

    The neuron is triggered by reporting or stance‐marking verbs that attribute opinions or claims (e.g. “say,” “argue,” “consider,” “claim”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to legislative actions and unionization efforts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Amy
    -0.08
    .Static
    -0.07
     UIStoryboard
    -0.07
     Cartesian
    -0.07
    たく
    -0.07
    Ka
    -0.07
     Townsend
    -0.07
     attorney
    -0.07
    spark
    -0.07
    pdf
    -0.06
    POSITIVE LOGITS
     delic
    0.07
     prin
    0.06
     σει
    0.06
     escol
    0.06
    atura
    0.06
     horas
    0.06
     ciudad
    0.06
    _dest
    0.06
     ///↵
    0.06
     bist
    0.06
    Act Density 0.048%

    No Known Activations