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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures and their actions

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

    by, with, between, of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     piemē
    -0.49
    warnai
    -0.47
     gravedad
    -0.45
     creș
    -0.44
     héroe
    -0.43
     izquier
    -0.43
     Anbau
    -0.42
     península
    -0.42
     prioridad
    -0.42
     Erwä
    -0.42
    POSITIVE LOGITS
     neur
    0.53
     חיצוניים
    0.50
     tac
    0.48
    NewLabel
    0.47
     mule
    0.47
    tagHelperRunner
    0.46
     Maori
    0.45
     AssemblyCompany
    0.45
     Leak
    0.45
    ukone
    0.44
    Act Density 0.070%

    No Known Activations