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

    Neuronpedia

    INDEX
    Explanations

    references to social support and accessibility issues

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

    indigent or destitute people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ousness
    -0.41
    ‍♀
    -0.40
     '\\;'
    -0.40
     infiniti
    -0.39
    地在
    -0.38
    ſt
    -0.37
     шла
    -0.36
     Draws
    -0.36
     MRS
    -0.35
    anjang
    -0.35
    POSITIVE LOGITS
     poorest
    0.60
    貧
    0.55
     poorer
    0.55
     destitute
    0.52
    贫
    0.50
     equitable
    0.50
     indigent
    0.49
     homeless
    0.49
     poverty
    0.48
     charitable
    0.47
    Act Density 0.070%

    No Known Activations