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

    Neuronpedia

    INDEX
    Explanations

    names and family relationships in a context of remembrance or obituaries

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

    Tokens occurring immediately before commas and periods

    np_acts-logits-general · gemini-2.0-flash

    family relationships and life events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.59
     дописавши
    -0.56
    $'
    -0.55
    Rather
    -0.52
     *__
    -0.52
    rimin
    -0.51
     relev
    -0.51
    )$-
    -0.50
    $-
    -0.50
    vellous
    -0.49
    POSITIVE LOGITS
     predeceased
    1.08
    deceased
    0.89
     deceased
    0.86
     residing
    0.77
     married
    0.75
     fiancé
    0.74
     husband
    0.73
     daughters
    0.73
     née
    0.72
     granddaughter
    0.72
    Act Density 0.057%

    No Known Activations