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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and parental involvement

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

    preceding "parents" or "parent"

    np_acts-logits-general · gemini-2.0-flash

    parents and parent consent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ĝ
    -0.41
     AGENCY
    -0.41
    ritter
    -0.38
    quias
    -0.38
    izzi
    -0.38
     rookies
    -0.38
    InstanceState
    -0.37
     שוליים
    -0.37
    新人
    -0.37
    Kirby
    -0.37
    POSITIVE LOGITS
     parent
    3.19
     parents
    3.19
    parent
    2.79
     father
    2.71
     Parent
    2.70
     Parents
    2.68
     mother
    2.65
    parents
    2.57
    Parents
    2.56
    Parent
    2.55
    Act Density 0.477%

    No Known Activations