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

    Neuronpedia

    INDEX
    Explanations

    elements indicating emotional or relational dynamics, particularly struggles and support within families

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

    Possessive pronouns followed by a family member

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns followed by family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.75
    principalTable
    -0.63
    ILayout
    -0.61
     JAXBElement
    -0.61
     courants
    -0.60
     traités
    -0.60
    timewa
    -0.59
     بیشتری
    -0.58
    pendenti
    -0.57
     honneur
    -0.57
    POSITIVE LOGITS
     increasingly
    1.04
     equally
    0.93
     bele
    0.90
     weary
    0.89
     rapidly
    0.85
     heavily
    0.84
     bewildered
    0.84
     highly
    0.83
     usually
    0.82
     fiercely
    0.81
    Act Density 0.383%

    No Known Activations