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

    Neuronpedia

    INDEX
    Explanations

    instances of social interactions involving companionship and shared activities

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

    collaboration or agreement

    np_acts-logits-general · gemini-2.0-flash

    acting together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    answers
    -0.56
     réponse
    -0.55
    responses
    -0.52
     responses
    -0.50
    responder
    -0.49
    AtIndex
    -0.48
    躇
    -0.48
     resposta
    -0.48
    kepada
    -0.47
     Responses
    -0.47
    POSITIVE LOGITS
     together
    1.10
     jointly
    1.04
     each
    1.01
     discussed
    0.99
     discussing
    0.99
     juntos
    0.98
     collectively
    0.97
    Together
    0.91
     agreed
    0.91
     nhau
    0.90
    Act Density 0.295%

    No Known Activations