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

    Neuronpedia

    INDEX
    Explanations

    references to conversations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ništvo
    -0.77
    cích
    -0.75
    SharedDtor
    -0.75
    Portail
    -0.69
    órios
    -0.69
     Glou
    -0.68
    tır
    -0.68
    SizeF
    -0.68
     Brut
    -0.66
    ]';
    -0.65
    POSITIVE LOGITS
     Conversation
    1.28
    Conversation
    1.23
     Conversations
    1.09
     Convers
    1.02
     CONVERS
    1.02
     conversation
    1.00
    conversation
    0.92
     conversational
    0.87
    Conversations
    0.87
     conversations
    0.84
    Act Density 0.004%

    No Known Activations