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

    Neuronpedia

    INDEX
    Explanations

    identifiers of personal roles and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millionaires
    -0.43
     例
    -0.42
    有名
    -0.41
     jopa
    -0.41
     famous
    -0.40
     importante
    -0.40
    Famous
    -0.40
    +#+#
    -0.40
     criticised
    -0.40
    famous
    -0.39
    POSITIVE LOGITS
     currently
    0.79
     passionate
    0.79
     attualmente
    0.78
    currently
    0.75
     Currently
    0.75
    Currently
    0.74
     passions
    0.72
     graag
    0.70
     loves
    0.69
     passione
    0.68
    Act Density 0.342%

    No Known Activations