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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal requirements and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote actions or conditions specified by a particular entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.78
    earchers
    -0.77
    olit
    -0.76
    ival
    -0.76
    iva
    -0.75
    ool
    -0.75
    heast
    -0.72
    ussion
    -0.71
    icip
    -0.70
    uality
    -0.70
    POSITIVE LOGITS
     virtue
    0.99
    laws
    0.92
     successive
    0.78
    products
    0.76
     employers
    0.71
     those
    0.71
     incumb
    0.70
     statute
    0.69
     refugees
    0.68
     outsiders
    0.68
    Act Density 0.110%

    No Known Activations