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

    Neuronpedia

    INDEX
    Explanations

    news articles about legal and political topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal actions or judicial decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.71
     Machina
    -0.65
    etheless
    -0.63
    gren
    -0.63
    iates
    -0.63
    gold
    -0.59
     obscurity
    -0.58
    utical
    -0.57
    lander
    -0.56
    being
    -0.56
    POSITIVE LOGITS
    ³³³³
    0.73
    Interested
    0.72
    ³³³³³³³³
    0.67
    neau
    0.66
    Amid
    0.65
    ³³³³³³³³³³³³³³³³
    0.64
    WASHINGTON
    0.63
    Specifically
    0.63
    æĪ¦
    0.63
    arta
    0.61
    Act Density 0.137%

    No Known Activations