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

    Neuronpedia

    INDEX
    Explanations

    legal and political terms related to government actions and agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and governmental processes or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĦ
    -0.65
    à¨
    -0.65
    uct
    -0.61
    pron
    -0.59
    ãĥĥãĤ¯
    -0.58
    omorph
    -0.56
    ãĥ¼ãĥĨãĤ£
    -0.56
    osc
    -0.56
     fict
    -0.55
     experien
    -0.55
    POSITIVE LOGITS
     threatens
    0.94
     underscores
    0.91
     violates
    0.91
     undermines
    0.89
     suggests
    0.88
     could
    0.85
     Read
    0.85
     Copyright
    0.84
     will
    0.83
     prompted
    0.83
    Act Density 0.707%

    No Known Activations