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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and action

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     frontman
    -0.60
    ãĥĦ
    -0.52
    surprisingly
    -0.51
    ¶
    -0.51
    tips
    -0.50
    ashington
    -0.49
     ®
    -0.49
     "[
    -0.48
    ]),
    -0.47
    ielding
    -0.47
    POSITIVE LOGITS
     ..."
    1.37
     âĢ¦"
    1.33
    )."
    1.26
    ..."
    1.15
    .")
    1.10
    .""
    1.10
    !"
    1.08
    .'"
    1.07
    âĢ¦"
    1.07
    âĢ¦."
    1.02
    Act Density 1.970%

    No Known Activations