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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political statements and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .UIManager
    -0.15
    etu
    -0.15
     Credits
    -0.15
    Credits
    -0.15
    undle
    -0.15
    à¸
    -0.14
    udeau
    -0.14
    ÑĢеменно
    -0.14
    ammad
    -0.14
     infix
    -0.14
    POSITIVE LOGITS
     Foreign
    0.25
     FOREIGN
    0.25
     foreign
    0.24
     CFR
    0.24
    Foreign
    0.23
    foreign
    0.22
     Kiss
    0.21
     Security
    0.20
    CF
    0.20
     security
    0.18
    Act Density 0.056%

    No Known Activations