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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political tensions and security issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    plex
    -0.15
    woord
    -0.15
    æĹ¥æľ¬
    -0.15
    ãĢģæĹ¥æľ¬
    -0.15
    éĢ¸
    -0.15
    .Automation
    -0.15
    ock
    -0.15
    peon
    -0.14
     omas
    -0.14
    POSITIVE LOGITS
     Diet
    0.35
     Abe
    0.26
     diet
    0.23
     Dia
    0.21
     Cabinet
    0.20
     Liberal
    0.19
    Dia
    0.18
    diet
    0.18
     MET
    0.18
    Comfort
    0.18
    Act Density 0.046%

    No Known Activations