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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and military contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hastings
    -0.15
    ł
    -0.15
     instances
    -0.14
    оÑģÑĮ
    -0.14
    ίο
    -0.14
    landa
    -0.14
    lien
    -0.14
    ilename
    -0.14
    ritz
    -0.13
    gren
    -0.13
    POSITIVE LOGITS
    etur
    0.19
     Scenario
    0.16
    _fps
    0.15
    iquer
    0.15
    Scenario
    0.14
    erra
    0.14
     reader
    0.14
    ception
    0.14
    füh
    0.14
     tonight
    0.13
    Act Density 0.315%

    No Known Activations