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

    Neuronpedia

    INDEX
    Explanations

    references to military actions and international conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ιÏĩ
    -0.16
     MSP
    -0.15
    .Expressions
    -0.15
    Artifact
    -0.14
    INUX
    -0.14
     Armor
    -0.14
     uniform
    -0.14
     Antarctica
    -0.14
    EMS
    -0.13
    泡
    -0.13
    POSITIVE LOGITS
     strikes
    0.34
     bombing
    0.32
    bomb
    0.32
     airstrikes
    0.31
     strike
    0.31
     airst
    0.28
     bombard
    0.27
     Strikes
    0.27
     targeting
    0.27
     bombs
    0.27
    Act Density 0.083%

    No Known Activations