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

    Neuronpedia

    INDEX
    Explanations

    references to border control and enforcement activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dig
    -0.17
    Dig
    -0.15
     Rams
    -0.15
    dig
    -0.15
    _invoke
    -0.15
    undle
    -0.14
    ève
    -0.14
    á»ijng
    -0.13
     dig
    -0.13
    .escape
    -0.13
    POSITIVE LOGITS
     Border
    0.47
     border
    0.41
    Border
    0.39
     CB
    0.39
     BORDER
    0.37
     Customs
    0.37
     agents
    0.36
     Agents
    0.33
     agent
    0.33
    border
    0.31
    Act Density 0.014%

    No Known Activations