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

    Neuronpedia

    INDEX
    Explanations

    phrases related to protests and opposition against various proposals or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prohibited
    -0.16
    sounds
    -0.14
    .examples
    -0.14
    iams
    -0.14
    inand
    -0.13
     probl
    -0.13
    ux
    -0.13
    ason
    -0.13
    OLE
    -0.13
     lore
    -0.13
    POSITIVE LOGITS
     decision
    0.28
     perceived
    0.27
     decisions
    0.25
     treatment
    0.24
     Decision
    0.23
     lack
    0.23
     recent
    0.23
    decision
    0.22
     plan
    0.21
     Treatment
    0.21
    Act Density 0.243%

    No Known Activations