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

    Neuronpedia

    INDEX
    Explanations

    references to protests or demonstrations occurring outside various locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¦ãĤ¹
    -0.81
    idae
    -0.73
    ãĥĥãĥī
    -0.72
     inval
    -0.72
    ãĥij
    -0.70
     teasp
    -0.70
    itialized
    -0.69
    utan
    -0.66
     hybrids
    -0.66
    LESS
    -0.65
    POSITIVE LOGITS
     courthouse
    1.03
     Starbucks
    0.94
     parliament
    0.89
     offices
    0.88
     Planned
    0.86
     Costco
    0.84
     doors
    0.84
     Embassy
    0.83
     gates
    0.82
     Parliament
    0.81
    Act Density 0.086%

    No Known Activations