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

    Neuronpedia

    INDEX
    Explanations

    words related to organized public displays or protests

    oai_token-act-pair · gpt-3.5-turbo

    references to demonstrations or protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saline
    -0.95
    erenn
    -0.79
    laus
    -0.77
    oho
    -0.73
    missions
    -0.69
    mins
    -0.64
    bourne
    -0.62
    olly
    -0.61
    sm
    -0.61
    bc
    -0.61
    POSITIVE LOGITS
     demonstration
    1.25
     demonstrations
    0.99
     demonstrating
    0.88
    stration
    0.83
     glim
    0.81
     demonstrators
    0.79
     demonstr
    0.79
     GOODMAN
    0.76
    imony
    0.74
     Demon
    0.73
    Act Density 0.008%

    No Known Activations