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

    Neuronpedia

    INDEX
    Explanations

    actions taken by groups of people in response to events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to public protests or collective actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.81
    ainment
    -0.72
    hin
    -0.66
    odan
    -0.64
     matured
    -0.63
    nown
    -0.63
    Prosecut
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    ulhu
    -0.61
    division
    -0.60
    POSITIVE LOGITS
     clam
    1.01
     petitions
    0.97
     boycot
    0.91
     ballots
    0.91
     selfies
    0.89
     candles
    0.87
     applaud
    0.85
     boycott
    0.85
     chants
    0.83
     queues
    0.81
    Act Density 0.454%

    No Known Activations