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

    Neuronpedia

    INDEX
    Explanations

    mentions of social or political movements

    oai_token-act-pair · gpt-3.5-turbo

    references to social movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oba
    -0.73
     dams
    -0.70
    ãĥ¯ãĥ³
    -0.70
    nect
    -0.65
     golf
    -0.65
     saline
    -0.63
    ãĤ¨ãĥ«
    -0.63
     nutrit
    -0.62
    itor
    -0.62
    æĢ
    -0.61
    POSITIVE LOGITS
    naire
    0.93
    atics
    0.84
    matic
    0.84
    naires
    0.84
     movement
    0.80
    ĸļ
    0.79
    ivism
    0.78
    ACY
    0.75
     movements
    0.73
    arily
    0.71
    Act Density 0.025%

    No Known Activations