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

    Neuronpedia

    INDEX
    Explanations

    references to social or political movements

    oai_token-act-pair · gpt-3.5-turbo

    references to social or political movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oba
    -0.76
     dams
    -0.73
    ãĥ¯ãĥ³
    -0.69
     golf
    -0.68
    nect
    -0.65
    itor
    -0.63
    æĢ
    -0.62
     nutrit
    -0.62
     vill
    -0.62
    bats
    -0.62
    POSITIVE LOGITS
    naire
    0.89
    ivism
    0.82
    ĸļ
    0.80
    matic
    0.79
    naires
    0.75
     movement
    0.73
    ACY
    0.72
    atics
    0.72
     anarchism
    0.71
    geist
    0.71
    Act Density 0.028%

    No Known Activations