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

    Neuronpedia

    INDEX
    Explanations

    instances where individuals are being subjected to something, potentially against their will

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "subjected" and related concepts indicating experiences of hardship or treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.65
    flies
    -0.65
     Islands
    -0.62
     Mush
    -0.61
    AGE
    -0.61
    assies
    -0.60
     Worldwide
    -0.60
     beans
    -0.59
     Berger
    -0.59
     Fargo
    -0.59
    POSITIVE LOGITS
    aton
    0.95
    ophile
    0.93
    etics
    0.91
    ĪĴ
    0.90
    hran
    0.90
    stasy
    0.83
    ħĭ
    0.83
    yssey
    0.81
    urst
    0.81
    itive
    0.80
    Act Density 0.033%

    No Known Activations