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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is being coerced or compelled to do something against their will

    oai_token-act-pair · gpt-3.5-turbo

    instances of coercion or being compelled to do something against one's will

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ight
    -0.77
    ership
    -0.73
     Excellence
    -0.73
    ouf
    -0.72
    ergy
    -0.70
    itect
    -0.69
    umer
    -0.66
    NOW
    -0.65
    thus
    -0.64
    itz
    -0.64
    POSITIVE LOGITS
     overtime
    0.81
     laborers
    0.81
     labou
    0.80
     pneum
    0.80
     forced
    0.77
    cible
    0.75
    ierrez
    0.75
    ãĥ¼ãĤ¯
    0.72
     choked
    0.69
    untarily
    0.69
    Act Density 0.016%

    No Known Activations