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

    Neuronpedia

    INDEX
    Explanations

    instances where something is being compelled or required

    oai_token-act-pair · gpt-3.5-turbo

    instances of coercion or compulsion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.79
    heimer
    -0.74
     Purpose
    -0.70
     Excellence
    -0.68
    ahu
    -0.66
    nam
    -0.64
     Blessed
    -0.63
    ihar
    -0.63
    yss
    -0.63
     iT
    -0.63
    POSITIVE LOGITS
     forcing
    0.76
     overtime
    0.73
     cooker
    0.73
     force
    0.72
     forced
    0.72
     exerted
    0.72
    ansson
    0.70
     overpowered
    0.69
     unbeliev
    0.67
     coer
    0.66
    Act Density 0.017%

    No Known Activations