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

    Neuronpedia

    INDEX
    Explanations

    phrases related to coercion and pressure

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    vironment
    -0.89
    obyl
    -0.82
    sterdam
    -0.80
    mbuds
    -0.80
    nam
    -0.80
    namese
    -0.79
    çĦ
    -0.74
    ership
    -0.74
    nect
    -0.69
    said
    -0.68
    POSITIVE LOGITS
     exerted
    1.07
     cooker
    1.04
     wedge
    0.86
     compel
    0.82
     pressuring
    0.78
     harder
    0.77
     compulsion
    0.77
     levers
    0.74
     pressure
    0.74
     pedal
    0.74
    Act Density 2.286%

    No Known Activations