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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being forced to do something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    vironment
    -0.93
    mbuds
    -0.87
    ership
    -0.81
    orkshire
    -0.74
    issance
    -0.74
    rou
    -0.71
    erb
    -0.70
    ahu
    -0.70
    namese
    -0.69
    lain
    -0.69
    POSITIVE LOGITS
     maj
    0.85
     overtime
    0.84
    otom
    0.79
     cooker
    0.75
     laborers
    0.72
     imposition
    0.72
    untarily
    0.72
     displacement
    0.72
     wedge
    0.71
     concessions
    0.70
    Act Density 0.611%

    No Known Activations