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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating coercion or compulsion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "force" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOW
    -0.75
    Hop
    -0.68
    umer
    -0.68
    vironment
    -0.68
    rou
    -0.68
     Emin
    -0.67
    apest
    -0.67
    ahu
    -0.67
    ergy
    -0.66
    gres
    -0.66
    POSITIVE LOGITS
     overtime
    0.80
    cible
    0.79
     induction
    0.77
    otom
    0.77
     compel
    0.74
     exerted
    0.74
     laborers
    0.73
     force
    0.72
     Awakens
    0.71
     arbitration
    0.70
    Act Density 0.030%

    No Known Activations