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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the use of force, especially in a coercive or physical manner

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "force" in various contexts, particularly related to its application in legal or military situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    algia
    -0.91
    STER
    -0.78
    vironment
    -0.77
     Hop
    -0.77
    alam
    -0.74
    Accessory
    -0.72
    DERR
    -0.71
    roma
    -0.71
    ebted
    -0.71
    lr
    -0.70
    POSITIVE LOGITS
     maj
    1.05
     force
    0.96
     exerted
    0.86
     Awakens
    0.85
    ivot
    0.84
     multiplier
    0.83
     diseng
    0.82
    fully
    0.79
    fulness
    0.78
    bang
    0.77
    Act Density 0.026%

    No Known Activations