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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "force" and variations related to coercion or compulsion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roidered
    -0.81
     Venedig
    -0.80
    derry
    -0.80
    ươi
    -0.79
     fær
    -0.79
     universitario
    -0.79
     olímp
    -0.78
    خواندن
    -0.78
     Wann
    -0.78
     regata
    -0.78
    POSITIVE LOGITS
     Force
    1.35
     Forces
    1.31
     force
    1.31
    FORCE
    1.25
     FORCE
    1.25
     forces
    1.25
    Force
    1.22
    force
    1.21
    forces
    1.17
    Forces
    1.11
    Act Density 0.066%

    No Known Activations