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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to penalties or disciplinary actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rouse
    -0.66
    /)
    -0.64
    them
    -0.62
    rium
    -0.60
     centers
    -0.57
     borne
    -0.56
     formations
    -0.56
     ze
    -0.56
     Merge
    -0.55
    bearing
    -0.55
    POSITIVE LOGITS
     aback
    0.91
     by
    0.87
     twice
    0.76
     criminally
    0.72
     yesterday
    0.71
     repeatedly
    0.71
     separately
    0.70
     unanimously
    0.69
    gewater
    0.69
    graded
    0.68
    Act Density 0.181%

    No Known Activations