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

    Neuronpedia

    INDEX
    Explanations

    terms related to consumer protection and related services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.79
     pse
    -0.71
    ccording
    -0.70
    orate
    -0.70
     mathemat
    -0.68
     proble
    -0.67
     constitu
    -0.67
     orth
    -0.66
    ernels
    -0.65
    earance
    -0.65
    POSITIVE LOGITS
     Manager
    0.86
     Aid
    0.85
     Tracker
    0.80
    Sense
    0.78
     Breaker
    0.78
    Runner
    0.78
     Lobby
    0.77
    Corp
    0.77
     Leader
    0.76
     Advisor
    0.76
    Act Density 0.067%

    No Known Activations