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

    Neuronpedia

    INDEX
    Explanations

    references to penalties or fines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erial
    -0.81
    rina
    -0.78
    atters
    -0.77
    ergy
    -0.74
    ullivan
    -0.73
    bits
    -0.73
    ãĤ¤ãĥĪ
    -0.72
    growth
    -0.72
    oscope
    -0.72
     Remastered
    -0.72
    POSITIVE LOGITS
     penalties
    1.20
     levied
    1.13
     imposed
    1.10
     penalty
    1.08
     sanction
    0.99
     incurred
    0.95
     inflicted
    0.92
     punishments
    0.88
     fines
    0.87
     punishment
    0.87
    Act Density 0.010%

    No Known Activations