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

    Neuronpedia

    INDEX
    Explanations

    references to financial penalties and fines in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.40
    brtc
    -0.38
    setArguments
    -0.36
    DrawerToggle
    -0.35
    ClientSize
    -0.34
     negotiations
    -0.34
     vitt
    -0.34
     stabilization
    -0.34
    ReLU
    -0.33
     sécur
    -0.33
    POSITIVE LOGITS
     fines
    0.92
     penalty
    0.88
     punishment
    0.88
     Penalty
    0.86
     penalties
    0.86
     punishments
    0.85
     fined
    0.84
     Punishment
    0.81
     Fines
    0.79
    Penalty
    0.77
    Act Density 0.427%

    No Known Activations