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

    Neuronpedia

    INDEX
    Explanations

    instances of legal charges and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concentrating
    -0.41
     Concentr
    -0.37
     crime
    -0.36
     crimes
    -0.35
     concentrate
    -0.35
    Concentr
    -0.32
     accidents
    -0.32
     successful
    -0.31
     obscene
    -0.31
     guns
    -0.31
    POSITIVE LOGITS
     charge
    0.83
     charges
    0.75
    charge
    0.73
     CHARGE
    0.70
     Charges
    0.70
    Charge
    0.69
     Charge
    0.68
     Journal
    0.67
    $_['
    0.67
    Charges
    0.66
    Act Density 0.098%

    No Known Activations