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

    Neuronpedia

    INDEX
    Explanations

    references to criminals and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.68
    Gön
    -0.63
    TagMode
    -0.63
    περ
    -0.62
    醐
    -0.60
    सन्दर्भ
    -0.58
     referenties
    -0.58
     Lokales
    -0.58
    ismet
    -0.56
    EDEFAULT
    -0.55
    POSITIVE LOGITS
     justice
    0.92
     perpetrators
    0.85
     accountability
    0.81
     criminal
    0.80
     accountable
    0.72
     prosecutions
    0.70
     Accountability
    0.69
    justice
    0.69
     culprits
    0.67
     justicia
    0.67
    Act Density 0.212%

    No Known Activations