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

    Neuronpedia

    INDEX
    Explanations

    terms related to illegal activities and legal charges

    oai_token-act-pair · gpt-3.5-turbo

    references to legal charges or criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hordes
    -0.76
    scenes
    -0.74
    igans
    -0.69
    sheets
    -0.68
     ants
    -0.68
    easy
    -0.68
     alot
    -0.67
     amazing
    -0.67
    flies
    -0.66
     awfully
    -0.66
    POSITIVE LOGITS
     lawful
    0.90
    versive
    0.89
     licensee
    0.88
     valid
    0.85
     violation
    0.84
     prohibited
    0.84
     permissible
    0.82
     bona
    0.80
     dwelling
    0.79
     person
    0.79
    Act Density 0.266%

    No Known Activations