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

    Neuronpedia

    INDEX
    Explanations

    references to illegal activities or objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of illegal activities or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oleon
    -0.80
    nil
    -0.77
    ĸļ
    -0.75
    addons
    -0.75
    ieu
    -0.74
    antics
    -0.73
    roth
    -0.73
    vation
    -0.72
    alg
    -0.70
    erer
    -0.70
    POSITIVE LOGITS
     detained
    0.85
     downloaded
    0.82
     downloading
    0.81
     illegally
    0.81
     copied
    0.78
     infringing
    0.78
     intercepted
    0.77
     planted
    0.75
     parked
    0.74
     infring
    0.72
    Act Density 0.013%

    No Known Activations