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

    Neuronpedia

    INDEX
    Explanations

    phrases related to infringement or violation

    oai_token-act-pair · gpt-3.5-turbo

    instances of patent infringement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.81
    agan
    -0.68
    brace
    -0.64
    tu
    -0.63
    roth
    -0.62
    hall
    -0.60
    adi
    -0.60
    =-=-=-=-=-=-=-=-
    -0.60
    oses
    -0.60
    bern
    -0.60
    POSITIVE LOGITS
     infring
    1.30
     infringement
    1.23
     infringing
    1.05
    yrights
    0.80
    emonium
    0.78
     proble
    0.70
    terness
    0.70
     counterfe
    0.69
     inhibition
    0.69
    rodu
    0.68
    Act Density 0.007%

    No Known Activations