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

    Neuronpedia

    INDEX
    Explanations

    specific legal charges or accusations

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases related to legal charges and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.74
    natureconservancy
    -0.67
     Nobel
    -0.66
     Runes
    -0.66
    pse
    -0.64
    istically
    -0.64
    Reviewer
    -0.63
     obser
    -0.63
    Tokens
    -0.63
    tnc
    -0.63
    POSITIVE LOGITS
     felony
    1.14
     punishable
    1.10
     offences
    1.09
     indict
    1.07
     offenses
    1.06
     misdemeanor
    1.05
     misdem
    1.05
     aggravated
    1.00
     alleging
    0.99
     indictment
    0.97
    Act Density 0.052%

    No Known Activations