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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to gender-based violence and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.81
     Devi
    -0.71
    acci
    -0.70
    olars
    -0.69
     Dino
    -0.66
     Krypt
    -0.66
    answered
    -0.64
    ©¶æ¥µ
    -0.63
     Samurai
    -0.61
    athered
    -0.61
    POSITIVE LOGITS
     knowingly
    1.25
     materially
    1.13
     willfully
    1.10
     unlawfully
    1.07
    :(
    1.04
     unlawful
    1.00
     wil
    0.99
     willful
    0.98
     intentionally
    0.96
     reck
    0.95
    Act Density 0.280%

    No Known Activations