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

    Neuronpedia

    INDEX
    Explanations

    references to legal accusations and the consequences of being involved in criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulo
    -0.15
    idar
    -0.15
     dumpsters
    -0.14
    lli
    -0.14
     mechanism
    -0.14
     exem
    -0.14
     Victims
    -0.13
     Sır
    -0.13
    à¹Ģลย
    -0.13
    oop
    -0.13
    POSITIVE LOGITS
     sed
    0.23
     treason
    0.18
     apost
    0.17
     aggravated
    0.17
    åı
    0.16
    membership
    0.16
     possession
    0.16
    Ĥ¹
    0.16
     Sed
    0.16
     inc
    0.16
    Act Density 0.112%

    No Known Activations