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

    Neuronpedia

    INDEX
    Explanations

    references to legal punishments and conditions of imprisonment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogenerated
    -0.19
    argon
    -0.19
    chia
    -0.16
    ãĥªãĤ«
    -0.14
    .AF
    -0.14
    کرÛĮ
    -0.14
     smo
    -0.13
    亡
    -0.13
    assis
    -0.13
    oppel
    -0.13
    POSITIVE LOGITS
     torture
    0.29
     sentence
    0.27
     TORT
    0.26
     punishment
    0.25
     branding
    0.24
     Sentence
    0.24
     punishments
    0.23
     sentenced
    0.22
     execution
    0.22
     Tort
    0.22
    Act Density 0.160%

    No Known Activations