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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical accounts and narratives involving evidence and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rud
    -0.17
    lege
    -0.15
    iosper
    -0.15
     ãĢĬ
    -0.14
    vig
    -0.14
    mund
    -0.14
    ада
    -0.14
    \Mapping
    -0.14
    ediator
    -0.14
    ddit
    -0.14
    POSITIVE LOGITS
    utor
    0.15
     Tee
    0.15
    ¥IJ
    0.15
    渡
    0.15
    oodoo
    0.14
    /tos
    0.14
    âķĿ
    0.14
    //{↵
    0.13
    ãģĹãģ®
    0.13
    ãĢĭçļĦ
    0.13
    Act Density 0.296%

    No Known Activations