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

    Neuronpedia

    INDEX
    Explanations

    references to official reports and statements regarding regulatory actions or complaints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     question
    -0.19
    talk
    -0.18
     spoke
    -0.17
     Frage
    -0.16
     describe
    -0.16
    Talk
    -0.16
     express
    -0.16
    문ìĿĺ
    -0.15
    encent
    -0.15
     questions
    -0.15
    POSITIVE LOGITS
     wrote
    0.18
    rier
    0.18
     writes
    0.17
     learned
    0.17
     discovered
    0.16
     learns
    0.16
     reported
    0.16
    learn
    0.15
     cont
    0.15
     charged
    0.15
    Act Density 0.046%

    No Known Activations