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

    Neuronpedia

    INDEX
    Explanations

    references to academic study and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĸĹ
    -0.15
    èĪŀ
    -0.15
    ãĥĥãĥģ
    -0.14
    -Agent
    -0.14
    æ®Ĭ
    -0.14
    ONT
    -0.14
    产
    -0.13
    adin
    -0.13
    infeld
    -0.13
     suspension
    -0.13
    POSITIVE LOGITS
     questions
    0.24
     reasoning
    0.19
     sectional
    0.19
    questions
    0.18
     RC
    0.18
     Fragen
    0.18
     Passage
    0.18
     asked
    0.17
     passage
    0.17
     Questions
    0.17
    Act Density 0.006%

    No Known Activations