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

    Neuronpedia

    INDEX
    Explanations

    references to personal growth and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bara
    -0.18
    asta
    -0.17
    ouser
    -0.14
    iore
    -0.14
    interop
    -0.14
    aul
    -0.14
    avenport
    -0.14
    asa
    -0.14
    elor
    -0.13
    æĭĶ
    -0.13
    POSITIVE LOGITS
     initially
    0.27
     originally
    0.27
    Initially
    0.25
    æľĢåĪĿ
    0.23
     Initially
    0.23
    ä»Ĭ天
    0.20
     Originally
    0.20
    initial
    0.19
    Originally
    0.19
     initial
    0.19
    Act Density 0.237%

    No Known Activations