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

    Neuronpedia

    INDEX
    Explanations

    references to academic dissertations and thesis work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lier
    -0.15
    §Ãĥ
    -0.14
     Dw
    -0.14
    gran
    -0.14
     Cop
    -0.14
     Shelter
    -0.14
    stm
    -0.14
     cess
    -0.14
    inet
    -0.14
    Cop
    -0.14
    POSITIVE LOGITS
    esor
    0.18
    aire
    0.17
    Ø·Ùĩ
    0.15
    ourcem
    0.15
    abeth
    0.15
    Ø®ÛĮ
    0.15
     padr
    0.15
    aten
    0.14
    ith
    0.14
    elay
    0.13
    Act Density 0.007%

    No Known Activations