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

    Neuronpedia

    INDEX
    Explanations

    references to excerpts from different sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.17
    acc
    -0.16
    jr
    -0.15
    ucken
    -0.15
    addock
    -0.15
    unal
    -0.15
    xiety
    -0.14
    ering
    -0.14
    ensch
    -0.14
     Excell
    -0.14
    POSITIVE LOGITS
     ex
    0.21
    remely
    0.19
    odus
    0.19
    uber
    0.18
     Ex
    0.17
    eter
    0.17
    ei
    0.17
    ̣
    0.17
    ãĥ³ãĥĪ
    0.17
    alted
    0.16
    Act Density 0.022%

    No Known Activations