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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic or professional credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nj
    -0.18
    iya
    -0.16
    eah
    -0.15
    riz
    -0.15
    arov
    -0.15
    iky
    -0.14
     Tick
    -0.14
    ös
    -0.14
    richt
    -0.14
    neh
    -0.14
    POSITIVE LOGITS
     Å
    0.25
     Åļ
    0.23
     Ziel
    0.22
    iec
    0.22
     Micha
    0.22
     Paw
    0.21
    ÄĻ
    0.21
    osi
    0.21
     Pie
    0.20
     Naw
    0.19
    Act Density 0.037%

    No Known Activations