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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their current or past roles in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥIJ
    -0.15
     appoint
    -0.14
    tical
    -0.14
    ´Ī
    -0.14
    vla
    -0.14
     hierarchy
    -0.13
    fern
    -0.13
    овÑĸд
    -0.13
    avia
    -0.13
     Turnbull
    -0.13
    POSITIVE LOGITS
     serve
    0.21
     served
    0.20
     serves
    0.20
    chet
    0.17
    Serve
    0.17
     serving
    0.17
    serve
    0.16
     bart
    0.16
     Serve
    0.15
    suma
    0.15
    Act Density 0.277%

    No Known Activations