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

    Neuronpedia

    INDEX
    Explanations

    expressions of exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lingen
    -0.16
    acock
    -0.16
    etros
    -0.15
    oot
    -0.14
    ycz
    -0.14
    umph
    -0.13
     NSK
    -0.13
    à¥įषण
    -0.13
    quan
    -0.13
     LOD
    -0.13
    POSITIVE LOGITS
     Clem
    0.15
     Butt
    0.15
    zers
    0.14
    WC
    0.14
    iero
    0.14
    ogue
    0.14
    wm
    0.14
    Decoration
    0.14
    wc
    0.14
    noinspection
    0.14
    Act Density 0.027%

    No Known Activations