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

    Neuronpedia

    INDEX
    Explanations

    references to plugins in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    plug-in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Estatal
    -0.44
    tableFuture
    -0.42
     כה
    -0.37
    ellido
    -0.37
     heer
    -0.37
    akei
    -0.37
    ✯
    -0.37
     Heere
    -0.36
     höchst
    -0.36
    #!
    -0.36
    POSITIVE LOGITS
     plug
    2.38
     Plug
    2.31
    Plug
    2.22
    plug
    2.16
     plugs
    1.99
     PLUG
    1.95
    plugs
    1.80
    PLUG
    1.71
     plugging
    1.69
     plugged
    1.64
    Act Density 0.006%

    No Known Activations