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

    Neuronpedia

    INDEX
    Explanations

    conditional and sequential language indicative of processes or steps

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

    Following "once" or "after."

    np_acts-logits-general · gemini-2.0-flash

    once conditions met

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.66
     ModelRenderer
    -0.64
    лтемелер
    -0.60
    Personendaten
    -0.58
     ivelany
    -0.56
    UnknownFieldSet
    -0.56
     pinulongan
    -0.54
    MLLoader
    -0.54
    +#+
    -0.54
     utafitiHapana
    -0.54
    POSITIVE LOGITS
     acestei
    0.39
     anota
    0.36
     ejecut
    0.35
    たった
    0.34
     mať
    0.34
    これに
    0.33
    これが
    0.33
     tohto
    0.33
     this
    0.33
     ausreich
    0.32
    Act Density 0.293%

    No Known Activations