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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases or expressions that indicate a change in topic or additional information

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

    connecting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    genodigd
    -0.76
     californ
    -0.68
     Jefus
    -0.59
     fusca
    -0.59
     ſy
    -0.59
     Nikon
    -0.58
     ſta
    -0.58
     Houſe
    -0.58
     tranſ
    -0.58
     pneu
    -0.58
    POSITIVE LOGITS
     Dabei
    0.59
    으며
    0.57
     wobei
    0.55
    Dabei
    0.52
    omiast
    0.52
     โดย
    0.52
     있으며
    0.51
    HtmlAttribute
    0.49
    الحياه
    0.47
    brigens
    0.47
    Act Density 0.008%

    No Known Activations