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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "more" in various contexts

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

    more and its qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bättre
    -0.48
     more
    -0.46
     closer
    -0.46
     duidelijk
    -0.44
     daha
    -0.44
     fiducia
    -0.42
    Aholisi
    -0.42
    تقاوى
    -0.41
    VersionUID
    -0.41
     betere
    -0.41
    POSITIVE LOGITS
     than
    0.46
     الرياضيه
    0.43
     otomatig
    0.42
     betweenstory
    0.41
    CppMethod
    0.40
    GMENT
    0.39
    IComponent
    0.39
    veless
    0.38
    lamabad
    0.37
     particuli
    0.37
    Act Density 0.057%

    No Known Activations