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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the phrase "in other words."

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

    introduces enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orElseThrow
    -0.42
     infatti
    -0.35
    inigte
    -0.34
     indeed
    -0.32
    Bảo
    -0.31
    allclose
    -0.31
     assuredly
    -0.30
     Belief
    -0.30
     przede
    -0.30
     desee
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.68
    GEBURTSDATUM
    0.68
     kasarigan
    0.67
     nahilalakip
    0.67
    ValueStyle
    0.67
    帖最后由
    0.67
     שוליים
    0.66
    NameInMap
    0.63
    ConstraintMaker
    0.63
    adaptiveStyles
    0.62
    Act Density 0.009%

    No Known Activations