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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various contexts

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

    I find that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.48
     Вікіпе
    -0.47
     Photocase
    -0.45
     propOrder
    -0.44
     ligiloj
    -0.44
    ToRead
    -0.44
     dor
    -0.43
     readout
    -0.42
     valor
    -0.42
     дописавши
    -0.41
    POSITIVE LOGITS
    matchCondition
    0.52
     AssemblyCulture
    0.52
     nargin
    0.46
     experimentar
    0.42
    ficulties
    0.40
     bleek
    0.39
     AudioClip
    0.39
     rasanya
    0.38
    BagConstraints
    0.38
    fährt
    0.38
    Act Density 0.051%

    No Known Activations