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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate time or frequency

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

    determiners followed by common English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.56
    tried
    -0.43
    IndentedString
    -0.40
     disambiguazione
    -0.39
    HomeAsUpEnabled
    -0.39
     ujednoznacz
    -0.37
    lementary
    -0.36
     ró
    -0.35
    vamp
    -0.35
     Tried
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.66
     Erişim
    0.46
    SequentialGroup
    0.46
    windowFixed
    0.45
    //
    0.45
    iastes
    0.44
    /*
    0.44
     &___
    0.44
    complexContent
    0.43
     scattata
    0.42
    Act Density 0.247%

    No Known Activations