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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting variations

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

    places after periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.15
     myſelf
    -1.04
     Monfieur
    -0.92
     Reſ
    -0.86
     himſelf
    -0.84
    InputBorder
    -0.82
     themſelves
    -0.81
     photolibrary
    -0.81
    ImageContext
    -0.81
     Theſe
    -0.79
    POSITIVE LOGITS
     
    0.54
     di
    0.49
    Lähteet
    0.45
     sa
    0.44
     +
    0.44
    неопр
    0.43
     co
    0.42
     relâche
    0.42
    BeginInit
    0.42
    ParallelGroup
    0.42
    Act Density 0.006%

    No Known Activations