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

    Neuronpedia

    INDEX
    Explanations

    statements of opinion and assertion clarity

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

    which followed by a comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $_"
    -0.72
    ImageContext
    -0.71
    BeginContext
    -0.65
    Geplaatst
    -0.63
    InjectAttribute
    -0.62
     AssemblyCompany
    -0.62
     queſta
    -0.62
    ValueStyle
    -0.60
     houſe
    -0.60
     myſelf
    -0.60
    POSITIVE LOGITS
     which
    0.50
     Which
    0.49
     WHICH
    0.46
    which
    0.44
    Which
    0.43
     laquelle
    0.33
     vlast
    0.32
     major
    0.32
     pretty
    0.31
    стати
    0.31
    Act Density 0.119%

    No Known Activations