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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the degree of intensity or extent of a situation

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

    "so" followed by an adverb

    np_acts-logits-general · gemini-2.0-flash

    so followed by intensifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __
    -0.60
    Polish
    -0.58
     useParams
    -0.56
    poptosis
    -0.54
    ِ
    -0.54
     Polish
    -0.52
    polish
    -0.52
     verific
    -0.52
    Elmer
    -0.51
    IRL
    -0.51
    POSITIVE LOGITS
     so
    0.76
    这般
    0.74
     Soto
    0.71
     SO
    0.71
    zzleHttp
    0.71
    reportWebVitals
    0.70
     fubject
    0.68
    auso
    0.67
    Sooo
    0.65
     thyself
    0.65
    Act Density 0.122%

    No Known Activations