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

    Neuronpedia

    INDEX
    Explanations

    repetitive conjunctions and phrases indicating contrast or comparison

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

    "as" or "so" followed by "is/are/has/have/will"

    np_acts-logits-general · gemini-2.0-flash

    as well as, so does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.64
    TypedDataSet
    -0.62
     rood
    -0.60
     purpoſe
    -0.54
    ftagPool
    -0.53
     Offisielt
    -0.53
    Související
    -0.50
    τεύ
    -0.50
    irsten
    -0.50
     Dider
    -0.50
    POSITIVE LOGITS
     does
    1.07
     did
    0.98
     do
    0.81
     Does
    0.81
    Does
    0.74
     were
    0.73
    did
    0.72
     are
    0.69
    does
    0.69
    Did
    0.68
    Act Density 0.150%

    No Known Activations