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

    Neuronpedia

    INDEX
    Explanations

    emotional states and their impacts on individuals

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

    negative emotions and their consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.47
    PreferredItem
    -0.44
    putExtra
    -0.41
    gnore
    -0.40
     disambiguazione
    -0.39
    Personensuche
    -0.38
     zumal
    -0.37
    不说
    -0.36
    Industry
    -0.36
     guida
    -0.35
    POSITIVE LOGITS
    exitRule
    0.53
    KommentareTeilen
    0.51
     AppCompatTheme
    0.45
     disponibilités
    0.45
    eqn
    0.44
     Taktlose
    0.43
    ConstraintMaker
    0.42
    tagHelper
    0.42
    xase
    0.41
     createState
    0.40
    Act Density 0.022%

    No Known Activations