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

    Neuronpedia

    INDEX
    Explanations

    expressions related to effort and intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     marchés
    -0.51
     Facile
    -0.50
    astéro
    -0.48
     partida
    -0.48
    EXHIB
    -0.47
    mení
    -0.47
    bolt
    -0.46
    Ranks
    -0.46
     potentially
    -0.46
    าย
    -0.46
    POSITIVE LOGITS
    BeginContext
    0.73
     Chwiliwch
    0.66
     Vikipedi
    0.60
    StoryboardSegue
    0.59
    MemoryWarning
    0.59
    Personendaten
    0.56
    TestingModule
    0.56
    WriteAttribute
    0.55
     BoxFit
    0.54
     désolés
    0.53
    Act Density 0.199%

    No Known Activations