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

    Neuronpedia

    INDEX
    Explanations

    phrases that express purpose or justification for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.73
     GenerationType
    -0.67
    AsUp
    -0.60
    MemoryWarning
    -0.59
     فريبيس
    -0.59
     configureStore
    -0.56
     Zig
    -0.55
     nahilalakip
    -0.54
    contentLoaded
    -0.54
    ロウィン
    -0.53
    POSITIVE LOGITS
     sake
    0.58
     purposes
    0.50
    findpost
    0.49
     Zwecke
    0.44
     kepentingan
    0.43
     Erhaltung
    0.42
     أجل
    0.42
     aşk
    0.41
     purpose
    0.40
     reasons
    0.40
    Act Density 0.238%

    No Known Activations