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

    Neuronpedia

    INDEX
    Explanations

    terms related to decisive actions or influences

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

    decisive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.61
     يتيمه
    -0.59
    AutoresizingMask
    -0.55
     grammes
    -0.54
    Хьажоргаш
    -0.52
    pecabe
    -0.51
     Houſe
    -0.50
     informée
    -0.50
     pleaſure
    -0.49
     automatique
    -0.48
    POSITIVE LOGITS
     decisive
    1.92
     decisively
    1.41
    cisive
    1.34
     decisivo
    1.30
     decisi
    1.30
    isive
    1.17
     conclusive
    0.92
     entscheid
    0.91
     decis
    0.89
     реша
    0.70
    Act Density 0.014%

    No Known Activations