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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with "how to" related to performing various tasks or functions

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

    Follows "How to" (or translations of "How to")

    np_acts-logits-general · gemini-2.0-flash

    how to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समीक्षाओं
    -0.42
    endios
    -0.41
     belangrij
    -0.39
    icanos
    -0.39
     faptul
    -0.37
     względu
    -0.37
     dachte
    -0.36
     companhia
    -0.36
     instituição
    -0.36
    Données
    -0.35
    POSITIVE LOGITS
    howto
    0.93
     كيفية
    0.61
     如何
    0.60
    Cách
    0.59
    如何
    0.59
     Cách
    0.58
     Cómo
    0.57
     cómo
    0.56
     canst
    0.56
    Рецепт
    0.55
    Act Density 0.149%

    No Known Activations