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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating necessity or obligation

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

    by X means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.62
    istoitu
    -0.60
     ویکی‌پدیا
    -0.55
     ujednoznacz
    -0.53
    новниш
    -0.51
    Hochspringen
    -0.51
    లాలు
    -0.50
    Erreferentziak
    -0.49
    Geplaatst
    -0.49
    #+#
    -0.48
    POSITIVE LOGITS
     certainly
    0.54
     definitely
    0.50
    certainly
    0.47
     means
    0.46
     surely
    0.45
     zeker
    0.45
     Certainly
    0.44
     indeed
    0.44
     unquestionably
    0.44
     keineswegs
    0.43
    Act Density 0.004%

    No Known Activations