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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or the variability of outcomes

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

    "Not all/every/always"

    np_acts-logits-general · gemini-2.0-flash

    general statements are qualified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सन्दर्भ
    -0.66
     lenker
    -0.62
     Paglinawan
    -0.62
    MessageTagHelper
    -0.61
    JspWriter
    -0.57
     Numerade
    -0.57
     Virtually
    -0.56
     virtually
    -0.56
    Autoritní
    -0.54
    __":
    -0.53
    POSITIVE LOGITS
     nécessairement
    0.87
     necessarily
    0.78
     necessariamente
    0.77
     mulus
    0.70
     forcément
    0.69
     kaikk
    0.66
     nemmeno
    0.64
     necesariamente
    0.64
     perfetta
    0.62
     sepenuhnya
    0.61
    Act Density 0.225%

    No Known Activations