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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing uncertainty or asking questions

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

    Followed by ":", ")", or "..."

    np_acts-logits-general · gemini-2.0-flash

    you/your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kháu
    -0.80
    存于互联网档案馆
    -0.75
    TagHelpers
    -0.73
     endblock
    -0.64
    makeText
    -0.63
    Portály
    -0.62
    InjectAttribute
    -0.62
    ArrowToggle
    -0.59
    Архівовано
    -0.57
     تانيه
    -0.57
    POSITIVE LOGITS
     your
    0.79
    Try
    0.72
     you
    0.71
    Your
    0.70
     yourself
    0.68
     Try
    0.68
    You
    0.67
    your
    0.66
     You
    0.65
     likely
    0.65
    Act Density 0.374%

    No Known Activations