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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating advisory or cautionary statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.71
    InjectAttribute
    -0.64
    IsMutable
    -0.64
    TagHelper
    -0.63
     समीक्षाएं
    -0.61
    postsleuth
    -0.60
     חיצוניים
    -0.60
     competitively
    -0.59
    Tikang
    -0.59
    ✨:
    -0.58
    POSITIVE LOGITS
    yesterday
    0.56
     yesterday
    0.56
    everywhere
    0.55
     tomorrow
    0.54
    tomorrow
    0.52
     [
    0.50
     everywhere
    0.49
     paragraphe
    0.47
     sinned
    0.47
     saying
    0.46
    Act Density 0.159%

    No Known Activations