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

    Neuronpedia

    INDEX
    Explanations

    the word "trip" in various forms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "tri" and its variations or contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IST
    -0.70
     deed
    -0.68
     deeds
    -0.67
    é»Ĵ
    -0.65
     CPC
    -0.64
     Goods
    -0.63
    nikov
    -0.63
    士
    -0.61
    manship
    -0.61
     saline
    -0.60
    POSITIVE LOGITS
    ppy
    1.23
    pling
    1.16
    ples
    1.14
    plets
    1.12
    assic
    1.11
    pped
    1.07
    pping
    1.06
    pled
    1.05
    umph
    1.04
    plet
    1.04
    Act Density 0.021%

    No Known Activations