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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "comp" and its variants in various contexts, often related to computation or technology-related topics

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

    compartment, comprising, complementary, compiling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vermelhas
    -0.58
     kierow
    -0.50
     suivante
    -0.47
     légiti
    -0.46
    ']?>
    -0.45
     quiser
    -0.45
     énon
    -0.45
     prédé
    -0.45
    didSet
    -0.45
    <bos>
    -0.44
    POSITIVE LOGITS
    comp
    2.38
     Comp
    2.09
    Comp
    2.06
     comp
    2.06
    COMP
    1.73
     COMP
    1.73
     comps
    1.42
    comps
    1.38
     Compton
    1.18
     compl
    1.07
    Act Density 0.014%

    No Known Activations