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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and their relationships in contexts, like dates and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eskort
    -0.16
    oog
    -0.15
    ·»
    -0.15
    -"
    -0.15
    rzy
    -0.14
    gran
    -0.14
    é³¥
    -0.14
     "
    -0.14
    estre
    -0.14
    tern
    -0.14
    POSITIVE LOGITS
    âĦĸâĦĸ
    0.17
    leck
    0.15
    âĨĴâĨĴ
    0.14
    Ð¡Ð¡Ðł
    0.14
    454
    0.14
    ElementsBy
    0.13
    еко
    0.13
    ÅĤe
    0.13
    RLF
    0.13
    elman
    0.13
    Act Density 0.035%

    No Known Activations