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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "knew" and its variations indicating knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kee
    -0.15
    chap
    -0.14
    uality
    -0.14
    rega
    -0.14
    achte
    -0.14
    ysqli
    -0.13
    ufe
    -0.13
    ummy
    -0.13
    DNA
    -0.13
    ager
    -0.13
    POSITIVE LOGITS
    Nonnull
    0.17
    lessly
    0.15
    098
    0.15
    彦
    0.14
    quarters
    0.13
    ESCO
    0.13
    errupt
    0.13
    -bg
    0.13
     miá»ģn
    0.13
    bias
    0.13
    Act Density 0.035%

    No Known Activations