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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "name" and its derivatives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    io
    -0.15
    ives
    -0.15
    assis
    -0.15
    asan
    -0.14
    tring
    -0.14
    fx
    -0.14
     rad
    -0.14
    rat
    -0.14
     Crime
    -0.14
    tor
    -0.14
    POSITIVE LOGITS
    ridged
    0.15
    unset
    0.15
    SBATCH
    0.15
    Ñĥг
    0.15
    ICI
    0.15
     showc
    0.14
    .Reference
    0.14
    .Selenium
    0.14
    eba
    0.14
    casting
    0.14
    Act Density 0.048%

    No Known Activations