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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe mechanisms or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avin
    -0.15
    boy
    -0.15
    hit
    -0.14
    gram
    -0.14
    shelf
    -0.14
    oard
    -0.14
    jug
    -0.13
    than
    -0.13
    ught
    -0.13
     SOM
    -0.13
    POSITIVE LOGITS
    ioned
    0.16
    ród
    0.16
    ifu
    0.16
    angs
    0.15
    serrat
    0.15
    ufe
    0.15
     ÙĨÙĪÙģ
    0.14
    illas
    0.14
    ums
    0.14
    valuator
    0.14
    Act Density 0.023%

    No Known Activations