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

    Neuronpedia

    INDEX
    Explanations

    terms indicating quantity or degree, especially in relation to improvements or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pyx
    -0.16
    pent
    -0.15
    ãģ¾ãģ¾
    -0.14
    pedia
    -0.13
     paradox
    -0.13
    ehler
    -0.13
    293
    -0.13
    kv
    -0.13
    hle
    -0.13
    ing
    -0.13
    POSITIVE LOGITS
    itches
    0.16
    ÑĢÑıд
    0.15
    amy
    0.14
    appen
    0.14
    ollen
    0.14
     ERC
    0.14
    legt
    0.14
    dbl
    0.14
    emy
    0.14
    ewood
    0.14
    Act Density 0.028%

    No Known Activations