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

    Neuronpedia

    INDEX
    Explanations

    references to sections or categories formatted as "under [number]"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alon
    -0.17
    eum
    -0.16
    agu
    -0.16
    olon
    -0.15
     Townsend
    -0.14
    ahun
    -0.14
    shed
    -0.14
    CALE
    -0.14
    ilder
    -0.14
    åij½
    -0.14
    POSITIVE LOGITS
    437
    0.15
    esa
    0.15
    isz
    0.15
    asma
    0.15
    acio
    0.14
    akan
    0.14
    iez
    0.14
    spi
    0.14
    ascar
    0.14
    isclosed
    0.14
    Act Density 0.029%

    No Known Activations