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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to research topics and their significance in science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enia
    -0.15
    uin
    -0.15
    lein
    -0.14
    ÏĦαι
    -0.14
    ingleton
    -0.14
    ewan
    -0.14
    usk
    -0.14
    ovol
    -0.14
    linky
    -0.14
    oje
    -0.14
    POSITIVE LOGITS
    emey
    0.16
     yourself
    0.16
     Roch
    0.16
    utherford
    0.15
    952
    0.15
     yourselves
    0.15
    SPA
    0.15
    Ä°T
    0.14
    edException
    0.14
    exceptions
    0.14
    Act Density 0.001%

    No Known Activations