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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases that indicate support or recognition of individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rlen
    -0.14
    âĢ¦↵↵↵
    -0.14
    ĶåĽŀ
    -0.14
    ád
    -0.13
    usk
    -0.13
    esel
    -0.13
    uards
    -0.13
    oire
    -0.13
    usi
    -0.13
    ÅĻád
    -0.12
    POSITIVE LOGITS
    ãģķãĤī
    0.15
     klu
    0.13
     recep
    0.13
    ÙĬار
    0.13
    IALIZ
    0.12
     ÐŁÐ¾Ð²
    0.12
     teb
    0.12
    'gc
    0.12
    /ay
    0.11
    HING
    0.11
    Act Density 0.002%

    No Known Activations