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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elez
    -0.15
    lists
    -0.15
    ibel
    -0.15
    roys
    -0.15
    olet
    -0.15
    ereo
    -0.14
    ics
    -0.14
    mast
    -0.14
    asc
    -0.14
    asha
    -0.14
    POSITIVE LOGITS
    CEE
    0.17
    寿
    0.15
    çķ
    0.14
     Essen
    0.14
    chie
    0.14
    ince
    0.14
    vik
    0.14
    sburg
    0.14
    åİŁæĿ¥
    0.14
     Ess
    0.13
    Act Density 0.042%

    No Known Activations