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

    Neuronpedia

    INDEX
    Explanations

    expressions related to evaluating performance and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anel
    -0.15
     çĶ±
    -0.15
    lef
    -0.15
    bull
    -0.15
    posit
    -0.14
    åĸ¶
    -0.14
    ethe
    -0.14
    etest
    -0.14
    Ì
    -0.14
     ext
    -0.14
    POSITIVE LOGITS
    iday
    0.15
    apat
    0.14
    allee
    0.14
    ertoire
    0.14
     ÐĴÑģ
    0.14
    sı
    0.14
     tròn
    0.14
    ÑĦек
    0.13
    ÏģιÏĥ
    0.13
    omnia
    0.13
    Act Density 0.048%

    No Known Activations