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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.22
    hub
    -0.17
    arme
    -0.15
    apt
    -0.15
    lung
    -0.15
    lag
    -0.15
    ÑģÑı
    -0.14
     Hancock
    -0.14
    hone
    -0.14
    ãĤ¯ãĤ»
    -0.14
    POSITIVE LOGITS
    YC
    0.17
    بار
    0.16
    alysis
    0.15
     latter
    0.15
    745
    0.15
    YD
    0.15
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.15
    213
    0.15
    ylum
    0.15
    ecko
    0.15
    Act Density 0.039%

    No Known Activations