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

    Neuronpedia

    INDEX
    Explanations

    titles or references related to official roles or positions of authority in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.16
     ÐĶо
    -0.14
    bos
    -0.14
    fsp
    -0.14
    óln
    -0.14
    /status
    -0.14
    afort
    -0.14
    央
    -0.13
    าà¸ģ
    -0.13
     quartz
    -0.13
    POSITIVE LOGITS
    avin
    0.19
    /lic
    0.17
    ritis
    0.16
    械
    0.15
    Race
    0.15
     Race
    0.15
     Til
    0.14
    pak
    0.14
    deb
    0.14
    ode
    0.14
    Act Density 0.001%

    No Known Activations