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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal or fraudulent activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íļį
    -0.16
    οÏħÏģγ
    -0.15
    ooth
    -0.15
    òng
    -0.15
    éĺħ
    -0.15
    ãģ¡ãģ¯
    -0.14
    ÙĪدÛĮ
    -0.14
    ãĥªãĥ³ãĤ°
    -0.14
    ernals
    -0.14
    edis
    -0.14
    POSITIVE LOGITS
    eker
    0.15
     Murray
    0.15
    elles
    0.15
    _DECLARE
    0.15
     Wick
    0.15
    dzi
    0.15
    elda
    0.14
     Wein
    0.14
     Cure
    0.14
     Norman
    0.14
    Act Density 0.016%

    No Known Activations