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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eld
    -0.17
     disappe
    -0.15
    ARI
    -0.14
     undermin
    -0.14
     misd
    -0.14
     prostit
    -0.14
     embod
    -0.14
    اÙĪÙĩ
    -0.14
     Airlines
    -0.14
     derec
    -0.14
    POSITIVE LOGITS
     sine
    0.19
    agens
    0.17
     Regina
    0.17
     Domino
    0.17
    familia
    0.16
     ("
    0.16
     pro
    0.16
    culus
    0.16
     Latin
    0.15
    quam
    0.15
    Act Density 0.078%

    No Known Activations