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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the concept of scope or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ½
    -0.15
    ingga
    -0.15
    Kir
    -0.15
    onen
    -0.14
    oubted
    -0.14
    tuÄŁ
    -0.14
    ÃŃf
    -0.14
     Sabb
    -0.14
    gross
    -0.14
    rieg
    -0.14
    POSITIVE LOGITS
    fds
    0.14
    ãĥ¼ãĥį
    0.14
    eward
    0.14
     draining
    0.14
    tons
    0.14
    ounder
    0.14
    atos
    0.14
    elia
    0.13
    MISS
    0.13
     André
    0.13
    Act Density 0.022%

    No Known Activations