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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proper requests and expectations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĩµ
    -0.17
    mpeg
    -0.15
    ecies
    -0.15
    388
    -0.14
    Äįe
    -0.14
    urved
    -0.14
    Ä©nh
    -0.14
    £
    -0.14
     Go
    -0.14
    trak
    -0.14
    POSITIVE LOGITS
    olik
    0.17
    WSC
    0.16
    atin
    0.15
    =find
    0.14
    caffold
    0.14
    .documentation
    0.14
    ational
    0.14
    iton
    0.14
    unday
    0.14
     оÑĤд
    0.13
    Act Density 0.320%

    No Known Activations